Beyond Voxel Prediction Uncertainty: Identifying brain lesions you can trust
This work addresses the need for clinically interpretable uncertainty estimates in automated medical image analysis, which is crucial for improving clinician trust and adoption, though it is incremental as it builds on existing Monte Carlo dropout methods.
The authors tackled the problem of unreliable uncertainty estimates in deep learning-based medical image segmentation by proposing a Graph Neural Network that aggregates voxel-level uncertainties into lesion-level assessments, achieving superior performance on a Multiple Sclerosis lesion segmentation task.
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.