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

2018/08/03 by T. R. Gopalakrishnan Nair, Nair, Tanya, Doina Precup +5 · 12 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

paper · pdf · doi:10.48550/arxiv.1808.01200

openalex publication_date 2018/08/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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

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

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