The DOI matches its Crossref record; 289 of the 289 references it cites were found in a registry or an index; 3 of the 129 sources its claims cite were checked for support.
An overview of deep learning in medical imaging focusing on MRI
Open accessAbstract
What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI. Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of deep learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This narrative review surveys deep learning in medical imaging with a focus on MRI, covering the MRI processing chain from acquisition and reconstruction to segmentation, diagnosis, and image retrieval. It argues that deep learning is already state-of-the-art in many imaging tasks but faces major challenges in data access, interpretability, workflow integration, and regulation.
Key findings
- Deep learning, especially CNNs, has become the de facto standard for many computer vision and medical image analysis tasks, and is being applied across the entire MRI workflow: acquisition/reconstruction, QSM and MR fingerprinting, denoising, super-resolution, synthesis, registration, segmentation, diagnosis/prediction, and content-based image retrieval.
- In MR fingerprinting, Cohen et al.’s DRONE network reconstructed in 10 to 70 ms per slice, reported as 300 to 5000 times faster than conventional dictionary matching; Hoppe et al. reported matching one time series about 100 times faster than the conventional method.
- QSMnet was trained on 60 scans from 12 healthy volunteers; DeepResolve used thin knee slices from 124 patients for training and 17 for testing, with 10 s inference time per 3D 344 × 344 × 160 volume.
- Early deep learning for medical CBIR was disappointing: Sklan et al. reported a true positive rate of 20% on an independent test set of 2100 labeled images, though the paper states medical CBIR is now dominated by deep learning algorithms.
Methods
- Narrative overview/review, not a systematic review or meta-analysis; the authors state three aims: introduce deep learning, indicate applications across the MRI processing chain, and point to educational resources, open-source code, data, and problems.
- No primary data collection or new experiments; the paper synthesizes cited literature and examples across MRI acquisition, reconstruction, quantitative parameter mapping, image restoration, super-resolution, synthesis, registration, segmentation, diagnosis/prediction, and CBIR.
- Includes short lists/tables of openly available code, medical imaging datasets/repositories, and competitions.
Limitations
- The paper states it does not survey the entire landscape and is not comprehensive; it focuses particularly on MRI and selected organs/applications.
- The paper states general and domain-specific challenges: lack of mathematical/theoretical underpinnings, difficulty interpreting “black box” predictions, data access/privacy issues, deep networks’ large training-data requirements, 3D CNN constraints, workflow integration, and regulatory/ethical/legal hurdles.
- Evident from the text: as a narrative review without a systematic search protocol or quantitative synthesis, it cannot estimate effect sizes, prevalence, or comparative performance across the field.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
54 Not checked yet · 23 Own interpretation · 11 No basis given · 7 Sources not found · 1 Partly supported · accuracy not yet measured
In the paper
“One can also do interorgan transfer learning in 3D, an idea we have used for kidney segmentation, where pre-training a network to do brain segmentation decreased the number of annotated kidneys needed to achieve good segmentation performance [342].”
What the sources say
- Not checked yetcites [342] [342] A. Lundervold, A. Lundervold, J. Rørvik, Fast semisupervised segmentation of the kidneys in DCEMRI using convolutional neural networks and transfer learning, 2017. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“They can also be used to reduce the gadolinium dose in contrast-enhanced brain MRI by an order of magnitude [88] without significant reduction in image quality.”
What the sources say
- Not checked yetcites [88] [88] E. Gong, J. M. Pauly, M. Wintermark, G. Zaharchuk, Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI, Journal of magnetic resonance imaging 48 (2018) 330-340. - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“By having each filter share the exact same weights across the whole input domain, i.e. translational equivariance at each layer, one achieves a drastic reduction in the number of weights that need to be learned.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Their autoencoder network outperformed the current FSL SUSAN denoising software according to peak signal-to-noise ratios.”
What the sources say
- Not matchedcites [180] [180] C. Bermudez, A. J. Plassard, T. L. Davis, A. T. Newton, S. M. Resnick, B. A. Landman, Learning implicit brain MRI manifolds with deep learning, Proceedings of SPIE-the International Society for Optical Engineering 10574 (2018). -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainn = 500- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“The authors achieved comparable tumor segmentation results when trained on the synthetic data rather than on real patient data.”
What the sources say
- Not matchedcites [213] [213] H.-C. Shin, N. A. Tenenholtz, J. K. Rogers, C. G. Schwarz, M. L. Senjem, J. L. Gunter, K. P. Andriole, M. Michalski, Medical Image Synthesis for Data Augmentation and Anonymization Using Generative Adversarial Networks, in: International Workshop on Simulation and Synthesis in Medical Imaging, Springer, pp. 1-11. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“Recently, deep learning methodology has been applied to MR fingerprinting.”
What the sources say
- Not checked yetcites [165] [165] O. Cohen, B. Zhu, M. S. Rosen, MR fingerprinting deep reconstruction network (DRONE), Magnetic resonance in medicine 80 (2018) 885-894. -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“This three-layer network outperformed both the standard MRF techniques based on dictionary matching, and also the analogous real neural network operating on the real and imaginary components separately.”
What the sources say
- Not matchedcites [169] [169] P. Virtue, S. X. Yu, M. Lustig, Better than real: Complex-valued neural nets for MRI fingerprinting, in: Proc. IEEE Int. Conf. Image Processing (ICIP), pp. 3953-3957. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“Recently, deep learning methods have been applied to image registration in order to improve accuracy and speed (e.g. Section 3.4 in [42]).”
What the sources say
- Not checked yetcites [42] [42] G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. W. M. van der Laak, B. van Ginneken, C. I. Snchez, A survey on deep learning in medical image analysis., Medical image analysis 42 (2017) 60-88. - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Recently Yoon et al. [147] constructed a three-dimensional CNN, named QSMnet and based on the U-Net architecture, able to generate high quality susceptibility source maps from single orientation data.”
What the sources say
- Not checked yetcites [147] [147] J. Yoon, E. Gong, I. Chatnuntawech, B. Bilgic, J. Lee, W. Jung, J. Ko, H. Jung, K. Setsompop, G. Zaharchuk, E. Y. Kim, J. Pauly, J. Lee, Quantitative susceptibility mapping using deep neural network: QSMnet., NeuroImage 179 (2018) 199-206. - source
plaindirectn = 12- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“The qualitative and quantitative (MSE) denoising results were better than spatiotemporal Beltrami, moving average, the dynamic Non Local Means method [182], and stacked denoising autoencoders [183].”
What the sources say
- Not checked yetcites [181] [181] A. Benou, R. Veksler, A. Friedman, T. Riklin Raviv, Ensemble of expert deep neural networks for spatiotemporal denoising of contrast-enhanced MRI sequences, Medical image analysis 42 (2017) 145-159. - source
- Not checked yetcites [182] [182] Y. Gal, A. J. H. Mehnert, A. P. Bradley, K. McMahon, D. Kennedy, S. Crozier, Denoising of dynamic contrast-enhanced MR images using dynamic nonlocal means, IEEE transactions on medical imaging 29 (2010) 302-310. - source
- Not matchedcites [183] [183] P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, P.-A. Manzagol, Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion, Journal of Machine Learning Research (JMLR) 11 (2010) 3371-3408. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainn = 33- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Employing least-squares generative adversarial networks (GANs) that learns texture details and suppresses high-frequency noise, [139] created a novel compressed sensing framework that can produce diagnostic quality reconstructions 'on the fly' (30 ms) 29 .”
What the sources say
- Not matchedcites [139] [139] M. Mardani, E. Gong, J. Y. Cheng, S. S. Vasanawala, G. Zaharchuk, L. Xing, J. M. Pauly, Deep generative adversarial neural networks for compressive sensing (GANCS) MRI., IEEE transactions on medical imaging (2018). -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“They found their reconstruction time (10 to 70 ms per slice) to be 300 to 5000 times faster than conventional dictionary-matching techniques, using both well-characterized calibrated ISMRM/NIST phantoms and in vivo human brains.”
What the sources say
- Not checked yetcites [165] [165] O. Cohen, B. Zhu, M. S. Rosen, MR fingerprinting deep reconstruction network (DRONE), Magnetic resonance in medicine 80 (2018) 885-894. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Recently deep learning approaches has been introduced, e.g. generating super-resolution single (no reference information) and multi-contrast (applying a high-resolution image of another modality as reference) brain MR images using CNNs [197]; constructing superresolution brain MRI by a CNN stacked by multi-scale fusion units [198]; and super-resolution musculoskeletal MRI ('DeepResolve') [199].”
What the sources say
- Not checked yetcites [197] [197] K. Zeng, H. Zheng, C. Cai, Y. Yang, K. Zhang, Z. Chen, Simultaneous single- and multi-contrast super-resolution for brain MRI images based on a convolutional neural network., Computers in biology and medicine 99 (2018) 133-141. - source
- Not checked yetcites [198] [198] C. Liu, X. Wu, X. Yu, Y. Tang, J. Zhang, J. Zhou, Fusing multi-scale information in convolution network for mr image super-resolution reconstruction., Biomedical engineering online 17 (2018) 114. - source
- Not checked yetcites [199] [199] A. S. Chaudhari, Z. Fang, F. Kogan, J. Wood, K. J. Stevens, E. K. Gibbons, J. H. Lee, G. E. Gold, B. A. Hargreaves, Super-resolution musculoskeletal MRI using deep learning, Magnetic resonance in medicine 80 (2018) 2139-2154. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Another important application area is advanced deformable image registration, enabling quantitative analysis across different physical imaging modalities and across time.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This suggested that complex-valued networks are better suited at uncovering information in complex data.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“MR image segmentation using deep learning approaches, typically CNNs, are now penetrating the whole field of applications.”
What the sources say
- Not checked yetcites [263] [263] L. Chen, P. Bentley, D. Rueckert, Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks, NeuroImage. Clinical 15 (2017) 633-643. - source
- Not checked yetcites [264] [264] M. Havaei, A. Davy, D. Warde-Farley, A. Biard, A. Courville, Y. Bengio, C. Pal, P.-M. Jodoin, H. Larochelle, Brain tumor segmentation with deep neural networks, Medical image analysis 35 (2017) 18-31. - source
- Not checked yetcites [265] [265] H. Choi, K. H. Jin, Fast and robust segmentation of the striatum using deep convolutional neural networks, Journal of Neuroscience Methods 274 (2016) 146-153. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“In addition to producing valuable measures that function as uncertainty measures [358, 359, 66], these techniques can also lessen deep neural networks susceptibility to adversarial attacks [357, 360].”
What the sources say
- Not checked yetcites [358] [358] C. Leibig, V. Allken, M. S. Ayhan, P. Berens, S. Wahl, Leveraging uncertainty information from deep neural networks for disease detection, Scientific reports 7 (2017) 17816. - source
- Not checked yetcites [359] [359] A. Kendall, V. Badrinarayanan, R. Cipolla, Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding, arXiv preprint arXiv:1511.02680 (2015). - source
- Not checked yetcites [66] [66] K. Wickstrøm, M. Kampffmeyer, R. Jenssen, Uncertainty Modeling and Interpretability in Convolutional Neural Networks for Polyp Segmentation, in: 2018 IEEE 28 th International Workshop on Machine Learning for Signal Processing (MLSP), IEEE, pp. 1-6. - source
- Not matchedcites [357] [357] Y. Li, Y. Gal, Dropout Inference in Bayesian Neural Networks with Alpha-divergences, in: International Conference on Machine Learning, pp. 2052-2061. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [360] [360] R. Feinman, R. R. Curtin, S. Shintre, A. B. Gardner, Detecting adversarial samples from artifacts, arXiv preprint arXiv:1703.00410 (2017). - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Considering the large difference between the high-quality images one typically work with when doing research and the messiness of the real, clinical world, this can be a major obstacle when putting deep learning systems into production.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: The high-quality images one typically works with in research differ from the messiness of the real clinical world.
None of the sources cited for this claim have been checked yet.
In the paper
“Medical CBIR is now, however, dominated by deep learning algorithms [311, 312, 313].”
What the sources say
- Not checked yetcites [311] [311] R. S. Bressan, D. H. A. Alves, L. M. Valerio, P. H. Bugatti, P. T. M. Saito, DOCToR: the role of deep features in content-based mammographic image retrieval, in: Proc. IEEE 31st Int. Symp. ComputerBased Medical Systems (CBMS), pp. 158-163. - source
- Not checked yetcites [312] [312] A. Qayyum, S. M. Anwar, M. Awais, M. Majid, Medical image retrieval using deep convolutional neural network, arXiv preprint arXiv:1703.08472v1 (2017). - source
- Not checked yetcites [313] [313] Y.-A. Chung, W.-H. Weng, Learning deep representations of medical images using siamese CNNs with application to content-based image retrieval, arXiv preprint arXiv:1711.08490v2 (2017). - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“One quickly meet challenges associated to memory and compute consumption when using CNNs with higher-dimensional image data, challenges that researchers are trying various approaches to deal with (treating 3D as stacks of 2Ds, patch- or segment-based training and inference, downscaling, etc).”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Even hiding the model and only exposing a prediction interface would still leave it open to attack, for example in the form of model-inversion [331] and membership attacks [332].”
What the sources say
- Not checked yetcites [331] [331] M. Fredrikson, S. Jha, T. Ristenpart, Model inversion attacks that exploit confidence information and basic countermeasures, in: Proceedings of the 22 nd ACM SIGSAC Conference on Computer and Communications Security, ACM, pp. 1322-1333. -
- Not checked yetcites [332] [332] R. Shokri, M. Stronati, C. Song, V. Shmatikov, Membership inference attacks against machine learning models, in: Security and Privacy (SP), 2017 IEEE Symposium on, IEEE, pp. 3-18. -
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“It is not enough to merely restrict access to the training set used to construct the model, as it is easy to use the model itself to discover details about the training set [330].”
What the sources say
- Not checked yetcites [330] [330] C. Zhang, S. Bengio, M. Hardt, B. Recht, O. Vinyals, Understanding deep learning requires rethinking generalization, arXiv preprint arXiv:1611.03530 (2016). -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“If the training samples are from a data distribution that is very different from the one met in the real world, then the network's generalization performance will be lower than expected. See [341] for a recent exploration of this issue.”
What the sources say
- Not checked yetcites [341] [341] J. R. Zech, M. A. Badgeley, M. Liu, A. B. Costa, J. J. Titano, E. K. Oermann, Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study, PLoS medicine 15 (2018). -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Probably not a substantial claim. 64
- It may state two separate claims as one. 33
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“They are, however, not limited to image processing and analysis but are outperforming other approaches in areas like natural language processing [3, 4, 5], speech recognition and synthesis [6, 7] 2 , and in the analysis of unstructured, tabular-type data using entity embeddings [8, 9].”
What the sources say
- Supportedcites [3] [3] M. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, L. Zettlemoyer, Deep contextualized word representations, in: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), volume 1, pp. 2227-2237. - source
This source is cited for the natural-language-processing portion of the sentence, not for speech or tabular data. In §4 Evaluation (page unavailable), the paper reports that adding its deep contextualized representations established a new state-of-the-art result on each of six benchmark NLP tasks. (LLM, conf=0.90)
- Not matchedcites [4] [4] J. Howard, S. Ruder, Universal language model finetuning for text classification, in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pp. 328-339. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [5] [5] A. Radford, K. Narasimhan, T. Salimans, I. Sutskever, Improving language understanding by generative pre-training (2018). -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Partly supportedcites [6] [6] W. Xiong, L. Wu, F. Alleva, J. Droppo, X. Huang, A. Stolcke, The Microsoft 2017 Conversational speech recognition system, in: Proc. Speech and Signal Processing (ICASSP) 2018 IEEE Int. Conf. Acoustics, pp. 5934-5938. [54 http://p4mi.org](http://p4mi.org/) - sourceExperimental — accuracy not yet measured
The Introduction (p. 1) attributes substantial gains in conversational speech recognition to deep networks, and the Conclusions (p. 6) report a further reduction in word error rate. This citation is attached to “speech recognition and synthesis”; our copy supports recognition but does not address speech synthesis. The separate citations for natural language processing and tabular data are outside this verdict. (LLM, conf=0.88)
- Partly supportedcites [7] [7] A. van den Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner, A. Senior, K. Kavukcuoglu, WaveNet: A generative model for raw audio, arXiv preprint arXiv:1609.03499v2 (2016). - sourceExperimental — accuracy not yet measured
The Conclusion (p. 8) says WaveNet outperformed the best existing text-to-speech systems in subjective naturalness. The Speech Recognition section (p. 8) reports the best TIMIT score, to the authors’ knowledge, specifically among models trained directly on raw audio—not superiority over speech-recognition approaches generally. The NLP and tabular-data portions of the citing sentence have separate citations and are not attributed to this paper. (LLM, conf=0.86)
- Not checked yetcites [8] [8] C. Guo, F. Berkhahn, Entity embeddings of categorical variables, arXiv preprint arXiv:1604.06737 (2016). - source
- Not checked yetcites [9] [9] A. De Br´ ebisson, ´ E. Simon, A. Auvolat, P. Vincent, Y. Bengio, Artificial neural networks applied to taxi destination prediction, arXiv preprint arXiv:1508.00021 (2015). - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Supported
In the paper
“Convolutional neural networks can be used for efficiency improvement in radiology practices through protocol determination based on short-text classification [87].”
What the sources say
- Not checked yetcites [87] [87] Y. H. Lee, Efficiency improvement in a busy radiology practice: Determination of musculoskeletal magnetic resonance imaging protocol using deeplearning convolutional neural networks., Journal of digital imaging (2018). - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This change is thanks to the growth of big data , powerful processors for parallel computations (in particular, GPUs), some important tweaks to the algorithms used to construct and train the networks, and the development of easy-to-use software frameworks.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Most famously on the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) 1 in 2012 [1] when a deep learning model (a convolutional neural network ) halved the second best error rate on the image classification task.”
What the sources say
- Not checked yetcites [1] [1] A. Krizhevsky, I. Sutskever, G. E. Hinton, ImageNet classification with deep convolutional neural networks, in: F. Pereira, C. J. C. Burges, L. Bottou, K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems 25, Curran Associates, Inc., 2012, pp. 1097-1105. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Deep learning rose to its prominent position in computer vision when neural networks started outperforming other methods on several high-profile image analysis benchmarks.”
What the sources say
- Not checked yetcites [1] [1] A. Krizhevsky, I. Sutskever, G. E. Hinton, ImageNet classification with deep convolutional neural networks, in: F. Pereira, C. J. C. Burges, L. Bottou, K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems 25, Curran Associates, Inc., 2012, pp. 1097-1105. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Artificial neural networks (ANNs) is one of the most famous machine learning models, introduced already in the 1950s, and actively studied since [41, Chapter 1.2].”
What the sources say
- Not checked yetcites [41, Chapter 1.2]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In deep learning, the computers learn useful representations and features automatically, directly from the raw data, bypassing this manual and difficult step.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Interestingly, CNNs was applied in medical image analysis already in the early 90s, e.g. [58], but with limited success.”
What the sources say
- Not checked yetcites [58] [58] S. C. Lo, M. T. Freedman, J. S. Lin, S. K. Mun, Automatic lung nodule detection using profile matching and back-propagation neural network techniques., Journal of digital imaging 6 (1993) 4854. -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Healthcare applications of deep learning range from one-dimensional biosignal analysis [17] and the prediction of medical events, e.g. seizures [18] and cardiac arrests [19], to computer-aided detection [20] and diagnosis [21] supporting clinical decision making and survival analysis [22], to drug discovery [23] and as an aid in therapy selection and pharmacogenomics [24], to increased operational”
What the sources say
- Not checked yetcites [17] [17] N. Ganapathy, R. Swaminathan, T. M. Deserno, Deep learning on 1-D biosignals: a taxonomy-based survey, Yearbook of medical informatics 27 (2018) 98-109. - source
- Not checked yetcites [20] [20] H.-C. Shin, H. R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, J. Yao, D. Mollura, R. M. Summers, Deep convolutional neural networks for computeraided detection: Cnn architectures, dataset characteristics and transfer learning., IEEE transactions on medical imaging 35 (2016) 1285-1298. - source
- Not matchedcites [23] [23] J. Jim´ enez, M. ˇ Skaliˇ c, G. Mart´ ınez-Rosell, G. De Fabritiis, KDEEP: Protein-Ligand absolute binding affinity prediction via 3D-Convolutional Neural Networks, Journal of Chemical Information and Modeling 58 (2018) 287-296. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“In medical imaging the interest in deep learning is mostly triggered by convolutional neural networks (CNNs) [57] 15 , a powerful way to learn useful representations of images and other structured data.”
What the sources say
- Not checked yetcites [57] [57] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proceedings of the IEEE 86 (1998) 22782324. - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Deep learning is applied in radiotherapy [89], in PET-MRI attenuation correction [90, 91], in radiomics [92, 93]”
What the sources say
- Not checked yetcites [90] [90] F. Liu, H. Jang, R. Kijowski, T. Bradshaw, A. B. McMillan, Deep learning MR imaging-based attenuation correction for PET/MR imaging, Radiology 286 (2018) 676-684. - source
- Not checked yetcites [91] [91] A. Mehranian, H. Arabi, H. Zaidi, Vision 20/20: Magnetic resonance imaging-guided attenuation correction in pet/mri: Challenges, solutions, and opportunities., Medical physics 43 (2016) 11301155. - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“there are several strong initiatives across academia, and multiple large companies are pursuing healthcare projects based on machine learning.”
What the sources say
- Not checked yetcites [29] [29] V. Gulshan, L. Peng, M. Coram, M. C. Stumpe, D. Wu, A. Narayanaswamy, S. Venugopalan, K. Widner, T. Madams, J. Cuadros, et al., Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, Jama 316 (2016) 2402-2410. - source
- Not checked yetcites [30] [30] R. Poplin, A. V. Varadarajan, K. Blumer, Y. Liu, M. McConnell, G. Corrado, L. Peng, D. Webster, Predicting Cardiovascular Risk Factors in Retinal Fundus Photographs using Deep Learning, Nature Biomedical Engineering (2018). - source
- Not checked yetcites [31] [31] R. Poplin, P.-C. Chang, D. Alexander, S. Schwartz, T. Colthurst, A. Ku, D. Newburger, J. Dijamco, N. Nguyen, P. T. Afshar, S. S. Gross, L. Dorfman, C. Y. McLean, M. A. DePristo, A universal SNP and small-indel variant caller using deep neural networks, Nature Biotechnology (2018). - source
- Not checked yetcites [32] [32] J. De Fauw, J. R. Ledsam, B. Romera-Paredes, S. Nikolov, N. Tomasev, S. Blackwell, H. Askham, X. Glorot, B. O'Donoghue, D. Visentin, et al., Clinically applicable deep learning for diagnosis and referral in retinal disease, Nature medicine 24 (2018) 1342. - source
- Not checked yetcites [33] [33] Y. Qin, K. Kamnitsas, S. Ancha, J. Nanavati, G. Cottrell, A. Criminisi, A. Nori, Autofocus Layer for Semantic Segmentation, arXiv preprint arXiv:1805.08403 (2018). - source
- Not matchedcites [34] [34] K. Kamnitsas, C. Baumgartner, C. Ledig, V. Newcombe, J. Simpson, A. Kane, D. Menon, A. Nori, A. Criminisi, D. Rueckert, et al., Unsupervised domain adaptation in brain lesion segmentation with adversarial networks, in: International Conference on Information Processing in Medical Imaging, Springer, pp. 597-609. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Rests on an assumption: The use of machine learning in general and deep learning in particular within healthcare is still in its infancy.
In the paper
“Removing the pooling layers simplifies the network architecture without necessarily sacrificing performance [62].”
What the sources say
- Not checked yetcites [62] [62] J. T. Springenberg, A. Dosovitskiy, T. Brox, M. Riedmiller, Striving for simplicity: The all convolutional net, arXiv preprint arXiv:1412.6806 (2014). -
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“A CNN architecture designed by a neural network, beating all the previous human-designed networks at the ILSVRC competition.”
What the sources say
- Not checked yetcites [77] [77] B. Zoph, V. Vasudevan, J. Shlens, Q. V. Le, Learning transferable architectures for scalable image recognition, arXiv preprint arXiv:1707.07012 2 (2017). -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“This makes it possible for the entire neural network to approximate almost any nonlinear function [48, 49] 19”
What the sources say
- Not matchedcites [48] [48] M. Leshno, V. Y. Lin, A. Pinkus, S. Schocken, Multilayer feedforward networks with a nonpolynomial activation function can approximate any function, Neural networks 6 (1993) 861-867. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [49] [49] S. Sonoda, N. Murata, Neural network with unbounded activation functions is universal approximator, Applied and Computational Harmonic Analysis 43 (2017) 233-268. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
None of the sources cited for this claim have been checked yet.
In the paper
“In the early days of modern deep learning one tended to use very simple combinations of the building blocks, as in Lenet [57] and AlexNet [1].”
What the sources say
- Not checked yetcites [57] [57] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proceedings of the IEEE 86 (1998) 22782324. - source
- Not matchedcites [1] [1] A. Krizhevsky, I. Sutskever, G. E. Hinton, ImageNet classification with deep convolutional neural networks, in: F. Pereira, C. J. C. Burges, L. Bottou, K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems 25, Curran Associates, Inc., 2012, pp. 1097-1105. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“A 152 layer deep ResNet won the 2015 ILSVRC competition, and the authors also successfully trained a version with 1001 layers.”
What the sources say
- Not checked yetcites [72] [72] K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778. -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Deep learning is applied in radiotherapy [89], in PET-MRI attenuation correction [90, 91], in radiomics [92, 93]”
What the sources say
- Not checked yetcites [92] [92] J. Lao, Y. Chen, Z.-C. Li, Q. Li, J. Zhang, J. Liu, G. Zhai, A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme., Scientific reports 7 (2017) 10353. - source
- Not checked yetcites [93] [93] L. Oakden-Rayner, G. Carneiro, T. Bessen, J. C. Nascimento, A. P. Bradley, L. J. Palmer, Precision radiology: Predicting longevity using feature engineering and deep learning methods in a radiomics framework., Scientific reports 7 (2017) 1648. - source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“The network that launched the current deep learning boom by winning the 2012 ILSVRC competition by a huge margin.”
What the sources say
- Not checked yetcites [1] [1] A. Krizhevsky, I. Sutskever, G. E. Hinton, ImageNet classification with deep convolutional neural networks, in: F. Pereira, C. J. C. Burges, L. Bottou, K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems 25, Curran Associates, Inc., 2012, pp. 1097-1105. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Deep learning techniques have become the de facto standard for a wide variety of computer vision problems.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“But by now, artificial neural networks form one of the dominant methods in machine learning, and the most intensively studied.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Once it became possible to use features learned directly from the data, many of the handcrafted image features were typically left by the wayside as they turned out to be almost worthless compared to feature detectors found by CNNs.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Deep learning methods are increasingly used to improve clinical practice, and the list of examples is long, growing daily.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Including batch normalization layers forces the network to periodically change its activations to zero mean and unit standard deviation as the training batch hits these layers, which works as a regularizer for the network, speeds up training, and makes it less dependent on careful parameter initialization [67].”
What the sources say
- Not checked yetcites [67] [67] S. Ioffe, C. Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, in: International Conference on Machine Learning, pp. 448-456. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Introduced skip connections , which makes it possible to train much deeper networks.”
What the sources say
- Not checked yetcites [72] [72] K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“These can also be used for biological image synthesis [208, 209] and text-to-image synthesis [210, 211, 212].”
What the sources say
- Not checked yetcites [208] [208] A. Osokin, A. Chessel, R. E. C. Salas, F. Vaggi, Gans for biological image synthesis, in: Proc. IEEE Int. Conf. Computer Vision (ICCV), pp. 2252-2261. -
- Not checked yetcites [209] [209] G. Antipov, M. Baccouche, J. Dugelay, Face aging with conditional generative adversarial networks, in: Proc. IEEE Int. Conf. Image Processing (ICIP), pp. 2089-2093. - source
- Not checked yetcites [210] [210] C. Bodnar, Text to image synthesis using generative adversarial networks, arXiv preprent arXiv:1805.00676v1 (2018). - source
- Not checked yetcites [211] [211] H. Dong, S. Yu, C. Wu, Y. Guo, Semantic image synthesis via adversarial learning, arXiv preprint arXiv:1707.06873v1 (2017). -
- Not checked yetcites [212] [212] S. Reed, Z. Akata, X. Yan, L. Logeswaran, B. Schiele, H. Lee, Generative adversarial text to image synthesis, arXiv preprint arXiv:1605.05396v2 (2016). -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“convolutional recurrent neural networks for dynamic MR image reconstruction [135], reconstructing good quality cardiac MR images from highly undersampled complex-valued k -space data by learning spatio-temporal dependencies, outperforming 3D CNN approaches and compressed sensing-based dynamic MRI reconstruction algorithms in computational complexity, reconstruction accuracy and speed for different”
What the sources say
- Not checked yetcites [135] [135] C. Qin, J. V. Hajnal, D. Rueckert, J. Schlemper, J. Caballero, A. N. Price, Convolutional recurrent neural networks for dynamic mr image reconstruction., IEEE transactions on medical imaging (2018). - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“A unified framework for image reconstruction [140], called automated transform by manifold approximation (AUTOMAP) consisting of a feedforward deep neural network with fully connected layers followed by a sparse convolutional autoencoder, formulate image reconstruction generically as a data-driven supervised learning task that generates a mapping between the sensor and the image domain based on an”
What the sources say
- Not checked yetcites [140] [140] B. Zhu, J. Z. Liu, S. F. Cauley, B. R. Rosen, M. S. Rosen, Image reconstruction by domain-transform manifold learning., Nature 555 (2018) 487-492. - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“The last couple of years have seen impressive results for photo-realistic image synthesis using deep learning techniques, especially generative adversarial networks (GANs, introduced by Goodfellow et al. in 2014 [80]), e.g. [205, 206, 207].”
What the sources say
- Not checked yetcites [80] [80] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative Adversarial Nets, in: Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems 27, Curran Associates, Inc., 2014, pp. 2672-2680. -
- Not checked yetcites [205] [205] A. Creswell, T. White, V. Dumoulin, K. Arulkumaran, B. Sengupta, A. A. Bharath, Generative adversarial networks: An overview, IEEE Signal Processing Magazine 35 (2018) 53-65. -
- Not checked yetcites [206] [206] Y. Hong, U. Hwang, J. Yoo, S. Yoon, How generative adversarial networks and their variants work: An overview of GAN, arXiv preprint arXiv:1711.05914v7 (2017). -
- Not checked yetcites [207] [207] H. Huang, P. S. Yu, C. Wang, An introduction to image synthesis with generative adversarial nets, arXiv preprint arXiv:1803.04469v1 (2018). -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Super-resolution for MRI have been around for almost 10 years [192, 193] and can be used to improve the trade-off between resolution, SNR, and acquisition time [194], generate 7T-like MR images on 3T MRI scanners [195], or obtain super-resolution T 1 maps from a set of low resolution T 1 weighted images [196].”
What the sources say
- Not checked yetcites [194] [194] E. Plenge, D. H. J. Poot, M. Bernsen, G. Kotek, G. Houston, P. Wielopolski, L. van der Weerd, W. J. Niessen, E. Meijering, Super-resolution methods in mri: can they improve the trade-off between resolution, signal-to-noise ratio, and acquisition time?, Magnetic resonance in medicine 68 (2012) 19831993. - source
- Not checked yetcites [195] [195] K. Bahrami, F. Shi, I. Rekik, Y. Gao, D. Shen, 7Tguided super-resolution of 3T MRI, Medical physics 44 (2017) 1661-1677. - source
- Not checked yetcites [196] [196] G. Van Steenkiste, D. H. J. Poot, B. Jeurissen, A. J. den Dekker, F. Vanhevel, P. M. Parizel, J. Sijbers, Super-resolution t, javax.xml.bind.jaxbelement@1458c115, estimation: Quantitative high resolution t, javax.xml.bind.jaxbelement@62365375, mapping from a set of low resolution t, javax.xml.bind.jaxbelement@20656587, -weighted images with different slice orientations., Magnetic resonance in medicine 77 (2017) 1818-1830. - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Such generative models for image synthesis serve as a form of data augmentation, and also as an anonymization tool.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Research on CNN and RNN-based image reconstruction methods is rapidly increasing, pioneered by Yang et al. [133] at NIPS 2016 and Wang et al. [134] at ISBI 2016.”
What the sources say
- Not checked yetcites [133] [133] Y. Yang, J. Sun, H. Li, Z. Xu, Deep ADMMNet for compressive sensing MRI, in: D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, R. Garnett (Eds.), Advances in Neural Information Processing Systems 29, Curran Associates, Inc., 2016, pp. 1018. -
- Not checked yetcites [134] [134] S. Wang, Z. Su, L. Ying, X. Peng, S. Zhu, F. Liang, D. Feng, D. Liang, Accelerating magnetic resonance imaging via deep learning, in: Biomedical Imaging (ISBI), 2016 IEEE 13th International Symposium on, IEEE, pp. 514-517. -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“and for theranostics in neurosurgical imaging, combining confocal laser endomicroscopy with deep learning models for automatic detection of intraoperative CLE images on-the-fly [95].”
What the sources say
- Not checked yetcites [95] [95] M. Izadyyazdanabadi, E. Belykh, M. A. Mooney, J. M. Eschbacher, P. Nakaji, Y. Yang, M. C. Preul, Prospects for theranostics in neurosurgical imaging: Empowering confocal laser endomicroscopy diagnostics via deep learning., Frontiers in oncology 8 (2018) 240. - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Quantitative susceptibility mapping (QSM) is a growing field of research in MRI, aiming to noninvasively estimate the magnetic susceptibility of biological tissue [145, 146].”
What the sources say
- Not checked yetcites [145] [145] A. Deistung, A. Sch¨ afer, F. Schweser, U. Biedermann, R. Turner, J. R. Reichenbach, Toward in vivo histology: a comparison of quantitative susceptibility mapping (QSM) with magnitude-, phase-, and R2*-imaging at ultra-high magnetic field strength, Neuroimage 65 (2013) 299-314. - source
- Not checked yetcites [146] [146] A. Deistung, F. Schweser, J. R. Reichenbach, Overview of quantitative susceptibility mapping, NMR in Biomedicine 30 (2017). - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Matching one time series was about 100 times faster than the conventional [150] matching method and with very small mean absolute deviations from ground truth values.”
What the sources say
- Not matchedcites [166] [166] E. Hoppe, G. Krzdrfer, T. Wrfl, J. Wetzl, F. Lugauer, J. Pfeuffer, A. Maier, Deep learning for magnetic resonance fingerprinting: A new approach for predicting quantitative parameter values from time series, Studies in health technology and informatics 243 (2017) 202-206. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
In the paper
“After training their model on synthetic data it was able to generalize to real-world clinical brain MRI data, computing susceptibility maps within seconds end-to-end.”
What the sources say
- Not matchedcites [149] [149] K. G. B. Rasmussen, M. J. Kristensen, R. G. Blendal, L. R. Ostergaard, M. Plocharski, K. O'Brien, C. Langkammer, A. Janke, M. Barth, S. Bollmann, DeepQSM-Using Deep Learning to Solve the Dipole Inversion for MRI Susceptibility Mapping, Biorxiv (2018) 278036. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
In the paper
“Schlemper et.al. [136] created a deep cascade of concatenated CNNs for dynamic MR image reconstruction, making use of data augmentation, both rigid and elastic deformations, to increase the variation of the examples seen by the network and reduce overfitting 28 .”
What the sources say
- Not checked yetcites [136] [136] J. Schlemper, J. Caballero, J. V. Hajnal, A. N. Price, D. Rueckert, A deep cascade of convolutional neural networks for dynamic MR image reconstruction., IEEE transactions on medical imaging 37 (2018) 491-503. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In this context, deep learning approaches have accelerated research and the amount of costly training data.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Recently, deep learning approaches have been introduced to denoising.”
What the sources say
- Not matchedcites [180] [180] C. Bermudez, A. J. Plassard, T. L. Davis, A. T. Newton, S. M. Resnick, B. A. Landman, Learning implicit brain MRI manifolds with deep learning, Proceedings of SPIE-the International Society for Optical Engineering 10574 (2018). -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [181] [181] A. Benou, R. Veksler, A. Friedman, T. Riklin Raviv, Ensemble of expert deep neural networks for spatiotemporal denoising of contrast-enhanced MRI sequences, Medical image analysis 42 (2017) 145-159. - source
plainn = 500- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Deep learning in MRI has typically been focused on segmentation and classification of reconstructed magnitude images.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“It uses a pseudo-randomized acquisition that causes the signals from different tissues to have a unique signal evolution ('fingerprint') that is a function of the multiple material properties being investigated.”
What the sources say
- Not checked yetcites [150] [150] D. Ma, V. Gulani, N. Seiberlich, K. Liu, J. L. Sunshine, J. L. Duerk, M. A. Griswold, Magnetic resonance fingerprinting, Nature 495 (2013) 187-192. - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Deep learning methods has also been applied to MR artifact detection , e.g. poor quality spectra in MRSI [188]; detection and removal of ghosting artifacts in MR spectroscopy [189]; and automated reference-free detection of patient motion artifacts in MRI [190].”
What the sources say
- Not checked yetcites [188] [188] S. S. Gurbani, E. Schreibmann, A. A. Maudsley, J. S. Cordova, B. J. Soher, H. Poptani, G. Verma, P. B. Barker, H. Shim, L. A. D. Cooper, A convolutional neural network to filter artifacts in spectroscopic MRI, Magnetic resonance in medicine 80 (2018) 1765-1775. - source
- Not checked yetcites [189] [189] S. P. Kyathanahally, A. Dring, R. Kreis, Deep learning approaches for detection and removal of ghosting artifacts in MR spectroscopy, Magnetic resonance in medicine 80 (2018) 851-863. - source
- Not matchedcites [190] [190] T. K¨ ustner, A. Liebgott, L. Mauch, P. Martirosian, F. Bamberg, K. Nikolaou, B. Yang, F. Schick, S. Gatidis, Automated reference-free detection of motion artifacts in magnetic resonance images, MAGMA 31 (2018) 243-256. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Using variational networks for single-shot fast spin-echo MRI with variable density sampling, Chen et.al. [137] enabled real-time (200 ms per section) image reconstruction, outperforming conventional parallel imaging and compressed sensing reconstruction.”
What the sources say
- Not checked yetcites [137] [137] F. Chen, V. Taviani, I. Malkiel, J. Y. Cheng, J. I. Tamir, J. Shaikh, S. T. Chang, C. J. Hardy, J. M. Pauly, S. S. Vasanawala, Variable-density singleshot fast Spin-Echo MRI with deep learning reconstruction by using variational networks, Radiology (2018) 180445. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It has an almost 50 years long history, and has become the biggest target for deep learning approaches in medical imaging.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“It can be regarded as a quantitative multiparametric MRI analysis, and with recent acquisition schemes using a single-shot spiral trajectory with undersampling, whole-brain coverage of T 1 , T 2 and proton density maps can be acquired at 1 . 2 × 1 . 2 × 3 mm 3 voxel resolution in less than 5 min [159].”
What the sources say
- Not checked yetcites [159] [159] D. Ma, Y. Jiang, Y. Chen, D. McGivney, B. Mehta, V. Gulani, M. Griswold, Fast 3D magnetic resonance fingerprinting for a whole-brain coverage, Magnetic resonance in medicine 79 (2018) 21902197. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“It is also possible to add attention mechanisms to neural networks [346, 347], enabling them to focus their resources on the most informative components of each layer input.”
What the sources say
- Not checked yetcites [346] [346] V. Mnih, N. Heess, A. Graves, et al., Recurrent models of visual attention, in: Advances in neural information processing systems, pp. 2204-2212. -
- Not checked yetcites [347] [347] K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhudinov, R. Zemel, Y. Bengio, Show, attend and tell: Neural image caption generation with visual attention, in: International conference on machine learning, pp. 2048-2057. -
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These are very inefficient models, requiring large number of training samples before they can produce anything remotely useful”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Recently, deep learning methods have also been used for automated generation of radiology reports , typically incorporating long-short-term-memory (LSTM) network models to generate the textual paragraphs [314, 315, 316, 317], and also to identify findings in radiology reports [318, 319, 320].”
What the sources say
- Not checked yetcites [314] [314] B. Jing, P. Xie, E. Xing, On the automatic generation of medical imaging reports, arXiv preprint arXiv:1711.08195v3 (2017). - source
- Not checked yetcites [315] [315] C. Y. Li, X. Liang, Z. Hu, E. P. Xing, Hybrid retrieval-generation reinforced agent for medical image report generation, arXiv preprint arXiv:1805.08298v1 (2018). - source
- Not checked yetcites [316] [316] M. Moradi, A. Madani, Y. Gur, Y. Guo, T. SyedaMahmood, Bimodal network architectures for automatic generation of image annotation from text, arXiv preprint arXiv:1809.01610v1 (2018). - source
- Not checked yetcites [317] [317] Y. Zhang, D. Y. Ding, T. Qian, C. D. Manning, C. P. Langlotz, Learning to summarize radiology findings, arXiv preprint arXiv:1809.04698v1 (????). - source
- Not checked yetcites [318] [318] E. Pons, L. M. M. Braun, M. G. M. Hunink, J. A. Kors, Natural language processing in radiology: A systematic review, Radiology 279 (2016) 329-343. - source
- Not checked yetcites [319] [319] J. Zech, M. Pain, J. Titano, M. Badgeley, J. Schefflein, A. Su, A. Costa, J. Bederson, J. Lehar, E. K. Oermann, Natural language-based machine learning models for the annotation of clinical radiology reports, Radiology 287 (2018) 570-580. - source
- Not checked yetcites [320] [320] D. J. Goff, T. W. Loehfelm, Automated radiology report summarization using an open-source natural language processing pipeline, Journal of digital imaging 31 (2018) 185-192. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“There are a few examples of these ideas entering the medical machine learning community, as in [340] where the distribution of deep learning models among several medical institutions was investigated, but then without considering the above privacy issues.”
What the sources say
- Not checked yetcites [340] [340] K. Chang, N. Balachandar, C. Lam, D. Yi, J. Brown, A. Beers, B. Rosen, D. L. Rubin, J. Kalpathy-Cramer, Distributed deep learning networks among institutions for medical imaging, Journal of the American Medical Informatics Association : JAMIA 25 (2018) 945-954. -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“But still, even if there is interest on the 'ground floor' and one is able to get prototype systems into the hands of clinicians, there are many higher-ups to convince and regulatory, ethical and legal hurdles to overcome.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the networks that are most frequently used, and with the best raw performance, remain the data-hungry standard deep neural networks.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For two-dimensional images one will almost always use a network that has been pre-trained on the ImageNet data set.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is clear that the ideas behind stateof-the-art two-dimensional CNNs can be lifted to three dimensions, but also that adding a third spatial dimension results in additional constraints.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“What's true about the openness of machine learning in general is increasingly true also for the sub-field of machine learning for medical image analysis.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The field of Bayesian Deep Learning aims to combine deep learning and Bayesian approaches to uncertainty.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Attempting to augment already established procedures necessitates knowledge of the entire workflow.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is possible to end up developing clever machine learning system for clinical use that turn out to be practically useless for actual clinicians.”
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“The idea of pre-training networks is not restricted to images. Pre-training entire models has recently been demonstrated to greatly impact the performance of natural language processing systems [3, 4, 5].”
What the sources say
- Not checked yetcites [3] [3] M. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, L. Zettlemoyer, Deep contextualized word representations, in: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), volume 1, pp. 2227-2237. -
- Not checked yetcites [4] [4] J. Howard, S. Ruder, Universal language model finetuning for text classification, in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pp. 328-339. -
- Not checked yetcites [5] [5] A. Radford, K. Narasimhan, T. Salimans, I. Sutskever, Improving language understanding by generative pre-training (2018). -
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Most current work on deep learning for medical data analysis use either open, anonymized data sets (as those in Table 4), or locally obtained anonymized research data, making these issues less relevant.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“One of the first application of deep learning for CBIR in the medical domain came in 2015 when Sklan et al. [310] trained a CNN to perform CBIR with more than one million random MR and CT images, with disappointing results (true positive rate of 20%) on their independent test set of 2100 labeled images.”
What the sources say
- Not checked yetcites [310] [310] J. E. S. Sklan, A. J. Plassard, D. Fabbri, B. A. Landman, Toward content based image retrieval with deep convolutional neural networks, Proceedings of SPIE-the International Society for Optical Engineering 9417 (2015). -
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the story for deep learning in medical imaging is not quite as settled.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Another way to increase their trustworthiness is to make them produce robust uncertainty estimates in addition to predictions.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using the basic building blocks described above, placed according to the ideas behind, say, ResNet and SENet, will easily result in close to state-of-the-art performance on two-dimensional object detection, image classification and segmentation tasks.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“This is illustrated by the tremendous amounts of high-impact publications in top-journals dealing with deep learning in medical imaging (for example [17, 21, 30, 32, 40, 90, 162, 137, 140, 273, 285], all published in 2018).”
What the sources say
- Not checked yetcites [17] [17] N. Ganapathy, R. Swaminathan, T. M. Deserno, Deep learning on 1-D biosignals: a taxonomy-based survey, Yearbook of medical informatics 27 (2018) 98-109. - source
- Not checked yetcites [21] [21] D. S. Kermany, M. Goldbaum, W. Cai, C. C. S. Valentim, H. Liang, S. L. Baxter, A. McKeown, G. Yang, X. Wu, F. Yan, J. Dong, M. K. Prasadha, J. Pei, M. Y. L. Ting, J. Zhu, C. Li, S. Hewett, J. Dong, I. Ziyar, A. Shi, R. Zhang, L. Zheng, R. Hou, W. Shi, X. Fu, Y. Duan, V. A. N. Huu, C. Wen, E. D. Zhang, C. L. Zhang, O. Li, X. Wang, M. A. Singer, X. Sun, J. Xu, A. Tafreshi, M. A. Lewis, H. Xia, K. Zhang, Identifying medical diagnoses and treatable diseases by image-based deep learning, Cell 172 (2018) 1122-1131.e9. - source
- Not checked yetcites [30] [30] R. Poplin, A. V. Varadarajan, K. Blumer, Y. Liu, M. McConnell, G. Corrado, L. Peng, D. Webster, Predicting Cardiovascular Risk Factors in Retinal Fundus Photographs using Deep Learning, Nature Biomedical Engineering (2018). - source
- Not checked yetcites [32] [32] J. De Fauw, J. R. Ledsam, B. Romera-Paredes, S. Nikolov, N. Tomasev, S. Blackwell, H. Askham, X. Glorot, B. O'Donoghue, D. Visentin, et al., Clinically applicable deep learning for diagnosis and referral in retinal disease, Nature medicine 24 (2018) 1342. - source
- Not matchedcites [40] [40] G. Hinton, Deep Learning A Technology With the Potential to Transform Health Care (2018) 1-2. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [90] [90] F. Liu, H. Jang, R. Kijowski, T. Bradshaw, A. B. McMillan, Deep learning MR imaging-based attenuation correction for PET/MR imaging, Radiology 286 (2018) 676-684. - source
- Not checked yetcites [162] [162] B. Rieger, M. Akakaya, J. C. Pariente, S. Llufriu, E. Martinez-Heras, S. Weingrtner, L. R. Schad, Time efficient whole-brain coverage with MR fingerprinting using slice-interleaved echo-planarimaging, Scientific reports 8 (2018) 6667. - source
- Not matchedcites [137] [137] F. Chen, V. Taviani, I. Malkiel, J. Y. Cheng, J. I. Tamir, J. Shaikh, S. T. Chang, C. J. Hardy, J. M. Pauly, S. S. Vasanawala, Variable-density singleshot fast Spin-Echo MRI with deep learning reconstruction by using variational networks, Radiology (2018) 180445. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [140] [140] B. Zhu, J. Z. Liu, S. F. Cauley, B. R. Rosen, M. S. Rosen, Image reconstruction by domain-transform manifold learning., Nature 555 (2018) 487-492. - source
- Not checked yetcites [273] [273] J. Wasserthal, P. Neher, K. H. Maier-Hein, TractSeg - fast and accurate white matter tract segmentation, Neuroimage 183 (2018) 239-253. - source
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As privacy and data protection is often a requirement when dealing with medical data, new techniques for training models without exposing the underlying training data to the user of the model are necessary.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
- Rests on an assumption: Privacy and data protection is often a requirement when dealing with medical data.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Other important challenges are related to data, trust, interpretability, workflow integration, and regulations, as discussed below.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“As deep neural networks relies on complicated interconnected hierarchical representations of the training data to produce its predictions, interpreting these predictions becomes very difficult. This is the 'black box' problem of deep neural networks [348].”
What the sources say
- Not checked yetcites [348] [348] D. Castelvecchi, Can we open the black box of AI?, Nature News 538 (2016) 20. - source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Even though there are many challenges associated to the introduction of deep learning in clinical settings, the methods produce results that are too valuable to discard.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“The ideas date back to the early 90s [354, 355, 356], but the field has recently seen renewed interest from the machine learning community at large, as new ways of computing uncertainty estimates from state of the art deep learning models have been developed [59, 65, 357].”
What the sources say
- Not matchedcites [354] [354] R. M. Neal, Bayesian learning for neural networks, Ph.D. thesis, University of Toronto, 1995. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [355] [355] D. J. MacKay, A practical Bayesian framework for backpropagation networks, Neural computation 4 (1992) 448-472. - source
- Not checked yetcites [356] [356] P. Dayan, G. E. Hinton, R. M. Neal, R. S. Zemel, The Helmholtz machine, Neural computation 7 (1995) 889-904. - source
- Not matchedcites [59] [59] S. Murray, An exploratory analysis of multi-class uncertainty approximation in Bayesian convolution neural networks, Master's thesis, University of Bergen, 2018. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [65] [65] Y. Gal, Uncertainty in deep learning, Ph.D. thesis, University of Cambridge, 2016. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [357] [357] Y. Li, Y. Gal, Dropout Inference in Bayesian Neural Networks with Alpha-divergences, in: International Conference on Machine Learning, pp. 2052-2061. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This is a crucially important obstacle for deep neural networks, especially in medical data analysis.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is interesting to note how deep learning-based models are completely dominating the leaderboards of essentially all image-based competitions. Other machine learning models, or non-machine learning-based techniques, have largely been outclassed.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“Another widely used technique is augmenting the training data set by applying various transformations that preserves the labels, as in rotations, scalings and intensity shifts of images, or more advanced data augmentation techniques like anatomically sound deformations, or other data set specific operations (for example in our work on kidney segmentation from DCE-MRI, where we used image”
What the sources say
- Not checked yetcites [343] [343] A. Lundervold, K. Sprawka, A. Lundervold, Fast estimation of kidney volumes and time courses in DCE-MRI using convolutional neural networks, 2018. -
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“But whatever you do, the way current deep neural networks are constructed and trained results in significant data size requirements.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper relies on this without support.
Healthcare providers generate and capture enormous amounts of data containing extremely valuable signals and information, at a pace far surpassing what 'traditional' methods of analysis can process.
“Healthcare providers generate and capture enormous amounts of data containing extremely valuable signals and information, at a pace far surpassing what 'traditional' methods of analysis can process.”
The paper relies on this without support.
The use of machine learning in general and deep learning in particular within healthcare is still in its infancy.
“The use of machine learning in general and deep learning in particular within healthcare is still in its infancy”
The paper relies on this without support.
Medical imaging datasets are often imbalanced, with few pathological findings, limiting the training of deep learning models.
“This approach is highly interesting as medical imaging datasets are often imbalanced, with few pathological findings, limiting the training of deep learning models.”
The paper relies on this without support.
Medical images are often three-dimensional.
“One issue is that medical images are often three-dimensional, and three-dimensional convolutional neural networks are as well-developed as their 2D counterparts.”
The paper relies on this without support.
Three-dimensional convolutional neural networks are as well-developed as their 2D counterparts.
“One issue is that medical images are often three-dimensional, and three-dimensional convolutional neural networks are as well-developed as their 2D counterparts.”
The paper relies on this without support.
Labeled training data is typically both expensive and difficult to produce.
“These are very inefficient models, requiring large number of training samples before they can produce anything remotely useful, and labeled training data is typically both expensive and difficult to produce.”
The paper relies on this without support.
Privacy and data protection is often a requirement when dealing with medical data.
“As privacy and data protection is often a requirement when dealing with medical data, new techniques for training models without exposing the underlying training data to the user of the model are necessary.”
The paper relies on this without support.
The training data has to be representative of the data the network will meet in the future.
“In addition, the training data has to be representative of the data the network will meet in the future.”
The paper relies on this without support.
The high-quality images one typically works with in research differ from the messiness of the real clinical world.
“Considering the large difference between the high-quality images one typically work with when doing research and the messiness of the real, clinical world, this can be a major obstacle when putting deep learning systems into production.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“After learning a new capability from the existing data, this can be applied to new images and the system can classify the images in the right category (Inference), similar to how a radiologist operates [28].”
From The rise of artificial intelligence in healthcare applications (2020) · cites this paper as [28]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ SPINE · p. 21
“| Metastasis | | [291] | A multi-resolution approach for spinal metastasis detection using deep Siamese neural networks comprising three identical subnetworks for multi-resolution analysis and detection.”
§ References · p. 41
“- [291] X. Wang, W. Yang, J. Weinreb, J. Han, Q. Li, X. Kong, Y. Yan, Z. Ke, B. Luo, T. Liu, L. Wang, Searching for prostate cancer by fully automated magnetic resonance imaging classification: deep learning versus non-deep learning., Scientific reports 7 (2017) 15415.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ SPINE · p. 21
“| sis | Spondylitis vs tuberculo- | [297] | CNN model for differentiating between tuberculous and pyogenic spondylitis in MR images. Compared their CNN performance with that of three skilled radiologists using spine MRIs from 80 patients”
§ References · p. 41
“- [297] K. H. Kim, W.-J. Do, S.-H. Park, Improving resolution of MR images with an adversarial network incorporating images with different contrast, Medical physics 45 (2018) 3120-3131.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 1. Introduction · p. 1
“The last ILSVRC competition was held in 2017, and computer vision research has moved on to other more difficult benchmark challenges.”
§ 4. Open science and reproducible research in machine learning for medical imaging · p. 22
“with the now annual ImageNet Large Scale Visual Recognition Challenge (ILSVRC) competition as the main driver of progress in deep learning for computer vision since 2012.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.1.6. Image registration · p. 17
“MRI-based attenuation correction for PET [243, 244]”
§ References · p. 39
“- [244] M. Liu, D. Cheng, K. Wang, Y. Wang, A. D. N. Initiative, Multi-modality cascaded convolutional neural networks for alzheimer's disease diagnosis., Neuroinformatics 16 (2018) 295-308.”
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Squeeze-and-Excitation NetworksPreprint
Hu, J., Shen, L., & Sun, G. (2017) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.48550/arxiv.1709.01507 · Cited by 37,845
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Donoho, D. L. (2006) · IEEE Transactions on Information Theory · doi:10.1109/tit.2006.871582 · Cited by 23,994
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Research works printed but not linked: 28
- Shickel, 2017, Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis, IEEE J Biomed Health Inform
- Poplin, 2018, Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning, Nat Biomed Eng, 2, 158, 10.1038/s41551-018-0195-0 · DOI · Paper page
- Cauchy, 1847, Méthode générale pour la résolution des systemes déquations simultanées, C R Sci Paris, 25, 536
- Srivastava, 2014, Dropout: a simple way to prevent neural networks from overfitting, J Mach Learn Res, 15, 1929
- Zheng, 2018, Pairwise domain adaptation module for CNN-based 2-D/3-D registration, J Med Imaging (Bellingham, Wash.), 5, 021204
- Savadjiev, 2018, Demystification of AI-driven medical image interpretation: past, present and future, Eur Radiol
- Qin, 2018, Convolutional recurrent neural networks for dynamic MR image reconstruction, IEEE Trans Med Imaging
- Chen, 2018, Variable-density single-shot fast Spin-Echo MRI with deep learning reconstruction by using variational networks, Radiology, 180445
- Knoll, 2018, Assessment of the generalization of learned image reconstruction and the potential for transfer learning, Magn Reson Med
- Mardani, 2018, Deep generative adversarial neural networks for compressive sensing (GANCS) MRI, IEEE Trans Med Imaging
- Rasmussen, 2018, DeepQSM-using deep learning to solve the dipole inversion for MRI susceptibility mapping, Biorxiv, 278036
- Aggarwal, 2018, Modl: model based deep learning architecture for inverse problems, IEEE Trans Med Imaging
- Li H, Schwab J, Antholzer S, Haltmeier M. Nett: solving inverse problems with deep neural networks, arXiv:1803.00092 (2018). · arXiv
- Hoppe, 2017, Deep learning for magnetic resonance fingerprinting: a new approach for predicting quantitative parameter values from time series, Stud Health Technol Inform, 243, 202
- Vincent, 2010, Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion, J Mach Learn Res (JMLR), 11, 3371
- Hong Y, Hwang U, Yoo J, Yoon S. How generative adversarial networks and their variants work: an overview of GAN, arXiv:1711.05914v7 (2017). · arXiv
- Nie, 2017, Medical image synthesis with context-aware generative adversarial networks, Medical image computing and computer-assisted intervention: MICCAI, 417
- Spuhler, 2018, Synthesis of patient-specific transmission image for PET attenuation correction for PET/MR imaging of the brain using a convolutional neural network, J Nucl Med
- Torrado-Carvajal, 2018, Dixon-VIBE deep learning (DIVIDE) pseudo-CT synthesis for pelvis PET/MR attenuation correction, J Nucl Med
- Bernal J, Kushibar K, Asfaw DS, Valverde S, Oliver A, Mart R, et al. Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review, arXiv:1712.03747v3 (2017). · arXiv
- Bernal, 2018, Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review, Artif Intell Med
- Pizarro, 2018, Using deep learning algorithms to automatically identify the brain MRI contrast: implications for managing large databases, Neuroinformatics
- Hoseini, 2018, Adaptahead optimization algorithm for learning deep CNN applied to MRI segmentation, J Digit Imaging
- Shehata, 2018, Computer-aided diagnostic system for early detection of acute renal transplant rejection using diffusion-weighted MRI, IEEE Trans Bio-med Eng
- Sklan, 2015, Toward content based image retrieval with deep convolutional neural networks, Proc SPIE, 9417
- Ronneberger, 2015, U-net: Convolutional networks for biomedical image segmentation, vol. 9351, 234
- Montavon, 2017, Methods for interpreting and understanding deep neural networks, Digit Signal Process
- Hohman, 2018, Visual analytics in deep learning: an interrogative survey for the next frontiers, IEEE Trans Vis Comput Graph
Cited by
Sorted by citations
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
The rise of artificial intelligence in healthcare applications
Bohr, A., & Memarzadeh, K. (2020) · Artificial Intelligence in Healthcare · doi:10.1016/b978-0-12-818438-7.00002-2 · Cited by 1,636
Wen, J., Thibeau-Sutre, E., Diaz-Melo, M., Samper-González, J., Routier, A., Bottani, S., Dormont, D., Durrleman, S., Burgos, N., & Colliot, O. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101694 · Cited by 809
Artificial intelligence in the creative industries: a review
Anantrasirichai, N., & Bull, D. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10039-7 · Cited by 793
Deep learning in cancer pathology: a new generation of clinical biomarkers
Echle, A., Rindtorff, N. T., Brinker, T. J., Luedde, T., Pearson, A. T., & Kather, J. N. (2021) · British Journal of Cancer · doi:10.1038/s41416-020-01122-x · Cited by 667
Metadata
- Authors
- Lundervold, A. S., & Lundervold, A.
- Affiliations
- Western Norway University of Applied Sciences (NO)
- Corresponding author
- Lundervold, Alexander Selvikvåg
- Venue
- Zeitschrift für Medizinische Physik
- Publisher
- Elsevier BV
- Published
- 2019-05
- Volume
- 29
- Issue
- 2
- Pages
- 102-127
- ISSN
- 0939-3889 (ISSN-L)
- OpenAlex
- W2900954917
- Semantic Scholar
- 0ebc300c16f01a4e94c8551997922fdb67ac1951
- Cited by
- 2,058
- References
- 289
- Citations by year
- 2026: 189 · 2025: 291 · 2024: 283 · 2023: 286 · 2022: 368 · 2021: 399 · 2020: 196 · 2019: 44
- FWCI
- 19.06
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Zeitschrift für Medizinische Physik (publishedVersion, cc-by)
- arXiv (Cornell University) (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University)
- Funders
- Bergens Forskningsstiftelse
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Advanced MRI Techniques and Applications
- Keywords
- deep learning, medical image analysis, magnetic resonance imaging, deep neural network, MRI segmentation, disease prediction, medical image retrieval, open-source code
- MeSH terms
- Deep Learning, Animals, Humans, Image Processing, Computer-Assisted, Magnetic Resonance Imaging
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
