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
Zhou, S. K., Greenspan, H. K., Davatzikos, C. A., Duncan, J. S., van Ginneken, B., Madabhushi, A., Prince, J. L., Rueckert, D., & Summers, R. M. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3054390 · Cited by 1,373
“[168]) and were nicely included in an anatomicallyconstrained deep learning strategy by [169].”
BackgroundSelf-citationEmbracing imperfect datasets: A review of deep learning solutions for medical image segmentation
Tajbakhsh, N., Jeyaseelan, L., Li, Q., Chiang, J. N., Wu, Z., & Ding, X. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101693 · Cited by 1,095
“For the task of myocardium segmentation, the authors report performance superior to 3D-ACNN Oktay et al. (2017),”
MethodDeep Learning for Cardiac Image Segmentation: A Review
Chen, C., Qin, C., Qiu, H., Tarroni, G., Duan, J., Bai, W., & Rueckert, D. (2020) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2020.00025 · Cited by 1,002
Self-citationMedical image segmentation using deep learning: A survey
Wang, R., Lei, T., Cui, R., Zhang, B., Meng, H., & Nandi, A. K. (2022) · IET Image Processing · doi:10.1049/ipr2.12419 · Cited by 1,012
“[124] proposed a novel and general method to combine a priori knowledge of shape and label structure into the anatomically constrained neural networks”
MethodDeep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography
Leclerc, S., Smistad, E., Pedrosa, J., Ostvik, A., Cervenansky, F., Espinosa, F., Espeland, T., Berg, E. A. R., Jodoin, P., Grenier, T., et al. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2900516 · Cited by 841
“[19] used CNNs to segment the 3D”
MethodInfluentialAutomatic Multi-Organ Segmentation on Abdominal CT With Dense V-Networks
Gibson, E., Giganti, F., Hu, Y., Bonmati, E., Bandula, S., Gurusamy, K. S., Davidson, B. R., Pereira, S. P., Clarkson, M. J., & Barratt, D. C. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2806309 · Cited by 701
“Imposing shape [29] and topological [30] constraints between specified organs also remains”
Ali, O., Abdelbaki, W., Shrestha, A., Elbasi, E., Alryalat, M. A. A., & Dwivedi, Y. K. (2023) · Journal of Innovation & Knowledge · doi:10.1016/j.jik.2023.100333 · Cited by 568
Deep learning and medical image processing for coronavirus (COVID-19) pandemic: A survey
Bhattacharya, S., Maddikunta, P. K. R., Pham, Q., Gadekallu, T. R., Siva Rama Krishnan, S., Chowdhary, C. L., Alazab, M., & Piran, M. J. (2020) · Sustainable Cities and Society · doi:10.1016/j.scs.2020.102589 · Cited by 495
“The authors in Oktay et al. (2017) propose a novel technique to overcome this challenge by implementing a generic training strategy that embeds prior knowledge into the CNNs using a regularisation model which is trained thoroughly.”
Automated deep-neural-network surveillance of cranial images for acute neurologic events
Titano, J. J., Badgeley, M., Schefflein, J., Pain, M., Su, A., Cai, M., Swinburne, N., Zech, J., Kim, J., Bederson, J., et al. (2018) · Nature Medicine · doi:10.1038/s41591-018-0147-y · Cited by 458
Deep learning for cardiovascular medicine: a practical primer
Krittanawong, C., Johnson, K. W., Rosenson, R. S., Wang, Z., Aydar, M., Baber, U., Min, J. K., Tang, W. H. W., Halperin, J. L., & Narayan, S. M. (2019) · European Heart Journal · doi:10.1093/eurheartj/ehz056 · Cited by 452
Khened, M., Kollerathu, V. A., & Krishnamurthi, G. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.10.004 · Cited by 387
Ambellan, F., Tack, A., Ehlke, M., & Stefan Zachow, A. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.11.009 · Cited by 369
Deep learning for cardiac image segmentation: A review
Chen, C., Qin, C., Qiu, H., Tarroni, G., Duan, J., Bai, W., & Rueckert, D. (2019) · City Research Online (City University London) · Cited by 358
Self-citationAn application of cascaded 3D fully convolutional networks for medical image segmentation
Roth, H. R., Oda, H., Zhou, X., Shimizu, N., Yang, Y., Hayashi, Y., Oda, M., Fujiwara, M., Misawa, K., & Mori, K. (2018) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2018.03.001 · Cited by 330
“Furthermore, additional anatomical constraints could be included in order to guarantee topologically correct segmentation results (BenTaieb and Hamarneh, 2016; Oktay et al., 2017).”
BackgroundEmbracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image SegmentationPreprint
Tajbakhsh, N., Jeyaseelan, L., Li, Q., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.10454 · Cited by 324
“For the task of myocardium segmentation, the authors report performance superior to 3D-ACNN Oktay et al. (2017),”
MethodA survey on incorporating domain knowledge into deep learning for medical image analysis
Xie, X., Niu, J., Liu, X., Chen, Z., Tang, S., & Yu, S. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.101985 · Cited by 331
Chen, H., Gomez, C., Huang, C.-M., & Unberath, M. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00699-2 · Cited by 300
Machine learning in cardiovascular magnetic resonance: basic concepts and applications
Leiner, T., Rueckert, D., Suinesiaputra, A., Baeßler, B., Nezafat, R., Išgum, I., & Young, A. A. (2019) · Journal of Cardiovascular Magnetic Resonance · doi:10.1186/s12968-019-0575-y · Cited by 289
Self-citationA Review of the Deep Learning Methods for Medical Images Super Resolution Problems
Li, Y., Sixou, B., & Peyrin, F. (2020) · IRBM · doi:10.1016/j.irbm.2020.08.004 · Cited by 295
A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology
Clough, J. R., Byrne, N., Öksüz, İ., Zimmer, V. A., Schnabel, J. A., & King, A. P. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3013679 · Cited by 281
Isensee, F., Jaeger, P. F., Full, P. M., Ivo Wolf, A., Engelhardt, S., & Maier-Hein, K. H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-75541-0_13 · Cited by 313
Fully Convolutional Architectures for Multiclass Segmentation in Chest Radiographs
Novikov, A. A., Lenis, D., Major, D., Hladůvka, J., Wimmer, M., & Bühler, K. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2806086 · Cited by 275
“[39], or favouring abstract loss objectives as described by Baumgartner et al.”
BackgroundIkechukwu, A. V., Murali, S., Deepu, R., & Shivamurthy, R. C. (2021) · Global Transitions Proceedings · doi:10.1016/j.gltp.2021.08.027 · Cited by 267
An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation
Baumgartner, C. F., Koch, L. M., Pollefeys, M., & Ender Konukoglu, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-75541-0_12 · Cited by 234
“For the LV cavity two recent deep learning methods [1,14] report Dice scores of around 0.”
MethodDuan, J., Bello, G., Schlemper, J., Bai, W., Dawes, T. J. W., Biffi, C., de Marvao, A., Doumoud, G., O'Regan, D. P., & Rueckert, D. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2894322 · Cited by 227
Self-citationPET Image Denoising Using a Deep Neural Network Through Fine Tuning
Gong, K., Guan, J., Liu, C., & Qi, J. (2018) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2018.2877644 · Cited by 245
“The idea is similar to the one used in the anatomically constrained network [22], where features were extracted from the hidden layer of an auto-encoder.”
MethodEL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection
Ghafoorian, M., Nugteren, C., Baka, N., Booij, O., & Hofmann, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11009-3_15 · Cited by 234
“Examples include road scene understanding for autonomous driving [1, 2, 3] and medical imaging [4, 5, 6, 7, 8, 9].”
BackgroundMethodHigh-Resolution Encoder–Decoder Networks for Low-Contrast Medical Image Segmentation
Zhou, S., Nie, D., Adeli, E., Yin, J., Lian, J., & Shen, D. G. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2919937 · Cited by 230
“[18] modified the convolutional neural network by adding an autoencoder to enforce the prediction of the network to be close to the groundtruth label map in both the original image space and the low dimensional manifold.”
MethodBillot, B., Magdamo, C., Cheng, Y., Arnold, S. E., Das, S., & Iglesias, J. E. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2216399120 · Cited by 261
“Recent approaches have sought to solve this problem by modelling high-order topological relations, either by aligning predictions and ground truths in latent space during training (26), by correcting predictions with a registered atlas (27), or with denoising networks (28).”
BackgroundMulti-modal deep learning model for auxiliary diagnosis of Alzheimer’s disease
Zhang, F., Li, Z., Zhang, B., Du, H., Wang, B., & Zhang, X. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.04.093 · Cited by 245
Left-Ventricle Quantification Using Residual U-Net
Kerfoot, E., Clough, J. R., Öksüz, İ., Lee, J., King, A. P., & Schnabel, J. A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-12029-0_40 · Cited by 244
3-D Consistent and Robust Segmentation of Cardiac Images by Deep Learning With Spatial Propagation
Zheng, Q., Delingette, H., Duchateau, N., & Ayache, N. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2820742 · Cited by 200
“In [9], the segmentation models are trained to follow the cardiac anatomical properties via a learned representation of the 3D shape.”
MethodDisentangled representation learning in cardiac image analysis
Chartsias, A., Joyce, T., Papanastasiou, G., Semple, S. I. K., Williams, M. C., Newby, D. E., Dharmakumar, R., & Tsaftaris, S. A. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101535 · Cited by 197
Attention-Enriched Deep Learning Model for Breast Tumor Segmentation in Ultrasound Images
Vakanski, A., Xian, M., & Freer, P. E. (2020) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2020.06.015 · Cited by 198
“logy gland segmentation (BenTaieb and Hamarneh 2016). Likewise, loss functions in FCNs that encode a shape prior were proposed for kidney segmentation (Ravishankar et al. 2017), cardiac segmentation (Oktay et al. 2018a), and segmentation of star shapes in skin lesions (Mirikharaji and Hamarneh 2018). The disadvantage…”
BackgroundMethodInfluentialA machine learning-based framework for diagnosis of COVID-19 from chest X-ray images
Rasheed, J., Hameed, A. A., Djeddi, C., Jamıl, A., & Al-Turjman, F. M. (2021) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-020-00403-6 · Cited by 194
Test-time adaptable neural networks for robust medical image segmentation
Karani, N., Erdil, E., Chaitanya, K., & Konukoğlu, E. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101907 · Cited by 186
“Imposing Shape Constraints during Training: Another widely suggested idea is to impose shape / topological constraints on the predicted segmentations [21]–[27].”
BackgroundPrior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation
Zhou, Y., Li, Z., Bai, S., Chen, X., Han, M., Wang, C., Fishman, E. K., & Yuille, A. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01077 · Cited by 202
Review of Semantic Segmentation of Medical Images Using Modified Architectures of UNET
Devi, M. K. A. A., & Suganthi, K. (2022) · Diagnostics · doi:10.3390/diagnostics12123064 · Cited by 199
“It measures the precision of prediction [48–52] by counting the number of actual samples.”
Adversarial Image Synthesis for Unpaired Multi-modal Cardiac Data
Chartsias, A., Joyce, T., Dharmakumar, R., & Tsaftaris, S. A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68127-6_1 · Cited by 194
“Recently, cardiac super-resolution has been enhanced by incorporating a shape prior in the learning process [13].”
BackgroundBizopoulos, P., & Koutsouris, D. (2018) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2018.2885714 · Cited by 199
“ing strategy [167] that incorporates anatomical prior knowledge into CNNs through a regularization model, by encouraging it to follow the anatomy via learned non-linear representations of”
BackgroundMFP-Unet: A novel deep learning based approach for left ventricle segmentation in echocardiography
Moradi, S., Oghli, M. G., Alizadehasl, A., Shiri, I., Oveisi, N., Oveisi, M., Maleki, M., & D’hooge, J. (2019) · Physica Medica · doi:10.1016/j.ejmp.2019.10.001 · Cited by 173
Medical image super-resolution reconstruction algorithms based on deep learning: A survey
Qiu, D., Cheng, Y., & Wang, X. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107590 · Cited by 153
Karimi, D., Warfield, S. K., & Gholipour, A. (2021) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102078 · Cited by 181
Real-Time Tiny Part Defect Detection System in Manufacturing Using Deep Learning
Yang, J., Li, S., Wang, Z., & Yang, G. (2019) · IEEE Access · doi:10.1109/access.2019.2925561 · Cited by 145
Multi-modal learning from unpaired images: application to multi-organ segmentation in CT and MRI
Valindria, V. V., Pawlowski, N., Rajchl, M., Lavdas, I., Aboagye, E. O., Rockall, A. G., Rueckert, D., & Glocker, B. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00066 · Cited by 146
“Deep-learning based approaches such as convolutional neural networks (CNNs) have become popular in medical imaging but they require large amounts of data to achieve good results, near human-level capability [3, 22].”
BackgroundSelf-citationAdaResU-Net: Multiobjective adaptive convolutional neural network for medical image segmentation
Baldeon-Calisto, M., & Lai-Yuen, S. K. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.110 · Cited by 136
Cardiac Segmentation With Strong Anatomical Guarantees
Painchaud, N., Skandarani, Y., Judge, T., Bernard, O., Lalande, A., & Jodoin, P. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3003240 · Cited by 165
“uses an approach named anatomically constrained neural network (ACNN) [6].”
BackgroundMethodInfluentialSakshi, S., & Kukreja, V. (2022) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-022-09805-9 · Cited by 127
“…beyond critical disciplines such as medical image processing [159, 169] for tumors [95, 143], [263], cancer [30], and heart disease detection [46, 164] to mundane tasks such as pedestrian track detection [98, 139], video surveillance [262] or casual hand-writing [151, 238] or drawn structured…”
BackgroundC-CAM: Causal CAM for Weakly Supervised Semantic Segmentation on Medical Image
Chen, Z., Tian, Z., Zhu, J., Li, C., & Du, S. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01138 · Cited by 147
“Incorporating prior knowledge into image segmentation is a useful way to improve performance both for natural image [12, 27, 42] and medical image [11, 25, 31].”
BackgroundTeTrIS: Template Transformer Networks for Image Segmentation With Shape Priors
Lee, M. C. H., Petersen, K., Pawlowski, N., Glocker, B., & Schaap, M. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2905990 · Cited by 118
“More recent work has shown improved results by directly incorporating shape constraints into their learning algorithm rather than applying them as post-processing such as in [12]–[14], where priors are learnt to regularize neural network embeddings during training.”
BackgroundSelf-citationStar Shape Prior in Fully Convolutional Networks for Skin Lesion Segmentation
Mirikharaji, Z., & Hamarneh, G. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00937-3_84 · Cited by 140
“In addition, training convolutional auto-encoder networks to learn anatomical shape variations has demonstrated improvements in the robustness of FCN segmentation models [18,19].”
Fahmy, A. S., El-Rewaidy, H., Nezafat, M., Nakamori, S., & Nezafat, R. (2019) · Journal of Cardiovascular Magnetic Resonance · doi:10.1186/s12968-018-0516-1 · Cited by 122
Learning to Segment From Scribbles Using Multi-Scale Adversarial Attention Gates
Valvano, G., Leo, A., & Tsaftaris, S. A. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3069634 · Cited by 122
Liu, F., Wang, K., Liu, D., Yang, X., & Tian, J. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101873 · Cited by 121
Tanno, R., Worrall, D. E., Kaden, E., Ghosh, A., Grussu, F., Bizzi, A., Sotiropoulos, S. N., Criminisi, A., & Alexander, D. C. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2020.117366 · Cited by 150
Bottleneck feature supervised U-Net for pixel-wise liver and tumor segmentation
Li, S., Tso, K. F., & He, K. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.113131 · Cited by 110
High-level prior-based loss functions for medical image segmentation: A survey
Jurdi, R. E., Petitjean, C., Honeiné, P., Cheplygina, V., & Abdallah, F. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103248 · Cited by 118
“Another example is Oktay et al. (2018), where the authors modified the decoder layers of a U-Net-like structure in order to incorporate prior via super resolution ground truth maps.”
BackgroundZhang, Y., Chen, J., Chang, K.-T., Park, V. Y., Kim, M. J., Chan, S., Chang, P. D., Chow, D. S., Luk, A., Kwong, T. C., et al. (2019) · Academic Radiology · doi:10.1016/j.acra.2019.01.012 · Cited by 108
“…algorithms have been widely applied for classification applications, and they also provided an efficient method for organ and tissue segmentation, including the brain (14, 15), head and neck (16), chest and heart (17, 18), abdomen and pelvis (19-21), breast (22-24), and bone and joint (25).”
MethodAnatomical Priors in Convolutional Networks for Unsupervised Biomedical SegmentationPreprint
Dalca, A. V., Guttag, J. V., & Sabuncu, M. R. (2018) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 106
Wang, G., Song, T., Dong, Q., Cui, M., Huang, N., & Zhang, S. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101787 · Cited by 105
“. It should be noticed that the Hausdordistance of our results is still high. To address this problem, using Hausdordistance-based loss functions (Kervadec et al., 2019a) or high-level constraints (Oktay et al., 2018) are potential solutions. Our high-level feature extraction, pseudo DWI generation and lesion segmenta…”
MethodDeep Neural Architectures for Medical Image Semantic Segmentation: Review
Khan, M. Z., Gajendran, M. K., Lee, Y., & Khan, M. A. (2021) · IEEE Access · doi:10.1109/access.2021.3086530 · Cited by 106
“In the equation, TP is for true positive, and FP refers to false positive [120]–[124].”
BackgroundÖksüz, İ., Clough, J. R., Ruijsink, B., Anton, E. P., Bustin, A., da Cruz, G. J. L., Prieto, C., King, A. P., & Schnabel, J. A. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3008930 · Cited by 100
“Similar techniques have been proposed to fuse super-resolution and CMR segmentation [31] by using anatomical constraints through auto-encoders.”
MethodReal-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning
Smistad, E., Østvik, A., Salte, I. M., Melichova, D., Nguyen, T. M., Haugaa, K. H., Brunvand, H., Edvardsen, T., Leclerc, S., Bernard, O., et al. (2020) · IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control · doi:10.1109/tuffc.2020.2981037 · Cited by 102
“D and [5] for 3-D.”
Deep neural network for automatic characterization of lesions on 68Ga-PSMA-11 PET/CT
Zhao, Y. S., Gafita, A., Vollnberg, B., Tetteh, G., Haupt, F., Afshar‐Oromieh, A., Menze, B. H., Eiber, M. J., Rominger, A., & Shi, K. (2019) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-019-04606-y · Cited by 101
Pose-aware instance segmentation framework from cone beam CT images for tooth segmentation
Chung, M., Lee, M.-K., Hong, J., Park, S., Lee, J., Lee, J., Yang, I., Lee, J., & Shin, Y.-G. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103720 · Cited by 97
“Especially, a full 3DCNN-based approaches [27], [28], [31], [34] outperform other 2D-based methods [25] that are based on 3D convolutions.”
Medical Image Segmentation With Limited Supervision: A Review of Deep Network Models
Peng, J., & Wang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3062380 · Cited by 115
“Rather than using the compact codes produced by an autoencoder as the shape constraint in [94], Yue et al.”
BackgroundMethodInfluentialAnatomy-aided deep learning for medical image segmentation: a review
Liu, L., Wolterink, J. M., Brüne, C., & Veldhuis, R. N. J. (2021) · Physics in Medicine and Biology · doi:10.1088/1361-6560/abfbf4 · Cited by 100
Gao, Y., Huang, R., Yang, Y., Zhang, J., Shao, K., Tao, C., Chen, Y., Metaxas, D., Li, H., & Chen, M. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101831 · Cited by 92
“The high-dimensional shape usually lies in a lower-dimensional shape manifold (Wang et al., 2014; Oktay et al., 2017), where each shape would be mapped to a lowerdimensional point (vector) in the subspace.”
Automatic cardiac cine MRI segmentation and heart disease classification
Ammar, A., Bouattane, O., & Youssfi, M. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.101864 · Cited by 102
Learning deformable registration of medical images with anatomical constraints
Mansilla, L., Milone, D. H., & Ferrante, E. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.01.023 · Cited by 94
“In that sense, our contributions are four-fold: (i) we extend, for the first time, the concept of anatomically constrained neural networks [32] to the image registration problem, (ii) we perform a deeper study of the complementarity between global and local loss functions defined over segmentation…”
BackgroundMethodInfluentialSelf-citationComputational anatomy for multi-organ analysis in medical imaging: A review
Cerrolaza, J. J., Picazo, M. L., Humbert, L., Sato, Y., Rueckert, D., Ballester, M. Á. G., & Linguraru, M. G. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.04.002 · Cited by 88
Self-citationEarly Detection of Myocardial Infarction in Low-Quality Echocardiography
Degerli, A., Zabihi, M., Serkan Kiranyaz, B., Hamid, T., Mazhar, R., Hamila, R., & Gabbouj, M. (2021) · IEEE Access · doi:10.1109/access.2021.3059595 · Cited by 101
Ultrasound Medical Imaging Techniques
Avola, D., Cinque, L., Fagioli, A., Foresti, G. L., & Mecca, A. (2021) · ACM Computing Surveys · doi:10.1145/3447243 · Cited by 101
“gradient to the segmentation network, as depicted in Reference [69].”
BackgroundMethodArtificial Intelligence (AI)-Empowered Echocardiography Interpretation: A State-of-the-Art Review
Akkus, Z., Aly, Y. H., Attia, I. Z., López-Jiménez, F. A., Arruda-Olson, A. M., Pellikka, P. A., Pislaru, S. V., Kane, G. C., Friedman, P. A., & Oh, J. K. (2021) · Journal of Clinical Medicine · doi:10.3390/jcm10071391 · Cited by 95
“[32] incorporated anatomical prior knowledge in their CNN model that allows following the global anatomical properties of the underlying anatomy.”
BackgroundMethodCardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors
Qian, Y., Luo, X., Ye, Q., Xu, L., & Zhuang, X. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32245-8_62 · Cited by 93
Abdeltawab, H., Khalifa, F., Taher, F., Alghamdi, N. S., Ghazal, M. A., Beache, G. M., Mohamed, T., Keynton, R. S., & El-Baz, A. S. (2020) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2020.101717 · Cited by 91
Montero, A. M. B., Bibal, A., Huet‐Dastarac, M., Draguet, C., Valdés, G., Nguyen, D. T. D., Willems, S., Vandewinckele, L., Holmström, M., Löfman, F., et al. (2022) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac678a · Cited by 91
Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges
Isensee, F., Jaeger, P. F., Full, P. M., Ivo Wolf, A., Engelhardt, S., & Maier-Hein, K. H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-75541-0 · Cited by 86
Prior Information Guided Regularized Deep Learning for Cell Nucleus Detection
Tofighi, M., Guo, T., Vanamala, J., & Monga, V. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2895318 · Cited by 79
“imagery in [23], which leads to vastly different quantitative formulations.”
BackgroundInfluentialPost-DAE: Anatomically Plausible Segmentation via Post-Processing With Denoising Autoencoders
Larrazabal, A. J., Martínez, C. E., Glocker, B., & Ferrante, E. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3005297 · Cited by 79
“Different from other approaches like [8], [9] which incorporate the anatomical priors during the segmentation network training, our method is agnostic to the training process of the original predictor.”
BackgroundMethodSelf-citationKavur, A. E., Gezer, N. S., BARIŞ, M. M., Şahin, Y. H., Özkan, S., Baydar, B., Yuksel, U., Kılıkçıer, Ç., Olut, Ş., Akar, G. B., et al. (2019) · Diagnostic and Interventional Radiology · doi:10.5152/dir.2019.19025 · Cited by 76
Chaudhari, A. S., Sandino, C. M., Cole, E. K., Larson, D. B., Gold, G. E., Vasanawala, S. S., Lungren, M. P., Hargreaves, B. A., & Langlotz, C. P. (2020) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.27331 · Cited by 84
2D left ventricle segmentation using deep learning
Smistad, E., Østvik, A., Haugen, B. O., & Løvstakken, L. (2017) · IEEE International Ultrasonics Symposium · doi:10.1109/ultsym.2017.8092573 · Cited by 76
“[3] demonstrated the use of these neural networks on 3D left ventricle segmentation.”
BackgroundUnsupervised Deep Learning for Bayesian Brain MRI Segmentation
Dalca, A. V., Yu, E., Golland, P., Fischl, B. R., Sabuncu, M. R., & Iglesias, J. E. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32248-9_40 · Cited by 77
MC-Net: Multiple max-pooling integration module and cross multi-scale deconvolution network
You, H., Yu, L., Tian, S., et al. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107456 · Cited by 76
Explicit Topological Priors for Deep-Learning Based Image Segmentation Using Persistent Homology
Clough, J. R., Öksüz, İ., Byrne, N., Schnabel, J. A., & King, A. P. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20351-1_2 · Cited by 77
Kumar, R. R., & Priyadarshi, R. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19313-6 · Cited by 88
Zhou, C., Ye, H., Hu, J., et al. (2019) · Sensors · doi:10.3390/s19143106 · Cited by 71
BB-UNet: U-Net With Bounding Box Prior
Jurdi, R. E., Petitjean, C., Honeiné, P., & Abdallah, F. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3001502 · Cited by 67
Gaggion, N., Mansilla, L., Mosquera, C., Milone, D. H., & Ferrante, E. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3224660 · Cited by 70
“More recently, with the advent of deep fully convolutional networks [1], [22], major efforts were made to incorporate anatomical constraints into such models [23]–[25].”
BackgroundSelf-citationBtrfly Net: Vertebrae Labelling with Energy-based Adversarial Learning of Local Spine Prior
Sekuboyina, A., Rempfler, M., Kukačka, J., Tetteh, G., Valentinitsch, A., Kirschke, J., & Menze, B. H. (2018) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-030-00937-3_74 · Cited by 80
Model-Based and Data-Driven Strategies in Medical Image Computing
Rueckert, D., & Schnabel, J. A. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2943836 · Cited by 76
“Several approaches have already demonstrated that priors in the form of anatomical models can significantly improve the performance of applications such as segmentation [21], [67] or superresolution reconstruction [84].”
BackgroundSelf-citationA switched view of Retinex: Deep self-regularized low-light image enhancement
Jiang, Z., Li, H., Liu, L., et al. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.025 · Cited by 67
A distance map regularized CNN for cardiac cine MR image segmentation
Dangi, S., Linte, C. A., & Yaniv, Z. (2019) · Medical Physics · doi:10.1002/mp.13853 · Cited by 76
Variability of manual segmentation of the prostate in axial T2-weighted MRI: A multi-reader study
Becker, A. S., Chaitanya, K., Schawkat, K., Muehlematter, U. J., Hötker, A. M., Konukoğlu, E., & Donati, O. F. (2019) · European Journal of Radiology · doi:10.1016/j.ejrad.2019.108716 · Cited by 67
Li, L., Zimmer, V. A., Schnabel, J. A., & Zhuang, X. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102303 · Cited by 66
“To tackle this issue, some strategies have been utilized, such as graph-cuts/ conditional random field (CRF) regularization [25, 15], deep level set [41], deformable-model based shape refinement [2, 12, 23, 54], shape reconstruction [33, 53] and SSM [31, 20].”
MethodAutomatic segmentation with detection of local segmentation failures in cardiac MRI
Sander, J., de Vos, B. D., & Išgum, I. (2020) · Scientific Reports · doi:10.1038/s41598-020-77733-4 · Cited by 72
Anatomically-aware uncertainty for semi-supervised image segmentation
Vasudeva, S. A., Dolz, J., & Lombaert, H. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.103011 · Cited by 66
Guo, F., NG, M. M., Goubran, M., Petersen, S. E., Piechnik, S. K., Neubauer, S., & Wright, G. A. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101636 · Cited by 65
Echocardiographic image segmentation using deep Res-U network
Ali, Y., Janabi‐Sharifi, F., & Beheshti, S. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102248 · Cited by 64
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
