Anatomically plausible segmentations: Explicitly preserving topology through prior deformations
Open accessAbstract
Since the rise of deep learning, new medical segmentation methods have rapidly been proposed with extremely promising results, often reporting marginal improvements on the previous state-of-the-art (SOTA) method. However, on visual inspection errors are often revealed, such as topological mistakes (e.g. holes or folds), that are not detected using traditional evaluation metrics. Incorrect topology can often lead to errors in clinically required downstream image processing tasks. Therefore, there is a need for new methods to focus on ensuring segmentations are topologically correct. In this work, we present TEDS-Net: a segmentation network that preserves anatomical topology whilst maintaining segmentation performance that is competitive with SOTA baselines. Further, we show how current SOTA segmentation methods can introduce problematic topological errors. TEDS-Net achieves anatomically plausible segmentation by using learnt topology-preserving fields to deform a prior. Traditionally, topology-preserving fields are described in the continuous domain and begin to break down when working in the discrete domain. Here, we introduce additional modifications that more strictly enforce topology preservation. We illustrate our method on an open-source medical heart dataset, performing both single and multi-structure segmentation, and show that the generated fields contain no folding voxels, which corresponds to full topology preservation on individual structures whilst vastly outperforming the other baselines on overall scene topology. The code is available at: https://github.com/mwyburd/TEDS-Net.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
All model implementations and predictions follow the descriptions provided in [6].
“All model implementations and predictions follow the descriptions provided in [6].”
From rNCA: Self-Repairing Segmentation Masks (2025) · cites this paper as [6]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
U-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 · see citing works
A 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 · see citing works
A fast diffeomorphic image registration algorithm
Ashburner, J. (2007) · NeuroImage · doi:10.1016/j.neuroimage.2007.07.007 · Cited by 8,122 · see citing works
scikit-image: image processing in Python
(2014) · doi:10.7717/peerj.453 · Cited by 6,794 · see citing works
Swin-Unet: Unet-like pure transformer for medical image segmentation
Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., & Wang, M. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-25066-8_9 · Cited by 5,640 · see citing works
Jaderberg, M., Simonyan, K., Zisserman, A., & Kavukcuoglu, K. (2015) · arXiv · doi:10.48550/arxiv.1506.02025 · Cited by 5,137 · see citing works
Instance Normalization: The Missing Ingredient for Fast StylizationPreprint
Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2016) · arXiv.org · doi:10.48550/arxiv.1607.08022 · Cited by 4,239 · see citing works
Bernard, O., Lalande, A., Zotti, C., Cervenansky, F., Yang, X., Heng, P.-A., Cetin, I., Lekadir, K., Camara, O., Gonzalez Ballester, M. A., et al. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2837502 · Cited by 2,431 · see citing works
Nineteen Dubious Ways to Compute the Exponential of a Matrix, Twenty-Five Years Later
Moler, C., & Van Loan, C. (2003) · SIAM Review · doi:10.1137/s00361445024180 · Cited by 2,357 · see citing works
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
Balakrishnan, G., Zhao, A., Sabuncu, M. R., Guttag, J. V., & Dalca, A. V. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2897538 · Cited by 2,199 · see citing works
Deformable models in medical image analysis: a survey
McInerney, T., & Terzopoulos, D. (1996) · Medical Image Analysis · doi:10.1016/s1361-8415(96)80007-7 · Cited by 1,921 · see citing works
Oktay, O., Ferrante, E., Kamnitsas, K., Heinrich, M., Bai, W., Caballero, J., Cook, S. A., de Marvao, A., Dawes, T., O'Regan, D. P., et al. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2743464 · Cited by 751 · cited 2× · see citing works
“Higher-level shape information of desired structures has also been incorporated into CNNs using additional networks, tasked with learning the topology (Oktay et al., 2017; Mosinska et al., 2018; Painchaud et al., 2020; Cao et al., 2020).”
associated_data_Investigating the Effectiveness of clDice Loss for Road Crack SegmentationPreprint
Pereira, V. (2025) · arXiv (Cornell University) · doi:10.5281/zenodo.15696262 · Cited by 549 · see citing works
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
Dalca, A. V., Balakrishnan, G., Guttag, J., & Sabuncu, M. R. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.07.006 · Cited by 467 · see citing works
Il calcolo delle assicurazioni su gruppi di teste
Bonferroni, C., & Bonferroni, C. (1935) · Medical Entomology and Zoology · Cited by 425 · see citing works
Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
Dalca, A. V., Balakrishnan, G., Guttag, J. V., & Sabuncu, M. R. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00928-1_82 · Cited by 396 · see citing works
Performing label-fusion-based segmentation using multiple automatically generated templates
Chakravarty, M. M., Steadman, P. E., van Eede, M. C., Calcott, R. D., Gu, V. Y., Shaw, P., Raznahan, A., Collins, D. L., & Lerch, J. P. (2012) · Human Brain Mapping · doi:10.1002/hbm.22092 · Cited by 339 · see citing works
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 · see citing works
Beyond the Pixel-Wise Loss for Topology-Aware Delineation
Mosinska, A., Márquez-Neila, P., Koziński, M., & Fua, P. (2018) · 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/cvpr.2018.00331 · Cited by 280 · see citing works
Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networks
Mok, T. C. W., & Chung, A. C. S. (2020) · 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/cvpr42600.2020.00470 · Cited by 278 · see citing works
Non‐parametric combination and related permutation tests for neuroimaging
Winkler, A. M., Webster, M., Brooks, J. C. W., Tracey, I., Smith, S. M., & Nichols, T. E. (2016) · Human Brain Mapping · doi:10.1002/hbm.23115 · Cited by 237 · see citing works
Topology-Preserving Deep Image SegmentationPreprint
Hu, X., Li, F., Samaras, D., & Chen, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05404 · Cited by 164 · see citing works
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 160 · see citing works
TeTrIS: 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 · see citing works
Topology preserving deformable image matching using constrained hierarchical parametric models
Musse, O., Heitz, F., & Armspach, J. (2001) · IEEE Transactions on Image Processing · doi:10.1109/83.931102 · Cited by 95 · see citing works
Myocardial strain: a clinical review
Brady, B., King, G., Murphy, R. T., & Walsh, D. (2022) · Irish Journal of Medical Science (1971 -) · doi:10.1007/s11845-022-03210-8 · Cited by 90 · see citing works
Wang, S., Cao, S., Wei, D., Wang, R., Ma, K., Wang, L., Meng, D., & Zheng, Y. (2020) · 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/cvpr42600.2020.00918 · Cited by 83 · see citing works
Huang, W., Yang, H., Liu, X., Li, C., Zhang, I., Wang, R., Zheng, H., & Wang, S. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3059282 · Cited by 81 · see citing works
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 · see citing works
Estimating Topology Preserving and Smooth Displacement Fields
Karaçalı, B., & Davatzikos, C. A. (2004) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2004.827963 · Cited by 74 · see citing works
Johnson, C., Kuyt, K., Oxborough, D., & Stout, M. (2019) · Echo Research and Practice · doi:10.1530/erp-19-0020 · Cited by 58 · see citing works
A Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR
Byrne, N., Clough, J. R., Valverde, I., Montana, G., & King, A. P. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3203309 · Cited by 50 · see citing works
A Log-Euclidean Polyaffine Framework for Locally Rigid or Affine Registration
Arsigny, V., Commowick, O., Pennec, X., & Ayache, N. (2006) · Lecture notes in computer science · doi:10.1007/11784012_15 · Cited by 47 · see citing works
Ganguly, D., Chakraborty, S., Balitanas, M. O., & Kim, T.-H. (2010) · Communications in computer and information science · doi:10.1007/978-3-642-16444-6_63 · Cited by 46 · see citing works
NeurReg: Neural Registration and Its Application to Image Segmentation
Zhu, W., Myronenko, A., Xu, Z., Li, W., Roth, H. R., Huang, Y., Milletarì, F., & Xu, D. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093506 · Cited by 31 · see citing works
Deep Small Bowel Segmentation with Cylindrical Topological Constraints
Shin, S. Y., Lee, S., Elton, D., Gulley, J. L., & Summers, R. M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59719-1_21 · Cited by 31 · see citing works
Byrne, N., Clough, J. R., Montana, G., & King, A. P. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68107-4_1 · Cited by 29 · see citing works
Zeng, Q., Karimi, D., Pang, E., Mohammed, S. K., Schneider, C., Honarvar, M., & Salcudean, S. E. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32245-8_28 · Cited by 28 · see citing works
Segmentation of the Cortical Plate in Fetal Brain MRI with a Topological Loss
de Dumast, P., Kebiri, H., Atat, C., Dunet, V., Koob, M., & Cuadra, M. B. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87735-4_19 · Cited by 25 · see citing works
Wyburd, M. K., Dinsdale, N. K., Namburete, A. I. L., & Jenkinson, M. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-87193-2_24 · Cited by 22 · see citing works
Self-citationScale Factor Point Spread Function Matching: Beyond Aliasing in Image Resampling
Cardoso, M. J., Marc Modat, A., Vercauteren, T. K., & Sebastien Ourselin, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24571-3_81 · Cited by 16 · see citing works
OASIS: One-pass aligned atlas set for medical image segmentation
Zhu, Q., Wang, Y., Du, B., & Yan, P. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.114 · Cited by 13 · see citing works
A Multi-task Framework for Topology-guaranteed Retinal Layer Segmentation in OCT Images
Cao, J., Liu, X., Zhang, Y., & Wang, M. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283408 · Cited by 11 · see citing works
Samuel, T. J., Oneglia, A. P., Cipher, D. J., Ezekowitz, J. A., Dyck, J. R. B., Anderson, T. J., Howlett, J. G., Paterson, D. I., Thompson, R. B., & Nelson, M. D. (2023) · Journal of Cardiovascular Magnetic Resonance · doi:10.1186/s12968-023-00969-2 · Cited by 8 · see citing works
Probabilistic Atlases to Enforce Topological Constraints
Wickramasinghe, U., Knott, G. W., & Fua, P. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32239-7_25 · Cited by 5 · see citing works
Corona‐Villalobos, C. P., Sorensen, L. L., Chu, L. C. H., Abraham, T. P., Kamel, I. R., & Zimmerman, S. L. (2013) · Journal of Cardiovascular Magnetic Resonance · doi:10.1186/1532-429x-15-s1-p169 · Cited by 5 · see citing works
Sinclair, M. D., Schuh, A., Hahn, K., Petersen, K., Bai, Y., Batten, J., Schaap, M., & Glocker, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.10533 · Cited by 3 · see citing works
Zhang, H., & Lui, L. M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.13331 · Cited by 2 · see citing works
Flagged first, then by citations
1 of the 50 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- Dinsdale NK Jenkinson M Namburete AI Spatial warping network for 3d segmentation of the hippocampus in mr images MICCAI Springer 2019 284 291
- Shit S Paetzold JC Sekuboyina A Ezhov I Unger A Zhylka A Pluim JP Bauer U Menze BH Cldice-a novel topology-preserving loss function for tubular structure segmentation Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021 16560 16569
Cited by
Sorted by citations
Anatomically accurate cardiac segmentation using Dense Associative Networks
Ullah, Z., & Kim, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112742 · Cited by 15 · see citing works
Zhang, G., Chen, K., Liu, Y., Li, S., & Liu, Z. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112838 · Cited by 1 · see citing works
Wyburd, M. K., Kennedy, S., Fernandes, M., Dinsdale, N. K., Hesse, L. S., Gunier, R. B., Ismail, L. C., Ohuma, E. O., Gravett, M. G., Purwar, M., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-69657-w · Cited by 2 · see citing works
Self-citationStructured prompt-guided knowledge injection for medical image segmentation
Zhao, Y., He, K., Zhang, Y., Zhou, Y., Zhou, T., & Liang, D. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113852 · Cited by 1 · see citing works
rNCA: Self-Repairing Segmentation Masks
Silbernagel, M., Alonso, A., Petersen, J., Ibragimov, B., de Bruijne, M., & Wyburd, M. K. (2025) · arXiv · doi:10.48550/arxiv.2512.13397
“This results in fragmented masks with gaps degrading their reliability for quantitative downstream image processing tasks, critical for many clinical applications [6].”
InfluentialSelf-citationSu, M., Zhang, Y., Kaaniche, M., Wang, C., & Zhao, M. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356397
Topology-Guaranteed Image Segmentation: Enforcing Connectivity, Genus, and Width Constraints
Li, W., Tai, X., & Liu, J. (2026) · SIAM Journal on Imaging Sciences · doi:10.1137/25m1765870
Luan, H., Lyu, Y., Dong, J., & Pan, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-16271-7_3
Qi, Y., Yang, Y., Peng, W., Miao, S., Hu, Y., & Yang, G. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104179
He, Y., Pan, A., Li, Y., Wang, J., Qu, W., Zhu, W., & Ji, W. (2026) · Sensors · doi:10.3390/s26154769
Physics-guided topology-aware safeguarded unfolding for low-sampling computational ghost imaging
Cao, M., Duan, W., Li, B., & Sun, J. (2026) · Optics Express · doi:10.1364/oe.616758
HybPromptSeg: Spatial-frequency hybrid prompting for unified multi-task medical image segmentation
Niu, Y., Pei, S., Li, Y., Zhou, H., & Guoyan Zheng, A. (2026) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2026.102837
- Authors
- Wyburd, M. K., Dinsdale, N. K., Jenkinson, M., & Namburete, A. I. L.
- Affiliations
- University of Oxford (GB)
- Wellcome Centre for Integrative Neuroimaging (GB)
- Corresponding author
- Wyburd, Madeleine K.
- Venue
- Medical Image Analysis
- Publisher
- Elsevier BV
- Published
- 2024-10
- Volume
- 97
- Pages
- 103222
- ISSN
- 1361-8415 (ISSN-L)
- PMC
- PMC7618872
- OpenAlex
- W4399708533
- Cited by
- 11
- References
- 50
- Citations by year
- 2026: 8 · 2025: 3
- FWCI
- 1.54
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Medical Image Analysis (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Institute for Health and Care Research
- Engineering and Physical Sciences Research Council
- Bill and Melinda Gates Foundation
- Academy of Medical Sciences
- NIHR Oxford Biomedical Research Centre
- Royal Academy of Engineering
- NIHR Imperial Biomedical Research Centre
- Medical Research Council (EP/L016052/1)
- Wellcome Trust (215573/Z/19/Z, 203139/Z/16/Z)
- 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
- Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
- Keywords
- medical image segmentation, topology preservation, cardiac image segmentation, segmentation errors
- MeSH terms
- Deep Learning, Algorithms, Humans, Image Processing, Computer-Assisted, Magnetic Resonance Imaging
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
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
