The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory and Practice
Open accessAbstract
The Dice score and Jaccard index are commonly used metrics for the evaluation of segmentation tasks in medical imaging. Convolutional neural networks trained for image segmentation tasks are usually optimized for (weighted) cross-entropy. This introduces an adverse discrepancy between the learning optimization objective (the loss) and the end target metric. Recent works in computer vision have proposed soft surrogates to alleviate this discrepancy and directly optimize the desired metric, either through relaxations (soft-Dice, soft-Jaccard) or submodular optimization (Lovasz-softmax). The aim of this study is two-fold. First, we investigate the theoretical differences in a risk minimization framework and question the existence of a weighted cross-entropy loss with weights theoretically optimized to surrogate Dice or Jaccard. Second, we empirically investigate the behavior of the aforementioned loss functions w.r.t. evaluation with Dice score and Jaccard index on five medical segmentation tasks. Through the application of relative approximation bounds, we show that all surrogates are equivalent up to a multiplicative factor, and that no optimal weighting of cross-entropy exists to approximate Dice or Jaccard measures. We validate these findings empirically and show that, while it is important to opt for one of the target metric surrogates rather than a cross-entropy-based loss, the choice of the surrogate does not make a statistical difference on a wide range of medical segmentation tasks.
Overview
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
Verification
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.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
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
The Nature of Statistical Learning Theory
Vapnik, V. N. (1995) · doi:10.1007/978-1-4757-2440-0 · Cited by 39,138
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
Kamnitsas, K., Ledig, C., Newcombe, V. F. J., Simpson, J. P., Kane, A. D., Menon, D. K., Rueckert, D., & Glocker, B. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.10.004 · Cited by 3,498 · cited 2×
“Nevertheless, training with the pixel-wise cross-entropy loss, or its weighted variant, remains highly popular, even when the evaluation is performed using the Dice score or Jaccard index [11,6].”
BackgroundMethodEncyclopedia of Machine Learning
(2010) · Springer eBooks · doi:10.1007/978-0-387-30164-8 · Cited by 3,465
Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations
Sudre, C. H., Li, W., Vercauteren, T., Ourselin, S., & Jorge Cardoso, M. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-67558-9_28 · Cited by 2,829
Morphometric analysis of white matter lesions in MR images: method and validation
Zijdenbos, A. P., Dawant, B. M., Margolin, R. A., & Palmer, A. C. (1994) · IEEE Transactions on Medical Imaging · doi:10.1109/42.363096 · Cited by 1,265
Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks
Salehi, S. S. M., Erdogmus, D., & Gholipour, A. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-67389-9_44 · Cited by 1,086
Convexity, Classification, and Risk Bounds
Bartlett, P. L., Jordan, M. I., & McAuliffe, J. D. (2006) · Journal of the American Statistical Association · doi:10.1198/016214505000000907 · Cited by 1,037
Cited by
Eelbode, T., Bertels, J., Berman, M., Vandermeulen, D., Maes, F., Bisschops, R., & Blaschko, M. B. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3002417 · Cited by 420
Self-citationAlzubaidi, M., Agus, M., Shah, U., Makhlouf, M., Alyafei, K., & Househ, M. (2022) · Diagnostics · doi:10.3390/diagnostics12092229 · Cited by 35
El Ghazouali, S., Mhirit, Y., Oukhrid, A., Michelucci, U., & Nouira, H. (2024) · Sensors · doi:10.3390/s24092889 · Cited by 24
Metadata
- Authors
- Bertels, J., Eelbode, T., Berman, M., Vandermeulen, D., Maes, F., Bisschops, R., & Blaschko, M. B.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2019
- Pages
- 92-100
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2979751829
- Cited by
- 283
- References
- 16
- FWCI
- 7.25
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory and Practice. https://app.cochat.ai/papers/10.1007/978-3-030-32245-8_11
- The paper
- Bertels, J., Eelbode, T., Berman, M., Vandermeulen, D., Maes, F., Bisschops, R., & Blaschko, M. B. (2019). Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory and Practice. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-030-32245-8_11
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.