The DOI matches its Crossref record; 53 of the 60 references it cites were found in a registry or an index; none of the 34 sources its claims cite is checked for support yet.
Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation
Open accessAbstract
Incorporation of prior knowledge about organ shape and location is key to improve performance of image analysis approaches. In particular, priors can be useful in cases where images are corrupted and contain artefacts due to limitations in image acquisition. The highly constrained nature of anatomical objects can be well captured with learning-based techniques. However, in most recent and promising techniques such as CNN-based segmentation it is not obvious how to incorporate such prior knowledge. State-of-the-art methods operate as pixel-wise classifiers where the training objectives do not incorporate the structure and inter-dependencies of the output. To overcome this limitation, we propose a generic training strategy that incorporates anatomical prior knowledge into CNNs through a new regularisation model, which is trained end-to-end. The new framework encourages models to follow the global anatomical properties of the underlying anatomy (e.g. shape, label structure) via learnt non-linear representations of the shape. We show that the proposed approach can be easily adapted to different analysis tasks (e.g. image enhancement, segmentation) and improve the prediction accuracy of the state-of-the-art models. The applicability of our approach is shown on multi-modal cardiac data sets and public benchmarks. In addition, we demonstrate how the learnt deep models of 3-D shapes can be interpreted and used as biomarkers for classification of cardiac pathologies.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
The paper proposes anatomically constrained neural networks (ACNN), a generic end-to-end training strategy that uses a stacked convolutional autoencoder and T-L network to impose learnt anatomical shape priors on CNN predictions. It demonstrates improved cardiac MR segmentation, 3D ultrasound segmentation, MR super-resolution, and pathology classification over state-of-the-art baselines.
Key findings
- For cardiac cine-MR segmentation, ACNN-Seg improved endocardium Dice to .939 ± .017 versus .908 ± .021 for 2D-FCN, and myocardium Dice to .811 ± .027 versus .727 ± .046; mean surface distances were also lower (endocardium 1.37 ± 0.42 mm vs 2.07 ± 0.61 mm; myocardium 1.14 ± 0.22 mm vs 1.58 ± 0.44 mm), with p < 0.001 for Dice and mean distance.
- On the CETUS’14 3D-US benchmark, ACNN-Seg achieved end-diastole Dice .912 ± .023 versus .906 ± .026 for FCN and .894 ± .041 for BEAS, and end-systole Dice .873 ± .051 versus .872 ± .050 for FCN and .856 ± .057 for BEAS; Hausdorff distance at ED was 6.96 ± 1.75 mm versus 11.94 ± 9.46 mm for FCN.
- For cardiac MR super-resolution, ACNN-SR achieved SSIM .796 ± .041 versus .783 ± .046 for SR-CNN, clinician MOS scores of 4.36 ± 0.62 and 4.25 ± .68 versus 3.59 ± 1.05 and 3.85 ± .70, and inference time .06 s versus .29 s.
- For pathology classification, T-L codes gave 83.3% accuracy from ED phase and 91.6% with ED+ES, compared with PCA codes at 76.6% and 86.6%, using 10-fold cross-validation on 60 CMR sequences.
Methods
- ACNN adds a shape-regularisation loss to standard CNN training: segmentation uses cross-entropy plus a low-dimensional shape loss and weight decay, while super-resolution uses smooth ℓ1 reconstruction plus a global shape loss and weight decay. The regulariser is a stacked convolutional autoencoder and T-L network that learns 64-dimensional anatomical shape/label representations; it is used only during training, not inference.
- Data include the UK Digital Heart Project dataset of 1200 cine 2D stack and 3D HR cardiac MR image pairs, split into 900 training, 100 validation, and 200 testing for segmentation, and 1000 training / 200 testing for super-resolution; CETUS’14 with 45 3D+time ultrasound sequences from 15 healthy subjects and 30 patients, evaluated blinded on 30 test sequences; and ACDC MICCAI’17 with 20 cine stacks per class for classification.
- Comparisons include 2D-FCN, 3D-UNet, AE-Seg, 3D-Seg, BEAS, FCN, and SR-CNN; metrics include Dice, mean and Hausdorff surface distances, SSIM, mean opinion score, ejection-fraction correlation/bias, and classification accuracy, with Wilcoxon signed-rank tests for top methods.
Limitations
- The paper states that 3D-US training data were limited to 15 image sequences; segmentation results could improve by segmenting ED and ES frames simultaneously or using temporal information such as optical flow; classification accuracy could improve by training the AE and T-L models with a classification objective; and achieving the best possible segmentation accuracy was not the main focus.
- The paper also notes that the T-L regulariser is used only at training time, that latent codes are expected to be correlated because the decoder merges codes across spatial dimensions, and that a variational autoencoder was not used because the K-L term would reduce representation power and generative sampling was not needed.
- Evident from the text: the method is evaluated on cardiac applications only, and the authors state future work will extend ACNN to tasks such as human pose estimation and landmark localisation.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 of 34 cited sources checked · 0 supported · 0 flagged
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“(II) An implicit statistical parametrisation of the left ventricular shape via NNs for pathology classification;”
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The applicability of our approach is shown on multi-modal cardiac datasets and public benchmarks.”
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesNone of the sources cited for this claim have been checked yet.
In the paper
“Our evaluation shows: (I) A sub-pixel cardiac MR image segmentation approach that, in contrast to previous CNN approaches [44], [2], is robust against slice misalignment and coverage problems;”
What the sources say
- Not checked yetcites [44] [44] P. V. Tran. A fully convolutional neural network for cardiac segmentation in short-axis MRI. arXiv preprint arXiv:1604.00494 , 2016. - source
- Not matchedcites [2] [2] M. Avendi, A. Kheradvar, and H. Jafarkhani. A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. MedIA , 30:108-119, 2016. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We show that the proposed approach can be easily adapted to different analysis tasks ( e.g. image enhancement, segmentation) and improve the prediction accuracy of the state-of-the-art models.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The main contribution of ACNN model over the standard FCN approaches is the improved shape delineation of the LV, as it can be seen in terms of the distance error metrics.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Rests on an assumption: The CETUS web platform evaluation is a valid blinded benchmark for segmentation accuracy.
None of the sources cited for this claim have been checked yet.
In the paper
“Slice by slice analysis [2], [44] significantly under-performs compared to the proposed subpixel and ACNN-Seg segmentation methods.”
What the sources say
- Not matchedcites [2] [2] M. Avendi, A. Kheradvar, and H. Jafarkhani. A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. MedIA , 30:108-119, 2016. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked yetcites [44] [44] P. V. Tran. A fully convolutional neural network for cardiac segmentation in short-axis MRI. arXiv preprint arXiv:1604.00494 , 2016. - source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Rests on an assumption: The HR ground-truth label maps projected from HR image space are an accurate reference for segmentation evaluation.
- Not matched
A result the paper reports from its own data — 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 particular, the dice score metrics are observed to be lower since 2D analysis can yield poor performance in basal and apical parts of the heart as shown in Fig. 6.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Rests on an assumption: The HR ground-truth label maps projected from HR image space are an accurate reference for segmentation evaluation.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Instead of applying these two gradient descent updates sequentially in an iterative fashion, we perform a joint update training scheme and experimentally observed better convergence.”
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The experimental results, given in Table II, show that neural network models outperforms previous state-of-theart approaches in this public benchmark dataset although the training data size was limited to 15 image sequences.”
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Rests on an assumption: The CETUS web platform evaluation is a valid blinded benchmark for segmentation accuracy.
A result the paper reports from its own data — 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 can be seen in the bottom row of Fig. 6, without the learnt shape priors, label map predictions are more prone to imaging artefacts.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
- It may state two separate claims as one. 34
- The quote only partly states this claim. 5
- Probably not a substantial claim. 16
In the paper
“We show that the proposed segmentation and SR models become more robust against imaging artefacts mentioned earlier which is underlined by our state-of-the-art results on the MICCAI'14 CETUS public benchmark [8].”
What the sources say
- Not checked yetcites [8] [8] O. Bernard, J. G. Bosch, B. Heyde, M. Alessandrini, D. Barbosa, S. Camarasu-Pop, F. Cervenansky, S. Valette, O. Mirea, M. Bernier, et al. Standardized evaluation system for left ventricular segmentation algorithms in 3D echocardiography. IEEE TMI , 35(4):967-977, 2016. - source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“(III) An image SR technique that extends previous work [34] and that is robust against slice misalignments;”
What the sources say
- Not checked yetcites [34] [34] O. Oktay, W. Bai, M. Lee, R. Guerrero, K. Kamnitsas, J. Caballero, A. de Marvao, S. Cook, D. ORegan, and D. Rueckert. Multi-input cardiac image super-resolution using convolutional neural networks. In International Conference on MICCAI , pages 246-254. Springer, 2016. - source
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“our approach is computationally more efficient than the state-of-the-art SR-CNN model [34] as the feature extraction is performed in the low-dimensional image space.”
What the sources say
- Not checked yetcites [34] [34] O. Oktay, W. Bai, M. Lee, R. Guerrero, K. Kamnitsas, J. Caballero, A. de Marvao, S. Cook, D. ORegan, and D. Rueckert. Multi-input cardiac image super-resolution using convolutional neural networks. In International Conference on MICCAI , pages 246-254. Springer, 2016. - source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“ACNN-Seg | 1.37 ± 0.42 | 7.89 ± 3.83 | .939 ± .017 | 1.14 ± 0.22 | 7.31 ± 3.59 | .811 ± .027 | 1 . 60 × 10 6 |”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: The high-resolution motion-free cardiac MR images provide an appropriate reference for evaluating segmentation performance on low-resolution 2D stacks.
A result the paper reports from its own data — 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 observed that the learnt latent representations in general follow a normal distribution and they are not separated in multi-clusters ( e.g. mixture of Gaussians).”
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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 particular, Hausdorff distances were reduced significantly”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe quote only partly states this claim.
- Rests on an assumption: The CETUS web platform evaluation is a valid blinded benchmark for segmentation accuracy.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Previous slice by slice segmentation approaches validated their methods on LR annotations; however, we see that the produced label maps are far off from the true underlying ventricular geometry and it can be a limiting factor for the analysis of ventricle morphology.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: The HR ground-truth label maps projected from HR image space are an accurate reference for segmentation evaluation.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Similarly, we observed an improvement in terms of normalised Dice score, which was quantitatively not significant due to large volumetric size of the LV cavity.”
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: The CETUS web platform evaluation is a valid blinded benchmark for segmentation accuracy.
A result the paper reports from its own data — 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 observed that the ACNN approach ensures better consistency between frames although none of the methods have used temporal information.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: The CETUS web platform evaluation is a valid blinded benchmark for segmentation accuracy.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We also analysed the performance change in AE-Seg with respect to the number of parameters, which shows that the small capacity AE-Seg model ( 8 × 10 4 pars) is not suitable for cardiac image segmentation as the second stage in the cascaded model does not improve the performance significantly.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: The HR ground-truth label maps projected from HR image space are an accurate reference for segmentation evaluation.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We observed that reconstruction of label-maps from low dimensional representations was limited since the ventricle boundaries were not delineated properly but rather a rough segmentation was generated (DSC: . 734 ).”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: The HR ground-truth label maps projected from HR image space are an accurate reference for segmentation evaluation.
A result the paper reports from its own data — 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 the segmentation problem, the Sorensen-Dice loss was tested in the experiments as an alternative to the cross-entropy loss, yet we observed a degraded performance since the latter is a smoother function.”
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By including the codes from ES phase, the classification accuracies were improved to 86 . 6% vs 91 . 6% .”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: The HR ground-truth label maps projected from HR image space are an accurate reference for segmentation evaluation.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We used 10 -fold cross-validation on 60 CMR sequences and obtained 76 . 6% vs 83 . 3% accuracy using PCA and T-L codes extracted from ED phase.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: The HR ground-truth label maps projected from HR image space are an accurate reference for segmentation evaluation.
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
“It is also observed to be more memory efficient compared to the standard 3D-UNet architecture [12].”
What the sources say
- Not matchedcites [11] [11] H. Chen, Y. Zheng, J.-H. Park, P.-A. Heng, and S. K. Zhou. Iterative multi-domain regularized deep learning for anatomical structure detection and segmentation from ultrasound images. In International Conference on MICCAI , pages 487-495. Springer, 2016. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [12] [12] ¨ O. C ¸ ic ¸ek, A. Abdulkadir, S. S. Lienkamp, T. Brox, and O. Ronneberger. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In Proceedings of MICCAI , pages 424-432. Springer, 2016. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- 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
“The proposed global training objective in SR corresponds to a prior on the space of feasible high-resolution (HR) solutions, which is experimentally shown to be useful since SR is an illposed problem.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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 particular, priors can be useful in cases where images are corrupted and contain artefacts due to limitations in image acquisition.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. 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
“In that regard, the proposed method is not only useful for image enhancement and segmentation but also for the study of anatomical shape variations in population studies and their associations with cardiac related pathologies.”
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Our framework learns a non-linear compact representation of the underlying anatomy through a stacked convolutional autoencoder [31] and enforces network predictions to follow the learnt statistical shape/label distributions.”
What the sources say
- Not checked yetcites [31] [31] J. Masci, U. Meier, D. Cires ¸an, and J. Schmidhuber. Stacked convolutional auto-encoders for hierarchical feature extraction. In International - Conference on Artificial Neural Networks , pages 52-59. Springer, 2011. -
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
“More importantly, our approach is independent of the particular NN architecture or application; it can be combined with any of the state-of-the-art segmentation or super-resolution (SR) NN models and potentially improve its prediction accuracy and robustness without introducing any memory or computational complexity at inference time.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
In the paper
“We also demonstrate that the lower dimensional representations learnt by the proposed ACNN can be useful for classification of pathologies such as dilated and hypertrophic cardiomyopathy, and it does not require point-wise correspondence search between subjects as in [39].”
What the sources say
- Not matchedcites [39] [39] M. Shakeri, H. Lombaert, S. Tripathi, S. Kadoury, A. D. N. Initiative, et al. Deep spectral-based shape features for Alzheimers disease classification. In SASHIMI , pages 15-24. Springer, 2016. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Not matched
In the paper
“Similarly, 3D-US is recommended over the use of 2D-US since it has been demonstrated to provide more accurate and reproducible volumetric measurements [25].”
What the sources say
- Not checked yetcites [25] [25] R. M. Lang, L. P. Badano, W. Tsang, D. H. Adams, E. Agricola, T. Buck, F. F. Faletra, A. Franke, J. Hung, L. P. de Isla, et al. EAE/ASE recommendations for image acquisition and display using three-dimensional echocardiography. Journal of the American Society of Echocardiography , 25(1):3-46, 2012. -
Strength:boosted· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
“More importantly, our approach is independent of the particular NN architecture or application; it can be combined with any of the state-of-the-art segmentation or super-resolution (SR) NN models and potentially improve its prediction accuracy and robustness without introducing any memory or computational complexity at inference time.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt 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
“Using the proposed approach we can perform full 3D segmentation without explicit motion correction and do not have to rely on LR slice-by-slice 2D segmentation.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
In the paper
“In [1], Alain and Bengio showed that the denoising reconstruction error is equivalent to contractive penalty, which forces the feature extraction (encoder) function f resist perturbations of the input and contracts these input samples to similar low dimensional codes.”
What the sources say
- Not checked yetcites [1] [1] G. Alain and Y. Bengio. What regularized auto-encoders learn from the data-generating distribution. Journal of Machine Learning Research , 15(1):3563-3593, 2014. -
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
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 for the case of image segmentation, learnt shape representations can be used to regularise image SR, constraining the model to make only anatomically meaningful predictions.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
In the paper
“It provides two main advantages over the state-of-the-art medical image SR model proposed in [34]: (I) the network generates image features in the LR image grid rather than early upsampling of the features, which reduces memory and computation requirements significantly.”
What the sources say
- Not checked yetcites [34] [34] O. Oktay, W. Bai, M. Lee, R. Guerrero, K. Kamnitsas, J. Caballero, A. de Marvao, S. Cook, D. ORegan, and D. Rueckert. Multi-input cardiac image super-resolution using convolutional neural networks. In International Conference on MICCAI , pages 246-254. Springer, 2016. - source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
“The given penalty function promotes the network to learn the underlying low-dimensional data manifold and capture its local smooth structure.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The experimental results were evaluated in a blinded fashion by uploading the generated segmentations from separate 30 sequences into the CETUS web platform.”
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
In the paper
“Low dimensional encoding enables us to train models with global characteristics but also yields better generalisation power for the underlying anatomy as shown in earlier work [43].”
What the sources say
- Not checked yetcites [43] [43] A. Torralba and Y. Weiss. Small codes and large image databases for recognition. In Proceedings of CVPR , pages 1-8. IEEE, 2008. - source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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 addition to the smoothness of the latent distributions, the extracted codes are expected to be correlated since the decoder merges some of the codes along the three spatial dimensions to construct input feature maps for the transposed convolutions, but this characteristic is not a limitation in our study.”
Strength:hedged· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
“Image SR is an ill-posed problem as there are an infinite number of solutions for a given input sample but only a few would be anatomically meaningful and accurate.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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 addition to imposing shape regularisation, this parametrisation encourages label consistency in model predictions, and reduces false-positive detections as they can influence the predicted codes in the hidden layer.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
“global regularisation reduces the amount of spurious false positive predictions and enforces abnormal LV segmentation shapes to fit into the learnt representation model.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
“It is important to note that the T-L regulariser model is used only at training time but not during inference; in other words, the fully convolutional (FCN) segmentation and super-resolution models can still be used for applications using different image sizes.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
“Moreover, we believe that adversarial training comes at the expense of less interpretability of the regularisation term and unstable model training behaviour, which still remains an open research problem.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“In SR application, AL enables the SR network to hallucinate fine texture detail, and the synthesized HR images appear qualitatively more realistic. However, at the same time the PSNR and SSIM scores are usually worse.”
What the sources say
- Not checked yetcites [26] [26] C. Ledig, L. Theis, F. Husz´ ar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, et al. Photo-realistic single image super-resolution using a generative adversarial network. arXiv preprint arXiv:1609.04802 , 2016. -
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
“The proposed regulariser model can be seen as an application-specific training objective.”
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
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
“The 3DSeg approach uses the convolution kernels more efficiently without requiring the model to output a high-dimensional intensity image.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: The clinical HR images used as reference for SR evaluation are accurate ground truth.
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
“The presented ACNN framework is not only limited to the medical image segmentation and SR tasks but can be extended to other image analysis tasks where prior knowledge can provide model guidance and robustness.”
Strength:plain· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✗ Checkable: fails✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Such approaches have been used successfully in natural image super-resolution (SR) [26] and segmentation [30] tasks.”
What the sources say
- Not checked yetcites [26] [26] C. Ledig, L. Theis, F. Husz´ ar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, et al. Photo-realistic single image super-resolution using a generative adversarial network. arXiv preprint arXiv:1609.04802 , 2016. - source
- Not checked yetcites [30] [30] P. Luc, C. Couprie, S. Chintala, and J. Verbeek. Semantic segmentation using adversarial networks. In NIPS Workshop on Adversarial Training , 2016. - source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“For this reason, the authors of [26] have pointed out that adversarial training may not be suitable for medical applications, where the accuracy and fidelity of the visual content more important than the qualitative appearance of the HR images.”
What the sources say
- Not checked yetcites [26] [26] C. Ledig, L. Theis, F. Husz´ ar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, et al. Photo-realistic single image super-resolution using a generative adversarial network. arXiv preprint arXiv:1609.04802 , 2016. -
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
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
“the additional K-L divergence term (constraint) would reduce the representation power of the AE; thus, the local anatomical variations would not be captured in detail.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. 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
“Additionally, non-linear layers are not applied on the lower dimensional latent representations since that would further constrain the autoencoder.”
Strength:hedged· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
“More importantly, cascaded approaches add additional computational complexity due to the increased number of filters, which could be redundant given that the standard segmentation model is able to capture shape properties of the organs as long as it has a large receptive field and is optimised with shape constraints.”
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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 contrast to this, our AE model is trained solely on cardiac segmentation masks and features are customised to identify anatomical variations observed in the heart chambers.”
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper relies on this without support.
The high-resolution motion-free cardiac MR images provide an appropriate reference for evaluating segmentation performance on low-resolution 2D stacks.
“Since the ground-truth information is obtained from the HR motionfree images, the experimental results are expected to reflect the performance of the method with respect to an appropriate reference.”
The paper relies on this without support.
A perfect mapping between intensity and label spaces is practically not achievable.
“Since a perfect mapping between the intensity and label spaces is practically not achievable, the T-L learnt codes are expected to be more representative due to the inclusion of additional information.”
The paper relies on this without support.
Anatomical objects in medical images are naturally more constrained in shape and location than objects in natural images.
“Inclusion of priors in medical imaging could potentially have much more impact compared to their use in natural image analysis since anatomical objects in medical images are naturally more constrained in terms of their shape and location.”
The authors state this as an assumption.
The proposed ACNN is one of the earliest studies demonstrating the use of convolutional autoencoder networks to learn anatomical shape variations from medical images.
“More importantly, to the best of our knowledge, this is one of the earliest studies demonstrating the use of convolutional autoencoder networks to learn anatomical shape variations from medical images.”
The paper relies on this without support.
The HR ground-truth label maps projected from HR image space are an accurate reference for segmentation evaluation.
“The corresponding groundtruth label maps, however, are projected from the HR image space, which are annotated in the HR image grid.”
The paper relies on this without support.
The clinical HR images used as reference for SR evaluation are accurate ground truth.
“The quality of the upsampled images is evaluated in terms of SSIM metric [47] between the clinical HR image data and reconstructed HR images.”
The paper relies on this without support.
The two expert cardiologists' MOS ratings reliably quantify image quality.
“Two expert cardiologists were asked to rate the upsampled images from 1 (very poor) to 5 (excellent) based on the accuracy of the reconstructed LV boundary and geometry.”
The paper relies on this without support.
The CETUS web platform evaluation is a valid blinded benchmark for segmentation accuracy.
“The experimental results were evaluated in a blinded fashion by uploading the generated segmentations from separate 30 sequences into the CETUS web platform.”
The paper relies on this without support.
The 2D stack LR images are a commonly used acquisition protocol for cardiac imaging.
“only the 2D stack LR images are used, which is a commonly used acquisition protocol for cardiac imaging”
The paper relies on this without support.
The LV blood pool is larger than the myocardium.
“due to the larger size of the LV blood pool compared to the myocardium.”
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?
In the citing paper
“the authors report performance superior to 3D-ACNN Oktay et al. (2017), achieving 4.3% increase in Dice and 4.15mm (40% less) improvement in Hausdorff distance .”
From Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation (2020) · cites this paper as Oktay et al. (2017)
In the citing paper
“The authors attribute the inferior performance by Ravishankar et al. (2017) to over-regularization, which they have overcome by replacing CDAE with a frozen encoder during training.”
From Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation (2020) · cites this paper as Oktay et al. (2017)
In the citing paper
“The suggested model achieves 1.2% and 2.0% improvement respectively in Dice over Ravishankar et al. (2017) for 3D endocardium and myocardium segmentation on a cine-MR dataset (1000 training and 200 testing).”
From Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation (2020) · cites this paper as Oktay et al. (2017)
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.
Cross-entropy and Euclidean gradients have their roles reversed
MinorThe text defines cross-entropy as the segmentation-reconstruction loss and Euclidean distance as the loss matching the predictor's latent codes. It then assigns the predictor-matching role to the first gradient, ∂L x, and the reconstruction role to the second, ∂L h-the reverse of those definitions.
“The first gradient encourages the encoder to generate codes that could be easily extracted by the predictor while the second gradient making sure that a good segmentation-reconstruction can be obtained at the output of the decoder.”
“In the first stage, the AE is trained separately with ground-truth segmentation masks and cross-entropy loss L x . Later, the predictor model is trained to match the learnt latent space h by minimising the Euclidean distance L h between the codes predicted by the AE and predictor as shown in Fig. 3.”
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 · cited 4×
“In that regard, our model differentiates from the VGG-Net [42] feature based training objectives [26], [21].”
MethodInfluentialU-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · cited 6×
“In that regard, the proposed SR model and U-Net segmentation models are concatenated to obtain HR segmentation results.”
BackgroundMethodInfluentialImage quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · cited 1×
“The quality of the upsampled images is evaluated in terms of SSIM metric [47] between the clinical HR image data and reconstructed HR images.”
MethodFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 1×
“In CNN based segmentation models [22], [29], [38], this task is performed by learning a discriminative function that models the underlying conditional probability distribution P(ys |x).”
MethodA survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332 · cited 2×
“As explained in a recent NN survey paper [28], the majority of the classification and regression models utilise a pixel-”
BackgroundConditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
Lafferty, J., McCallum, A., & Pereira, F. C. N. (2001) · ScholarlyCommons (University of Pennsylvania) · Cited by 12,935
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696 · cited 5×
“ture based training objectives [21], [26].”
BackgroundMethodInfluentialSelf-citationPhoto-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z.-H., et al. (2016) · Computer Vision and Pattern Recognition · doi:10.48550/arxiv.1609.04802 · Cited by 12,624
Self-citationPerceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283 · cited 3×
“Similar modifications of the objective function during training have been introduced to enhance the quality of natural images, such as perceptual [21] and adversarial [26] loss terms, which were used to synthesise more realistic images in terms of texture and object boundaries.”
Method3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46723-8_49 · Cited by 7,945
Flagged first, then by citations
7 of the 60 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Items 101–200 of 758
Leclerc, S., Smistad, E., Østvik, A., Cervenansky, F., Espinosa, F., Espeland, T., Berg, E. A. R., Belhamissi, M., Israilov, S., Grenier, T., et al. (2020) · IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control · doi:10.1109/tuffc.2020.3003403 · Cited by 65
“Oktay et al. [17] further extended a U-Net model so that its segmentation output was constrained to fit a nonlinear compact representation of the underlying anatomy derived from an autoencoder network.”
BackgroundJin, S., Yu, S., Peng, J., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-33357-y · Cited by 62
Global and Local Interpretability for Cardiac MRI Classification
Clough, J. R., Oksuz, I., Puyol-Antón, E., Ruijsink, B., King, A. P., & Schnabel, J. A. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-32251-9_72 · Cited by 73
Li, M., Wang, C., Zhang, H., & Yang, G. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103728 · Cited by 60
Cardiac MRI Segmentation with Strong Anatomical Guarantees
Painchaud, N., Skandarani, Y., Judge, T., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32245-8_70 · Cited by 60
“In particular, Oktay et al. used an approach named anatomically constrained neural network (ACNN) [5].”
BackgroundMethodInfluentialArtificial intelligence with deep learning in nuclear medicine and radiology
Decuyper, M., Maebe, J., Holen, R. V., & Vandenberghe, S. (2021) · EJNMMI Physics · doi:10.1186/s40658-021-00426-y · Cited by 61
TransBridge: A Lightweight Transformer for Left Ventricle Segmentation in Echocardiography
Deng, K., Meng, Y., Gao, D., Bridge, J., Shen, Y., Lip, G. Y. H., Zhao, Y., & Zheng, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87583-1_7 · Cited by 74
“Echocardiography imaging is essential for evaluating cardiac functions in clinical practice, such as left ventricular ejection fraction [16].”
MethodDeep learning and its application to medical image segmentationPreprint
Roth, H. R., Shen, C., Oda, H., Oda, M., Hayashi, Y., Misawa, K., & Mori, K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08691 · Cited by 136
A Review on Progress in Semantic Image Segmentation and Its Application to Medical Images
Kar, M. K., Nath, M. K., & Neog, D. R. (2021) · SN Computer Science · doi:10.1007/s42979-021-00784-5 · Cited by 65
Deep MR Brain Image Super-Resolution Using Spatio-Structural Priors
Cherukuri, V., Guo, T., Schiff, S. J., & Monga, V. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2942510 · Cited by 63
“Future work could develop and incorporate other meaningful priors such as those that are anatomically inspired [54].”
BackgroundZhao, M., Liu, X., Liu, H., & Wong, K. K. L. (2020) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2020.101698 · Cited by 61
ResDUnet: A Deep Learning-Based Left Ventricle Segmentation Method for Echocardiography
Amer, A., Ye, X., & Janan, F. (2021) · IEEE Access · doi:10.1109/access.2021.3122256 · Cited by 56
“Leclerc et al. [5], showed that the aforementioned U-net implementations outperformed the sophisticated deep learning approach proposed by Oktay et al. [15], and the B-spline prior approach suggested by Barbosa et al. [11].”
MethodCross-dimensional transfer learning in medical image segmentation with deep learning
Messaoudi, H., Belaid, A., Salem, D. B., & Conze, P.-H. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102868 · Cited by 62
Jafari, M. H., Girgis, H., Woudenberg, N. V., Liao, Z., Rohling, R. N., Gin, K., Abolmaesumi, P., & Tsang, T. S. M. (2019) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-019-01954-w · Cited by 57
Deep Atlas Network for Efficient 3D Left Ventricle Segmentation on Echocardiography
Dong, S., Luo, G., Tam, C., Wang, W., Wang, K., Cao, S., Chen, B., Zhang, H., & Li, S. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101638 · Cited by 54
Temporal-Consistent Segmentation of Echocardiography with Co-learning from Appearance and Shape
Wei, H., Cao, H., Cao, Y., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59713-9_60 · Cited by 56
Learning With Context Feedback Loop for Robust Medical Image Segmentation
Girum, K. B., Créhange, G., & Lalande, A. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3060497 · Cited by 56
“results [25], incorporating the prior knowledge such as shape models [26], [27], or using transfer learning from pre-trained”
BackgroundMethodInfluentialSemi-supervised Learning for Segmentation Under Semantic Constraint
Ganaye, P.-A., Sdika, M., & Benoit-Cattin, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00931-1_68 · Cited by 51
“In [9], Oktay et. al . went further by learning a representation of the label space with an auto-encoder, extracting shape and location priors of the structures.”
BackgroundHaq, R., Hotca, A. E., Apte, A., Rimner, A., Deasy, J. O., & Thor, M. (2020) · Physics and Imaging in Radiation Oncology · doi:10.1016/j.phro.2020.05.009 · Cited by 56
Arbitrary Scale Super-Resolution for Medical Images
Zhu, J., Tan, C. Q., Yang, J., Yang, G., & Lió, P. (2021) · International Journal of Neural Systems · doi:10.1142/s0129065721500374 · Cited by 61
Causal knowledge fusion for 3D cross-modality cardiac image segmentation
Guo, S., Liu, X., Zhang, H., Lin, Q., Xu, L., Shi, C., Gao, Z., Guzzo, A., & Fortino, G. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101864 · Cited by 58
Artificial intelligence: improving the efficiency of cardiovascular imaging
Lin, A., Kolossváry, M., Išgum, I., Maurovich‐Horvat, P., Slomka, P. J., & Dey, D. (2020) · Expert Review of Medical Devices · doi:10.1080/17434440.2020.1777855 · Cited by 59
A Survey on Shape-Constraint Deep Learning for Medical Image Segmentation
Bohlender, S., Öksüz, İ., & Mukhopadhyay, A. (2021) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2021.3136343 · Cited by 72
“A famous AE approach is introduced by [128] and is known as”
BackgroundSegmentation of histological images and fibrosis identification with a convolutional neural network
Fu, X., Liu, T., Xiong, Z., Smaill, B. H., Stiles, M. K., & Zhao, J. (2018) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2018.05.015 · Cited by 53
Jia, S., Despinasse, A., Wang, Z., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-12029-0_24 · Cited by 53
Wang, W., Xia, Q., Hu, Z., Yan, Z., Li, Z., Wu, Y., Huang, N., Gao, Y., Metaxas, D., & Zhang, S. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3053008 · Cited by 52
“Some recent methods [47], [48] have tried to incorporate shape priors into segmentation networks in supervised learning to encourage the prediction to be similar to the learned shape and ground truth.”
RIANet: Recurrent interleaved attention network for cardiac MRI segmentation
Tong, Q., Li, C., Si, W., Liao, X., Tong, Y., Yuan, Z., & Heng, P. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.04.042 · Cited by 54
TPSSI-Net: Fast and Enhanced Two-Path Iterative Network for 3D SAR Sparse Imaging
Wang, M., Wei, S., Liang, J., et al. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3104168 · Cited by 52
Overview of the Whole Heart and Heart Chamber Segmentation Methods
Habijan, M., Babin, D., Galić, I., Leventić, H., Romić, K., Velicki, L., & Pižurica, A. (2020) · Cardiovascular Engineering and Technology · doi:10.1007/s13239-020-00494-8 · Cited by 48
“Further refinement of the segmentation results obtained using CNN can be seen in terms of incorporating prior knowledge using ASMs or by training with a new regularization model as presented by Oktay et al. 82 .”
MethodA Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR
Byrne, N., Clough, J. R., Valverde, I., Montana, G., & King, A. P. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3203309 · Cited by 53
“Other works have attempted to inject prior information into CNN optimisation directly, via a learned, latent representation of anatomically plausible shapes [16].”
BackgroundMedical Image Segmentation Using Transformer Networks
Karimi, D., Dou, H., & Gholipour, A. (2022) · IEEE Access · doi:10.1109/access.2022.3156894 · Cited by 54
“There have also been attempts to improve the accuracy and robustness of these methods by modeling the statistical variation in the shape of the organ of interest and incorporating this shape information in the deep learning method [12], [22], [23].”
Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders
Larrazabal, A. J., Martínez, C. E., & Ferrante, E. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32226-7_65 · Cited by 47
“ding on the image properties of every dataset. Instead, our method is trained once and can be used independently of the image propierties. Note that we do not compare Post-DAE with other methods like [6,7] which incorporate anatomical priors while training the segmentation method itself, since these are not post-proce…”
MethodInfluentialSelf-citationUndersampled MR image reconstruction using an enhanced recursive residual network
Bao, L., Ye, F., Cai, C., Wu, J., Zeng, K., van Zijl, P. C. M., & Chen, Z. (2019) · Journal of Magnetic Resonance · doi:10.1016/j.jmr.2019.07.020 · Cited by 48
Shiode, R., Mototaka, K., Hiasa, Y., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-94634-2 · Cited by 49
Comparative studies of deep learning segmentation models for left ventricle segmentation
Shoaib, M. A., Lai, K. W., Chuah, J. H., et al. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2022.981019 · Cited by 48
“Deep learning-based architecture “Fully Convolutional Network (FCN)” (38) is used for LV segmentation in CT images, U-Net on MRI images (39, 40), U-Net on 2D echocardiography images (41), and another U-Net-based architecture “Anatomically Constrained Neural Network (ACNN)” (42) is used for 3D images.”
MethodDomain and Geometry Agnostic CNNs for Left Atrium Segmentation in 3D Ultrasound
Degel, M., Navab, N., & Albarqouni, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00937-3_72 · Cited by 47
“The increased performance of C3 compared to V-Net and ACNN is significant with respect to all metrics.”
BackgroundMethodInfluentialGilbert, K., Bai, W., Mauger, C., Medrano−Gracia, P., Suinesiaputra, A., Lee, A. M., Sanghvi, M. M., Aung, N., Piechnik, S. K., Neubauer, S., et al. (2019) · Scientific Reports · doi:10.1038/s41598-018-37916-6 · Cited by 46
Self-citationLearning Shape Priors for Robust Cardiac MR Segmentation from Multi-view Images
Chen, C., Biffi, C., Tarroni, G., Petersen, S. E., Bai, W., & Rueckert, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32245-8_58 · Cited by 61
“tional cost and requires an extra post-processing step to merge the predictions from the two networks. Another approach is to incorporate cardiac anatomical prior knowledge into segmentation networks [10,11]. In [10], the learned representation of the 3D cardiac shape is employed to constrain the segmentation model to…”
MethodSelf-citationPrior-aware Neural Network for Partially-Supervised Multi-Organ SegmentationPreprint
Zhou, Y., Li, Z., Bai, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.06346 · Cited by 47
Liu, Z., Ni, S., Yang, C., Sun, W., Huang, D., Su, H., Shu, J., & Qin, N. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104715 · Cited by 47
Liu, X., Qu, L., Xie, Z., Zhao, J., Shi, Y., & Song, Z. (2024) · BioMedical Engineering OnLine · doi:10.1186/s12938-024-01238-8 · Cited by 69
Sdiri, B., Kaaniche, M., Cheikh, F. A., Beghdadi, A., & Elle, O. J. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2853808 · Cited by 46
“As a result, other medical image enhancement methods which adjust the coefficients using specific mapping functions, neural networks [11], [12], or filtering techniques [13], [14], have been designed.”
BackgroundSekuboyina, A., Rempfler, M., Valentinitsch, A., et al. (2020) · Radiology Artificial Intelligence · doi:10.1148/ryai.2020190074 · Cited by 46
“However, Btrfly Net was fundamentally different in the training and inference processes compared with the previous work (12,13).”
BackgroundMethodResultInfluentialJafari, M. H., Girgis, H., Liao, Z., Behnami, D., Abdi, A. H., Vaseli, H., Luong, C. L., Rohling, R. N., Gin, K., Tsang, T. S. M., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00889-5_4 · Cited by 50
Ge, R., Yang, G., Chen, Y., Luo, L., Feng, C., Zhang, H., & Li, S. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101554 · Cited by 45
Wei, H., Ma, J., Zhou, Y., Xue, W., & Ni, D. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102686 · Cited by 46
CNN-based superresolution reconstruction of 3D MR images using thick-slice scans
Jurek, J., Kociński, M., Materka, A., et al. (2019) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2019.10.003 · Cited by 44
Distracted driving recognition method based on deep convolutional neural network
Rao, X., Lin, F., Chen, Z., & Zhao, J. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-019-01597-4 · Cited by 44
Lesion Segmentation in Ultrasound Using Semi-Pixel-Wise Cycle Generative Adversarial Nets
Xing, J., Li, Z., Wang, B., Qi, Y., Yu, B., Zanjani, F. G., Zheng, A., Duits, R., & Tan, T. (2020) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2020.2978470 · Cited by 47
“The generator used above itself is an FCN and this type of network is applied extensively in ultrasound [33], [34], [35], [36], [37], [38] [39], [40] for various applications.”
MethodZhang, W., Yang, G., Zhang, N., Xu, L., Wang, X., Zhang, Y., Zhang, H., Ser, J. D., & de Albuquerque, V. H. C. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.01.009 · Cited by 44
Sinclair, M. D., Schuh, A., Hahn, K., Petersen, K., Bai, Y., Batten, J., Schaap, M., & Glocker, B. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102383 · Cited by 45
Self-citationA Densely Connected Network Based on U-Net for Medical Image Segmentation
Yang, Z., Xu, P., Yang, Y., & Bao, B. (2021) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3446618 · Cited by 42
“Nowadays, the medical image segmentation [1] is very important and has been widely used in the field of biomedical engineering.”
BackgroundLucas, C., Kemmling, A., Bouteldja, N., Aulmann, L. F., Mamlouk, A. M., & Heinrich, M. P. (2018) · Frontiers in Neurology · doi:10.3389/fneur.2018.00989 · Cited by 41
Self-citationQiao, S., Pang, S., Luo, G., Pan, S., Chen, T., & Lv, Z. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3091579 · Cited by 41
“Oktay et al. [21] presented an anatomically constrained neural network (ACNN) to detect left ventricle endocardium in adult US images.”
Background3D Graph-Connectivity Constrained Network for Hepatic Vessel Segmentation
Li, R., Huang, Y.-J., Chen, H., Liu, X., Yu, Y., Qian, D., & Wang, L. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3118104 · Cited by 40
Compressed Domain Deep Video Super-Resolution
Chen, P., Yang, W., Wang, M., et al. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3101826 · Cited by 40
Upadhyay, A. K., & Bhandari, A. K. (2023) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-10028-9 · Cited by 45
“Oktay et al. [114] presented anatomically constrained CNNs that Uneven illumination and structural losses in medical images make it difficult for automatic analysis.”
Fast and accurate reconstruction of human lung gas MRI with deep learning
Duan, C., Deng, H., Xiao, S., Xie, J., Li, H., Sun, X., Ma, L., Lou, X., Ye, C., & Zhou, X. H. (2019) · Magnetic Resonance in Medicine · doi:10.1002/mrm.27889 · Cited by 38
Removing segmentation inconsistencies with semi-supervised non-adjacency constraint
Ganaye, P.-A., Sdika, M., Triggs, B., & Benoit-Cattin, H. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101551 · Cited by 37
Image quality recognition technology based on deep learning
He, T., & Li, X. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.102654 · Cited by 40
Wu, C., Qiao, Z., Zhang, N., et al. (2020) · Biomedical Optics Express · doi:10.1364/boe.386101 · Cited by 39
Sedghi, A., Mehrtash, A., Jamzad, A., Amalou, A., Wells, W. M., Kapur, T., Kwak, J. T., Türkbey, B., Choyke, P. L., Pinto, P. A., et al. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02172-5 · Cited by 39
“Several groups [20,21] have proposed different strategies for training that can deal with missing data from one of the modalities at testtime.”
BackgroundAdaptive Fractional Image Enhancement Algorithm Based on Rough Set and Particle Swarm Optimization
Zhang, X., Liu, R., Ren, J., et al. (2022) · Fractal and Fractional · doi:10.3390/fractalfract6020100 · Cited by 39
Dong, S., Luo, G., Wang, K., Cao, S., Mercado, A., Shmuilovich, O., Zhang, H., & Li, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00937-3_71 · Cited by 43
Deep Multi-Class Segmentation Without Ground-Truth Labels
Joyce, T. A., Chartsias, A., & Tsaftaris, S. A. (2018) · Cited by 39
Predicting EGFR mutational status from pathology images using a real-world dataset
Pao, J. J., Biggs, M., Duncan, D., Lin, D. I., Davis, R., Huang, R. S. P., Ferguson, D., Janovitz, T., Hiemenz, M. C., Eddy, N. R., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-31284-6 · Cited by 40
Khor, H. G., Ning, G., Sun, Y., Xu, L., Zhang, X., & Liao, H. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102811 · Cited by 41
Three-dimensional cardiovascular imaging-genetics: a mass univariate framework
Biffi, C., de Marvao, A., Attard, M., Dawes, T. J. W., Whiffin, N., Bai, W., Shi, W., Francis, C., Meyer, H. V., Buchan, R. J., et al. (2017) · Bioinformatics · doi:10.1093/bioinformatics/btx552 · Cited by 37
Self-citationNogovitsyn, N., de Souza, R. M., Muller, M., Srajer, A., Hassel, S., Arnott, S. R., Davis, A. D., Hall, G. B., Harris, J. K., Zamyadi, M., et al. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.05.017 · Cited by 38
StoolNet for Color Classification of Stool Medical Images
Yang, Z., Leng, L., & Kim, B. (2019) · Electronics · doi:10.3390/electronics8121464 · Cited by 37
Azzopardi, C., Camilleri, K. P., & Hicks, Y. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.2965088 · Cited by 37
“Their framework involved combining a stacked convolutional autoencoder within a T-L network to learn a non-linear compact representation of the underlying anatomy, and then forcing network predictions to follow the learnt shape/label distributions[32].”
BackgroundMethodResultInfluentialArtificial Intelligence in Cardiac Imaging With Statistical Atlases of Cardiac Anatomy
Gilbert, K., Mauger, C., Young, A. A., & Suinesiaputra, A. (2020) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2020.00102 · Cited by 41
Ahmed, S., Kamal, U., & Hasan, M. K. (2020) · Ultrasonics · doi:10.1016/j.ultras.2020.106283 · Cited by 37
Beetz, M., Banerjee, A., Ossenberg-Engels, J., & Grau, V. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102975 · Cited by 43
Unified model for interpreting multi-view echocardiographic sequences without temporal information
Li, M., Dong, S., Gao, Z., Feng, C., Xiong, H., Zheng, W., Ghista, D. N., Zhang, H., & de Albuquerque, V. H. C. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2019.106049 · Cited by 37
Neural networks for open and closed Literature-based Discovery
Crichton, G., Baker, S., Guo, Y., & Korhonen, A. (2020) · PLoS ONE · doi:10.1371/journal.pone.0232891 · Cited by 36
Wang, L., Guo, D., Wang, G., & Zhang, S. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3047807 · Cited by 46
Thomas, S., Gilbert, A., & Ben-Yosef, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16440-8_37 · Cited by 44
Wu, X., Udupa, J. K., Tong, Y., et al. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.01.008 · Cited by 35
Medical image segmentation algorithm based on feedback mechanism convolutional neural network
Feng-Ping, A., & Liu, Z. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.101589 · Cited by 34
Deep Biomedical Image Classification Using Diagonal Bilinear Interpolation and residual network
Assad, M. B., & Kiczales, R. (2020) · International Journal of Intelligent Networks · doi:10.1016/j.ijin.2020.11.001 · Cited by 35
Advanced Ultrasound and Photoacoustic Imaging in Cardiology
Wu, M., Awasthi, N., Rad, N. M., Pluim, J. P. W., & Lopata, R. G. P. (2021) · Sensors · doi:10.3390/s21237947 · Cited by 38
“[72] introduced an anatomically constrained CNN for LV segmentation.”
BackgroundMethodDeep Implicit Statistical Shape Models for 3D Medical Image Delineation
Raju, A., Miao, S., Jin, D., Lü, L., Huang, J., & Harrison, A. P. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20110 · Cited by 34
“Another line of work use indirect voxel-based constraints by auto-encoders (AEs) [36, 41] or generative adversarial networks (GANs) [49, 40, 4], but these are hard to interpret and are not invariant to rigid similarity transforms, meaning a true shape prior is not constructed [14].”
BackgroundMethodA Framework for Interpretability in Machine Learning for Medical Imaging
Wang, A. Q., Karaman, B. K., Kim, H., Rosenthal, J., Saluja, R., Young, S. I., & Sabuncu, M. R. (2024) · IEEE Access · doi:10.1109/access.2024.3387702 · Cited by 41
“In classification, mechanistic models [8] and anatomical priors [24] incorporate knowledge of specific objects of interest into the architecture, for example brain midline shift [97], models for tumor growth [41], and cardiac image enhancement and segmentation [89].”
BackgroundDeeply self-supervised contour embedded neural network applied to liver segmentation
Chung, M., Lee, J., Lee, M.-K., Lee, J., & Shin, Y.-G. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105447 · Cited by 32
“The authors attempted to construct convolutional autoencoder networks to learn anatomical shape variations from training images [33].”
BackgroundHybrid Automatic Lung Segmentation on Chest CT Scans
Peng, T., Xu, T. C., Wang, Y., et al. (2020) · IEEE Access · doi:10.1109/access.2020.2987925 · Cited by 33
“[18] have presented an anatomically constrained neural networks model to enhance and segment cardiac images, but it requires prior knowledge of an anatomical shape.”
BackgroundKoo, H. J., Lee, J., Ko, J. Y., et al. (2020) · Korean Journal of Radiology · doi:10.3348/kjr.2019.0378 · Cited by 33
“Therefore, highly accurate automatic LV wall segmentation methods have been investigated using computed tomography (CT), magnetic resonance imaging (MRI), and echocardiography (2-7).”
MethodInterpretable cardiac anatomy modeling using variational mesh autoencoders
Beetz, M., Acero, J. C., Banerjee, A., Eitel, I., Zacur, E., Lange, T., Stiermaier, T., Evertz, R., Backhaus, S. J., Thiele, H., et al. (2022) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2022.983868 · Cited by 36
Medical Imaging with Deep Learning for COVID- 19 Diagnosis: A Comprehensive ReviewPreprint
Bharati, S., Podder, P., Mondal, M. R. H., & Prasath, V. B. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.09602 · Cited by 50
“The authors of [87] suggested a new approach to address this problem by applying a basic learning process that embeds prior information into CNNs utilizing a thoroughly qualified regularization model.”
BackgroundZhao, C., Chen, W., Qin, J., Yang, P., Xiang, Z., Frangi, A. F., Chen, M., Fan, S., Yu, W., Chen, X., et al. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102648 · Cited by 32
Whole Heart Segmentation from CT images Using 3D U-Net architecture
Habijan, M., Leventić, H., Galić, I., et al. (2019) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip.2019.8787253 · Cited by 32
“Since cardiac images contain a huge amount of anatomical variability and unclear boundaries that are often caused by lacks in acquisition procedures, methods that incorporate prior knowledge and artificial neural networks have recently commonly used [7], [8].”
BackgroundShape Constrained Network for Eye Segmentation in the Wild
Luo, B., Shen, J., Cheng, S., et al. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093483 · Cited by 32
“Inspired by ACNN [29], we regularise the shape prediction in the latent space of pre-trained VAE-GAN.”
MethodCardiac point-of-care to cart-based ultrasound translation using constrained CycleGAN
Jafari, M. H., Girgis, H., Woudenberg, N. V., Moulson, N., Luong, C. L., Fung, A., Balthazaar, S. J. T., Jue, J., Tsang, M. B., Nair, P., et al. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02141-y · Cited by 31
Li, X., Liu, X., Deng, X., & Fan, Y. (2022) · Biomedicines · doi:10.3390/biomedicines10092157 · Cited by 32
Selecting the best optimizers for deep learning–based medical image segmentation
Mortazi, A., Çiçek, V., Keleş, E., et al. (2023) · Frontiers in Radiology · doi:10.3389/fradi.2023.1175473 · Cited by 31
“The shape before information from deep networks was used to guide segmentation network to delineate cardiac substructures from MR images (40, 41).”
MethodJafari, M. H., Girgis, H., Abdi, A. H., et al. (2019) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2019.8759292 · Cited by 31
“Deep learning solutions have also been investigated to tackle this challenging task [2], including utilization of anatomical shape priors [3], and employing the U-Net architecture and its variations [4, 5].”
MethodUnsupervised Deep Contrast Enhancement With Power Constraint for OLED Displays
Shin, Y.-G., Park, S., Yeo, Y.-J., Yoo, M.-J., & Ko, S.-J. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2953352 · Cited by 31
“performance compared to non-deep learning methods as demonstrated in [17]–[20].”
BackgroundResultRU-Net: A refining segmentation network for 2D echocardiography
Leclerc, S., Jodoin, P., Løvstakken, L., et al. (2019) · IEEE International Ultrasonics Symposium · doi:10.1109/ultsym.2019.8926158 · Cited by 31
“In EDN frameworks, refining the segmentation has been addressed by cascaded networks, either trained end-to-end as Stacked Hourglasses (SHG) [4] or trained separately to derive a shape constraint as Anatomically Constrained Neural Networks (ACNN) [5].”
MethodAIDAN: An Attention-Guided Dual-Path Network for Pediatric Echocardiography Segmentation
Hu, Y., Xia, B., Mao, M., Jin, Z., Du, J., Guo, L., Frangi, A. F., Lei, B., & Wang, T. (2020) · IEEE Access · doi:10.1109/access.2020.2971383 · Cited by 30
“RELATED WORKS A. SEGMENTATION METHODS WITHOUT ATTENTION MECHANISMS Fully convolutional neural network (FCN) [24] and U-Net [40] are the first two neural networks attempting semantic segmentation in a fully convolutional manner in computer vision and biomedical image analysis, respectively.”
BackgroundInfluentialChung, M., Lee, J., Park, S., Lee, C. E., Lee, J., & Shin, Y.-G. (2021) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102023 · Cited by 35
Metadata
- Authors
- Oktay, O., Ferrante, E., Kamnitsas, K., Heinrich, M., Bai, W., Caballero, J., Cook, S. A., de Marvao, A., Dawes, T., O'Regan, D. P., Kainz, B., Glocker, B., & Rueckert, D.
- Affiliations
- Imperial College London (GB)
- ORCID
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2018-02
- Volume
- 37
- Issue
- 2
- Pages
- 384-395
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W2620296437
- Semantic Scholar
- 33f7b95903eeefdde37fabf9655b4de089d53bd2
- Cited by
- 751
- References
- 60
- Citations by year
- 2026: 34 · 2025: 64 · 2024: 61 · 2023: 87 · 2022: 81 · 2021: 135 · 2020: 118 · 2019: 119 · 2018: 47
- FWCI
- 32.79
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- National University of Singapore (submittedVersion)
- Spiral (Imperial College London) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- EPSRC Program (EP/P001009/1)
- British Heart Foundation, U.K. (PG/12/27/29489)
- National Institute for Health Research (NIHR) Biomedical Research Centre-based at Imperial College Healthcare NHS Trust
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- anatomical prior knowledge, cardiac image segmentation, biomarkers, artifact reduction
- MeSH terms
- Algorithms, Heart, Humans, Magnetic Resonance Imaging, Cardiomyopathies, Databases, Factual, Neural Networks, Computer, Imaging, Three-Dimensional, Cardiac Imaging Techniques
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).
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
