The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.
Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation
Open accessAbstract
Fully convolutional neural networks (FCNs), and in particular U-Nets, have achieved state-of-the-art results in semantic segmentation for numerous medical imaging applications. Moreover, batch normalization and Dice loss have been used successfully to stabilize and accelerate training. However, these networks are poorly calibrated i.e. they tend to produce overconfident predictions for both correct and erroneous classifications, making them unreliable and hard to interpret. In this paper, we study predictive uncertainty estimation in FCNs for medical image segmentation. We make the following contributions: 1) We systematically compare cross-entropy loss with Dice loss in terms of segmentation quality and uncertainty estimation of FCNs; 2) We propose model ensembling for confidence calibration of the FCNs trained with batch normalization and Dice loss; 3) We assess the ability of calibrated FCNs to predict segmentation quality of structures and detect out-of-distribution test examples. We conduct extensive experiments across three medical image segmentation applications of the brain, the heart, and the prostate to evaluate our contributions. The results of this study offer considerable insight into the predictive uncertainty estimation and out-of-distribution detection in medical image segmentation and provide practical recipes for confidence calibration. Moreover, we consistently demonstrate that model ensembling improves confidence calibration.
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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Natekar al. [694] | et | 2020 | DenseUnet, ResUnet, SimUnet | Segmentation | Brain tumor | 1 | TTD (test time dropout) for VI”
From A review of uncertainty quantification in deep learning: Techniques, applications and challenges (2021) · cites this paper as [694]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Increasingly, disagreement among these CV models is reused as a proxy for epistemic uncertainty in downstream applications such as quality control and human-in-the-loop review [11,18,15].”
From Lost in the Folds: When Cross-Validation Is Not a Deep Ensemble for Uncertainty Estimation (2026) · cites this paper as [18]
Experimental — accuracy not yet measured
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Fully 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
(2014) · Cited by 33,419
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
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
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Milletari, F., Navab, N., & Ahmadi, S.-A. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.79 · Cited by 11,931
Fully convolutional networks for semantic segmentation
Shelhamer, E., Long, J., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2572683 · Cited by 11,898
Ensemble methods in machine learning
Dietterich, T. G. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-45014-9_1 · Cited by 8,408
Flagged first, then by citations
Research works printed but not linked: 10
- 2018, Tgs Salt Identification Challenge
- 2018, Grand Challenge on MR Brain Segmentation at MICCAI 2018
- 10.5555/3045118.3045167 · DOI
- 10.21236/ADA459827 · DOI
- 10.5555/3045390.3045502 · DOI
- Liao, 2019, On modelling label uncertainty in deep neural networks: Automatic estimation of intra-observer variability in 2D echocardiography quality assessment, arXiv:1911.00674 · arXiv
- 10.1109/CVPR.2018.00464 · DOI
- 10.1201/9781420002690 · DOI
- 10.5555/3295222.3295309 · DOI
- 10.1007/978-3-030-32251-9_73 · DOI
Cited by
Sorted by citations
Items 401–428 of 428
Fuzzy Adaptive Loss Based on Quality and Region Weighting for Medical Image Segmentation
Chung, S.-L., Huang, P.-C., Lee, Y.-T., Li, Y.-H., Chen, W.-C., Hsu, Y.-S., & Chung, I. (2026) · International Journal of Fuzzy Systems · doi:10.1007/s40815-026-02334-8
Fahim, T. A., Alam, F. B., Ahmed, M. S., & Jia, Y. (2026) · Computers · doi:10.3390/computers15090630
A Review of Lightweight Algorithm‐Driven Intelligent Sensing Technologies for Extreme Environments
Wang, Y., Li, S., Xiao, Z., Tian, L., Yang, C., Song, J., Zheng, L., Zhang, L., & Lawrie, C. H. (2026) · Journal of Sensors · doi:10.1155/js/3919320
Cross-cohort reliability and failure attribution in AI-based breast DCE-MRI tumor segmentation
Krikun, E., & Alkhateeb, A. (2026) · European Journal of Radiology Artificial Intelligence · doi:10.1016/j.ejrai.2026.100132
Gourine, S. A., Soufi, M., Otake, Y., Masaki, Y., Murakami, Y., Nagatani, Y., Watanabe, Y., Uemura, K., Kono, K., Takao, M., et al. (2026) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-026-03785-y
Uncertainty-Guided Conservative Propagation for Coronary Artery Segmentation
Huang, H., Xu, Z., Esposito, M., & Chen, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38085-2_56
Uncertainty-Aware Bayesian Prompt Adaptation for Robust Cross-Modality Medical Segmentation
Hong, S., Kim, J.-Y., & Lee, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38079-1_52
Park, Y., Jeong, J. G., & Yang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38079-1_29
Confidence-Aware Supervision for Robust Multi-task Embryo Grading
Park, B., Jo, Y., Kang, J., Heo, J., & Kim, H. M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38079-1_11
Missing Modality-Aware Calibration for Trustworthy Brain Tumor Segmentation
Lee, S., Kim, H., Hong, S., Han, D., & Yi, M. Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38079-1_39
Medical Image Segmentation via Morphological Conformal Prediction and Fractional Iterations
Mukama, B. C., Messoudi, S., Rousseau, S., & Destercke, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39518-4_36
An Inspectable Vision-Language and Convolutional Ensemble for Facial Pigmented Lesion Diagnosis
Zafeiriou, A., Kallipolitis, A., Τζιομάκα, Μ., & Maglogiannis, I. G. (2026) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-032-39674-7_20
Memon, S., Bhatti, S., Jawaid, M., & Usman, G. (2026) · Journal of Imaging · doi:10.3390/jimaging12100475
Harnessing Uncertainty in Code Language Models: Lessons from Vulnerability Detection
Li, H., Cheng, X. Y., Wang, X., Guo, Z., & Wang, H. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3837465
Tsai, C. M., & Lee, J.-D. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111588
Vallu, S., Gupta, K., Singh, C., & Tensingh, S. (2026) · International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC) · doi:10.1109/assic70037.2026.11717227
Intrinsic dimension for evaluating and analyzing neural networks for medical image segmentation
Li, W., Li, Z., Xu, J., Zhou, S., Guo, Y., Tao, Q., & Wang, Y. (2026) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2026.109680
Uncertainty-aware auto-segmentation enables adaptive radiotherapy planning of liver metastases
Langner, D., Gani, C., Boeke, S., Niyazi, M., Eickhoff, C., Küstner, T., & Thorwarth, D. (2026) · Radiotherapy and Oncology · doi:10.1016/j.radonc.2026.111816
Fu, K., Zhang, Y., Fan, W., Chen, Z., Hu, Q., Chen, K., & Wen, P. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02701-3
A review of Kolmogorov–Arnold networks for medical image analysis
Bai, J., Cai, Z., 楊榮順, Lekadir, K., & Li, S. (2026) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2026.102827
van Aalst, J. E., Simões, R., Maruccio, F. C., MacRae, D. C., der Hoek, L. V., Langendijk, J. A., van Ooijen, P. M. A., Janssen, T. M., & Brouwer, C. L. (2026) · Radiotherapy and Oncology · doi:10.1016/j.radonc.2026.111826
Uncertainty-Guided Diffusion Model for Biomedical Image Segmentation
Wang, J., Wang, Y., Yuan, X., & Huang, G. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729079
Alalwany, E., & Alsharif, B. (2026) · Diagnostics · doi:10.3390/diagnostics16203378
Global forest typology at 10-meter resolution for forest and land-use monitoring
Neumann, M., Raichuk, A., Potapov, P. V., Lesiv, M., Overlan, M., Rey, M., Rajakumar, R., Conserva, M., Stanimirova, R., Sims, M. J., et al. (2026) · Scientific Data · doi:10.1038/s41597-026-08299-5 · Cited by 1
C2F-SL: A Calibrated Cascade Framework for Soft Label Generation in Multispectral Segmentation
Nunes, W., Gonçalves, G. R., & Premebida, C. (2026) · International Conference on Information Science and Technology · doi:10.1109/icist71072.2026.11727863
Cross-Domain Uncertainty Evaluation in Predictive Analytics: Credit Default and Customer Churn
Valente, H. G. D. S., & Katits, E. É. (2026) · Qubahan Journal of Coaching and Sports Sciences · doi:10.48161/qjcs.v4n3a88
Ensemble MMS-unet segmentation algorithm for breast lesions based on multi-modal MRI images
Yu, H., Liu, B., Xie, Z., & Li, S. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135489
Calibration Results for Established Post-hoc Calibration Methods
Huang, W. (2025) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.15868156
Metadata
- Authors
- Mehrtash, A., Wells, W. M., Tempany, C. M., Abolmaesumi, P., & Kapur, T.
- Affiliations
- Brigham and Women's Hospital (US)
- University of British Columbia (CA)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2020-12
- Volume
- 39
- Issue
- 12
- Pages
- 3868-3878
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- PMC
- PMC7704933
- OpenAlex
- W2991523350
- Cited by
- 428
- References
- 55
- Citations by year
- 2026: 91 · 2025: 92 · 2024: 71 · 2023: 71 · 2022: 56 · 2021: 41 · 2020: 6
- FWCI
- 16.91
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- U.S. National Institutes of Health (P41EB015898)
- Natural Sciences and Engineering Research Council (NSERC) of Canada
- Canadian Institutes of Health Research
- 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 › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- confidence calibration, predictive uncertainty estimation, medical image segmentation, fully convolutional network, U-Net, Dice loss, cross-entropy loss, model ensembling, out-of-distribution detection, batch normalization, brain segmentation, cardiac image segmentation, prostate segmentation
- MeSH terms
- Brain, Calibration, Humans, Image Processing, Computer-Assisted, Male, Neural Networks, Computer, Uncertainty
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
