Beyond Voxel Prediction Uncertainty: Identifying brain lesions you can trust - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Beyond Voxel Prediction Uncertainty: Identifying brain lesions you can trust

Résumé

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.
Fichier principal
Vignette du fichier
MICCAI_2022_Paper_HD-final.pdf (728.35 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03883749 , version 1 (04-12-2022)

Identifiants

Citer

Benjamin Lambert, Florence Forbes, Senan Doyle, Alan Tucholka, Michel Dojat. Beyond Voxel Prediction Uncertainty: Identifying brain lesions you can trust. iMIMIC 2022 - Workshop on Interpretability of Machine Intelligence in Medical Image Computing, Sep 2022, Singapore, Singapore. pp.61-70, ⟨10.1007/978-3-031-17976-1_6⟩. ⟨hal-03883749⟩
34 Consultations
31 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More