Passer à la navigation principale Passer à la recherche Passer au contenu principal

Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis

  • Polytechnique Montréal
  • Université de Montréal
  • Centre Hospitalier de L'Universite de Montreal

Résultats de recherche: Chapitre dans un livre, rapport, actes de conférence › Participation à un ouvrage collectif lié à un colloque ou une conférence › Revue par des pairs

6 Citations (Scopus)

Résumé

Efficiently quantifying predictive uncertainty in medical images remains a challenge. While Bayesian neural networks (BNN) offer reliable predictive uncertainty, they require substantial computational resources to train. Although Bayesian approximations such as ensembles have shown promise, they still suffer from high training costs. Existing approaches to reducing computational burden primarily focus on lowering the costs of BNN inference, with limited efforts to improve training efficiency and minimize parameter complexity. This study introduces a training procedure for a sparse (partial) Bayesian network. Our method selectively assigns a subset of parameters as Bayesian by assessing their deterministic saliency through gradient sensitivity analysis. The resulting network combines deterministic and Bayesian parameters, exploiting the advantages of both representations to achieve high task-specific performance and minimize predictive uncertainty. Demonstrated on multi-label ChestMNIST for classification and ISIC, LIDC-IDRI for segmentation, our approach achieves competitive performance and predictive uncertainty estimation by reducing Bayesian parameters by over 95%, significantly reducing computational expenses compared to fully Bayesian and ensemble methods.

langue originaleAnglais
titreMedical Image Computing and Computer Assisted Intervention – MICCAI 2024 - 27th International Conference, Proceedings
rédacteurs en chefMarius George Linguraru, Qi Dou, Aasa Feragen, Stamatia Giannarou, Ben Glocker, Karim Lekadir, Julia A. Schnabel
EditeurSpringer Science and Business Media Deutschland GmbH
Pages675-684
Nombre de pages10
ISBN (imprimé)9783031721168
Les DOIs
étatPublié - 2024
Modification externeOui
Evénement27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024 - Marrakesh, Maroc
Durée: 6 oct. 2024 → 10 oct. 2024

Série de publications

NomLecture Notes in Computer Science
Volume15010 LNCS
ISSN (imprimé)0302-9743
ISSN (Electronique)1611-3349

Conférence

Conférence27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024
Pays/TerritoireMaroc
La villeMarrakesh
Période6/10/24 → 10/10/24

Empreinte digitale

Voici les principaux termes ou expressions associés à « Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis ». Ces libellés thématiques sont générés à partir du titre et du résumé de la publication. Ensemble, ils forment une empreinte digitale unique.

Citer cette ressource