Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation

2018/08/03 by Tanya Nair, T. R. Gopalakrishnan Nair, Doina Precup +6 · 1 voice · 14 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #AI in cancer detection #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #cs.CV

paper · pdf · doi:10.48550/arxiv.1808.01200

Updated references in Introduction; Accepted to the 21st International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2018)

openalex publication_date 2018/08/03 · arxiv published 2018/08/03 · arxiv created 2018/10/16 · arxiv updated 2018/10/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep learning (DL) networks have recently been shown to outperform other segmentation methods on various public, medical-image challenge datasets [3,11,16], especially for large pathologies. However, in the context of diseases such as Multiple Sclerosis (MS), monitoring all the focal lesions visible on MRI sequences, even very small ones, is essential for disease staging, prognosis, and evaluating treatment efficacy. Moreover, producing deterministic outputs hinders DL adoption into clinical routines. Uncertainty estimates for the predictions would permit subsequent revision by clinicians. We present the first exploration of multiple uncertainty estimates based on Monte Carlo (MC) dropout [4] in the context of deep networks for lesion detection and segmentation in medical images. Specifically, we develop a 3D MS lesion segmentation CNN, augmented to provide four different voxel-based uncertainty measures based on MC dropout. We train the network on a proprietary, large-scale, multi-site, multi-scanner, clinical MS dataset, and compute lesion-wise uncertainties by accumulating evidence from voxel-wise uncertainties within detected lesions. We analyze the performance of voxel-based segmentation and lesion-level detection by choosing operating points based on the uncertainty. Empirical evidence suggests that uncertainty measures consistently allow us to choose superior operating points compared only using the network's sigmoid output as a probability.

Cited by

• Automatic Neuronal Activity Segmentation in Fast Four Dimensional Spatio-Temporal Fluorescence Imaging using Bayesian Approach
• An Empirical Study on Variance-based MC Dropout Uncertainty-Error Correlation in 2D Brain Tumor Segmentation
• MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation
• Multi-Method Ensemble for Out-of-Distribution Detection
• Segmenting Thalamic Nuclei: T1 Maps Provide a Reliable and Efficient Solution
• Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models
• A Multi-granularity Concept Sparse Activation and Hierarchical Knowledge Graph Fusion Framework for Rare Disease Diagnosis
• Towards Reliable WMH Segmentation under Domain Shift: An Application Study using Maximum Entropy Regularization to Improve Uncertainty Estimation
• UPMAD-Net: A Brain Tumor Segmentation Network with Uncertainty Guidance and Adaptive Multimodal Feature Fusion
• UNSURF: Uncertainty Quantification for Cortical Surface Reconstruction of Clinical Brain MRIs
• WQLCP: Weighted Adaptive Conformal Prediction for Robust Uncertainty Quantification Under Distribution Shifts
• OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptation
• A Novel Convolutional Neural Network for Automated Multiple Sclerosis Brain Lesion Segmentation
• Explaining Uncertainty in Multiple Sclerosis Lesion Segmentation Beyond Prediction Errors

Discussions

• In WE-08 prof. Tal Arbel @mcgillu at #ISMRM19 deals with uncertainty in Machine Learning. Key point: Montecarlo dropout to estimate uncertainty + show the uncertainty to your docs, they will move upon [bsky, 0 points, 0 comments]

Related

• Beyond Voxel Prediction Uncertainty: Identifying brain lesions you can trust
• Explaining Uncertainty in Multiple Sclerosis Lesion Segmentation Beyond Prediction Errors
• Ensemble CNN and Uncertainty Modeling to Improve Automatic Identification/Segmentation of Multiple Sclerosis Lesions in Magnetic Resonance Imaging
• Improving Uncertainty-based Out-of-Distribution Detection for Medical Image Segmentation
• Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods