mlsanityData to 14 Oct 2026

Explaining Uncertainty in Multiple Sclerosis Cortical Lesion Segmentation Beyond Prediction Errors

arXiv 2504.04814 ↗First posted 7 Apr 2025eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Trustworthy artificial intelligence (AI) is essential in healthcare, particularly for high-stakes tasks like medical image segmentation. Explainable AI and uncertainty quantification significantly enhance AI reliability by addressing key attributes such as robustness, usability, and explainability. Despite extensive technical advances in uncertainty quantification for medical imaging, understanding the clinical informativeness and interpretability of uncertainty remains limited. This study presents an interpretability framework for analyzing lesion-scale predictive uncertainty in cortical lesion segmentation in multiple sclerosis using deep ensembles. The analysis shifts the focus from the uncertainty--error relationship towards clinically relevant medical and engineering factors. Our findings reveal that instance-wise uncertainty is strongly related to lesion size, shape, and cortical involvement. Expert rater feedback confirms that similar factors impede annotator confidence. Evaluations conducted on two datasets (206 patients, almost 2000 lesions) under both in-domain and distribution-shift conditions highlight the utility of the framework in different scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 76 references that are in the map. First posted on arXiv 7 Apr 2025.

Builds on

33 of 76 references.

References · 33

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  7. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  8. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  9. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 283
  10. 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
  11. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 280
  12. 2021SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retrainingcited by 237
21 more
  1. 2021Trustworthy AI: From Principles to Practicescited by 207
  2. 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
  3. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  4. 2019PHiSeg: Capturing Uncertainty in Medical Image Segmentationcited by 128
  5. 2021Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Taskscited by 101
  6. 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
  7. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 63
  8. 2023FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcarecited by 60
  9. 2023A Review of Uncertainty Estimation and its Application in Medical Imagingcited by 59
  10. 2018Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilitiescited by 54
  11. 2018Bayesian QuickNAT: Model Uncertainty in Deep Whole-Brain Segmentation for Structure-wise Quality Controlcited by 39
  12. 2023A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methodscited by 39
  13. 2020Explanation and Use of Uncertainty Quantified by Bayesian Neural Network Classifiers for Breast Histopathology Imagescited by 13
  14. 2023Annotator Consensus Prediction for Medical Image Segmentation with Diffusion Modelscited by 10
  15. 2022Novel structural-scale uncertainty measures and error retention curves: application to multiple sclerosiscited by 8
  16. 2023Structural-Based Uncertainty in Deep Learning Across Anatomical Scales: Analysis in White Matter Lesion Segmentationcited by 7
  17. 2022Beyond Voxel Prediction Uncertainty: Identifying brain lesions you can trustcited by 6
  18. 2023Boundary-weighted logit consistency improves calibration of segmentation networkscited by 4
  19. 2024ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation -- Methods and Resultscited by 4
  20. 2019Automatic detection of lesion load change in Multiple Sclerosis using convolutional neural networks with segmentation confidencecited by 3
  21. 2022Calibrating Segmentation Networks with Margin-based Label Smoothingcited by 2

Built on by

Not cited yet.