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
44 Own interpretation · 22 Not checked yet · 21 Own result · 8 No basis given · 2 Sources not found · 1 Own method
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;”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“The applicability of our approach is shown on multi-modal cardiac datasets and public benchmarks.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None 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.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A 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.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 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
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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 |”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. 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).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In particular, Hausdorff distances were reduced significantly”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- 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 ).”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A 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% .”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. 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.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- 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.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- 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.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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.”
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“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. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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.”
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It 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.
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
In the paper
“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. -
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“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.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says 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
“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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It 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. -
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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.”
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“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.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
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.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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. -
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“The proposed regulariser model can be seen as an application-specific training objective.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- 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.”
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“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. -
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“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.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In 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.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ D. T-L Network Model and SR-ACNN · p. 5
“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.”
§ D. T-L Network Model and SR-ACNN · p. 5
“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
Cited by
Sorted by citations
Items 701–758 of 758
Pal, J. B., Welling, S., Saini, H., & Awate, S. P. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00907
“A class of DNN methods [11, 14, 20] use anatomical information through loss terms designed on seg-mentations in the domain of interest, but they are inappli-cable to our problem setting dealing with OOD data that is unavailable during training.”
SSL-DA: Semi-and Self-Supervised Learning with Dual Attention for Echocardiogram Segmentation
Lv, L., Han, X., Sun, Z., Li, Z., Wang, X., Jiang, T., Liu, Y., Li, T., Xu, J., You, L., et al. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01532-4 · Cited by 1
“In addition, Oktay et al. [23] developed an anatomically constrained neural network model for three-dimensional echocardiographic segmentation, achieving state-of-the-art performance.”
Rajalakshmi, K., & Rajan, S. P. (2025) · Measurement Science Review · doi:10.2478/msr-2025-0012
Zhang, G., Zhang, L., Fu, X., Wang, Y., Zhou, S., Wei, J. W., & Zhao, D. (2025) · Pattern Analysis and Applications · doi:10.1007/s10044-025-01509-7
“Clinically, echocardiography [ 4 ] is frequently employed to assess the LV function [5 ], such as the ejection fraction, due to its non-invasive and low-cost.”
Multi-Scale Convolution-Aided Transformer-Based Medical Image Super-Resolution
Zhou, Z. (2025) · Applied and Computational Engineering · doi:10.54254/2755-2721/2025.kl24798
Anwaar, W., Manh, V., Xue, W., & Ni, D. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106413 · Cited by 1
Deep Learning-Based Temperature Distribution Estimation for Microwave Hyperthermia Applications
Gurbet, Y. S., Onal, H., & Doğu, S. (2025) · International Symposium on Innovative Approaches in Smart Technologies (ISAS) · doi:10.1109/isas66241.2025.11101969
“In particular, convolutional neural networks (CNNs) and encoder-decoder architectures like U-Net have enormous potential in medical imaging [8], [9] and, therefore, for temperature monitoring.”
Hu, M., Gao, Y., Li, Y., Qiu, R. L. J., Chang, C., Shah, K. D., Kapoor, P., Bradshaw, B., Shao, Y., Roper, J. R., et al. (2025) · Medical Physics · doi:10.1002/mp.18067 · Cited by 1
“58 Second, integrating advanced post-processing techniques,including topology-preserving surface refinements or deformable model-based corrections, 59 can help enforce anatomical consistency in the final segmentation outputs without modifying the core network architecture.”
Multi-Task Consistency Segmentation Network with Deep Shape Prior for Cartilage Segmentation
Zhang, P., Yuan, Y., Cheng, Y., et al. (2025) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2025edp7059
Precise Top-Layer Fabric Segmentation for Fabric Destacking with Edge- and Shape-Aware Deep Networks
Dong, W., Bhattacharya, D., Kobayashi, A., et al. (2025) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma65362.2025.11120697
“Some methods employ adversarial training or shape priors to encourage plausible segmentation boundaries [15], [16], while others utilize distance transforms or shape-aware losses as auxiliary supervision to enforce geometric regularity [17].”
Sar, A., Bhattacharjee, S., Choudhury, T., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6303-3_27
Wang, J., Qin, S., Qu, R., et al. (2025) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ae023a
Pratap, A., Sardana, N., Wu, T., et al. (2025) · NDT & E International · doi:10.1016/j.ndteint.2025.103569
Distance self-adaptive fuzzy c-means and its application to image segmentation
Chen, S., Feng, C., Li, D., et al. (2025) · Signal Processing Image Communication · doi:10.1016/j.image.2025.117424
LA-BPNet: Location-aware brachial plexus C 6 & C 7 nerves segmentation network in ultrasound images
Zhang, H., Shi, D., Zhou, G., Chen, X., Lv, F., & Zhou, P. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109120
Addressing Annotation Scarcity in Cardiac Vessel Segmentation Using Edge-Conditioned Cgan
Kulkarni, R., Desai, S. D., & Baligar, V. P. (2025) · doi:10.1109/icicnct66124.2025.11232624
Progressive Distillation Attention for Robust Left Ventricular Ejection Fraction Estimation
Basak, S., Hussain, N., & Bhattacharya, U. (2025) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz67716.2025.11281817
“U-Net [4] and its extensions (e.g., U-Net++ [11], ACNN [12]) became widely adopted for segmentation, including LV boundary detection.”
Cut it here: Image segmentation for MRI
Chen, C. (., & Li, Z. (2025) · Advances in magnetic resonance technology and applications · doi:10.1016/b978-0-443-14109-6.00012-2
Autoencoders in cardiology: Opportunities and challenges for clinical integration
Branda, F., Ciccozzi, M., Scarpa, F., Boccuto, F., Lomoio, U., Veltri, P., & Guzzi, P. H. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45242-0.00005-0
An optimal diagnosis model for pancreatic cancer prediction based on deep learning method
Venkatesh, C., Al‐Wesabi, F. N., Alshahrani, H. M., Yahya, A. E., Kiran, A., Chinna Babu, J., Sivayamini, L., & Alam, A. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3541 · Cited by 1
Augmentation of Small Ultrasound Databases: A Practical Approach
Kasamrach, O., Luangwilai, T., & Makhanov, S. S. (2026) · Mathematics · doi:10.3390/math14040646
Wu, J., Wang, Y., Liu, Y., Ren, Y., Wang, M., & Cai, W. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109884 · Cited by 1
Optimized CNN-U-Net Framework for MRI-Based Detection and Segmentation of Chronic Kidney Disease
Vishalakshi, M., & Kumar, P. R. (2025) · International Conference on Artificial Intelligence for Computing, Astronomy and Renewable Energy (AICARE) · doi:10.1109/aicare66005.2025.11402696
Cross-Modality Whole-Heart MRI Reconstruction with Deep Motion Correction and Super-Resolution
Dong, J., Ke, W., Ding, W., et al. (2026) · Sensors · doi:10.3390/s26051565
Li, Y. (2018) · theses.fr (ABES) · doi:10.70675/6a3b3769zbc79z4869z96e3z720d9cae64e9 · Cited by 1
Registration of multimodal images for characterization of cardiomyopathies
Atehortúa, A. (2020) · theses.fr (ABES) · doi:10.70675/c2c3af12za048z4255za5fdzf98ac7f287d5
A priori et apprentissage profond pour la segmentation en imagerie cérébrale
Ganaye, P.-A. (2019) · theses.fr (ABES) · doi:10.70675/57ede0c2zd4a6z4c95zbb4azd41373a8b76f · Cited by 2
Probabilistic models for image processing : applications in vascular surgery
Gangloff, H. (2020) · theses.fr (ABES) · doi:10.70675/db40a7e4z91b2z4e00zbf59z6f97ce7137e3
Deep learning architectures for automatic detection of viable myocardiac segments
Brahim, K. (2021) · theses.fr (ABES) · doi:10.70675/f5afa1e1zfe37z4f18z9794z2622e6cb27b1
Restoration of structural MRI images for the preclinical study of markers of cerebral aging
Bazzi, F. (2021) · theses.fr (ABES) · doi:10.70675/3390be2fzafd0z4eb6z870bz4603eaad6522
Integration and non-intrusive human clinic machine learning for kidney assessment
Do, Q. H. (2022) · theses.fr (ABES) · doi:10.70675/9cd78602z555bz4e01zb479zdb4b46f80000
Regularized deep learning models for multi-anatomy segmentation in pediatric imaging
Boutillon, A. (2022) · theses.fr (ABES) · doi:10.70675/9b91c712z37e6z425dz9844zd2bb83d59f6b
Arega, T. W. (2023) · theses.fr (ABES) · doi:10.70675/6f691b31z766dz4a4azb504za7b14d4cf213
Ribeiro, M. A. O., Gutierrez, M. A., & Nunes, F. L. S. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-01940-0
A causality-guided lightweight model for 3D multi-modal brain tumor segmentation
Fan, Y., Wang, C., Zhang, X., Yue, Z., Chen, J., & Zhou, Q. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110392
Vanderleest, T. E., & Arboleda‐Velásquez, J. F. (2026) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2026.1788958
“…direction that could be beneficial are the use of convolutional neural networks that incorporate prior knowledge or anatomical constraints (Liu et al., 2023; Oktay et al., 2018), which could potentially help produce a more continuous basement membrane and avoid small fragments of nucleus or lumen.”
Abdelrauof, D., Ibrahim, S., Rashwan, M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-19865-5_16
Physics-Informed Neural Networks with Embedded Shape Priors for Ultrasound Image Segmentation
Sel, K., & Jafari, R. (2026) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi61048.2026.11515773
“However, these approaches typically establish SSMs from the same ground truth masks they are being trained on [16], [17], [18].”
Škardová, K., Galabov, R., Fricková, K., et al. (2026) · Heliyon · doi:10.1016/j.heliyon.2026.e45034
Disentangling structure from modality: An attention-based framework for CBCT-to-CT synthesis
Guo, S., Mao, S., Shi, T., et al. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110832
OncoSeg2D: A deep framework for semantic segmentation of lung cancer in 2D CT scans
Yu, L., Dong, X., 法凯, & Li, Y. (2026) · PLoS ONE · doi:10.1371/journal.pone.0348719
Zhang, Y., Cheng, H., Zhang, J., Shi, G., Liu, X. Y., Shi, L. Y., Chen, J., & Wu, Y. T. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110939 · Cited by 1
Hong, L., Xu, J., Zhuang, S., Wang, J., Qiu, S., Guo, J., & Zhuang, Z. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00926-w
“Specifically, we introduce several comparative cardiac image segmentation methods— including ACNN (Oktay et al. 2018), U-Net (Ronneberger et al. 2015), PLAnet (Liu et al. 2021), and LUnet (Leclerc et al. 2020)—for benchmarking.”
Mmrsg-unet: integrating multi-scale Mamba and reverse semantic gating for medical image segmentation
Yang, C., Zhang, T., Ge, S., Cao, Y., & Lu, D. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02439-y
“Chuanhao Yang 1 · Tianyu Zhang 1 · Shijia Ge 1 · Yanfeng Cao 1 · Dunke Lu 1 propelled this field [ 3], the precise delineation of anatomical targets with complex topologies (e.g., spatially dispersed organs) persists as a challenge due to low contrast and ambiguous boundaries [ 4 ].”
Integrating physics guidance into deep learning for cine cardiovascular segmentation
Tran-Nguyen, M. A., Lương, Q. K., Kha, M. B., et al. (2026) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2026.102798
Gao, S., Xu, Q., Yin, Y., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-3531-5_30
Gazda, M., Drotár, P., Gazda, J., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7305295
Pan, Z., Song, N., Cheng, S., Pang, W., Liao, H., Wang, Y., & Gu, B. (2026) · Light Science & Applications · doi:10.1038/s41377-026-02464-6
AI in medical imaging for developing countries: Challenges and opportunities
Naaz, S., Saeed, M., Khan, R. S., et al. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44915-4.00015-0
Gong, J., Liu, J., & Wang, Q. (2026) · Electronics · doi:10.3390/electronics15184227
LAD: Learnable Anisotropic Deformation for 3D Medical Image Analysis
Liu, C., Sang, H., Huang, X., Wu, Y., Wang, C., Wu, W., Zeng, G., Tian, J., & Wang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38186-6_18
MAPI: A morphology-adaptive prior injection module for gear surface defect segmentation
Zhang, Y., Zhou, S., Zhang, L., et al. (2026) · Measurement · doi:10.1016/j.measurement.2026.123456
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
