Beyond Voxel Prediction Uncertainty: Identifying brain lesions you can trust

TL;DR

This paper introduces a novel Graph Neural Network method to assess uncertainty in brain lesion segmentation, moving beyond voxel-level measures to provide more clinically relevant uncertainty estimates.

Contribution

It presents an innovative GNN approach that fuses multiple voxel uncertainty estimators to better identify trustworthy brain lesions in medical images.

Findings

Outperforms existing voxel-wise uncertainty methods in MS lesion segmentation

Provides more clinically meaningful uncertainty assessments

Applicable to lesions of various shapes and sizes

Abstract

Deep neural networks have become the gold-standard approach for the automated segmentation of 3D medical images. Their full acceptance by clinicians remains however hampered by the lack of intelligible uncertainty assessment of the provided results. Most approaches to quantify their uncertainty, such as the popular Monte Carlo dropout, restrict to some measure of uncertainty in prediction at the voxel level. In addition not to be clearly related to genuine medical uncertainty, this is not clinically satisfying as most objects of interest (e.g. brain lesions) are made of groups of voxels whose overall relevance may not simply reduce to the sum or mean of their individual uncertainties. In this work, we propose to go beyond voxel-wise assessment using an innovative Graph Neural Network approach, trained from the outputs of a Monte Carlo dropout model. This network allows the fusion of three estimators of voxel uncertainty: entropy, variance, and model's confidence; and can be applied to any lesion, regardless of its shape or size. We demonstrate the superiority of our approach for uncertainty estimate on a task of Multiple Sclerosis lesions segmentation.