Skip to main navigation Skip to search Skip to main content

Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis

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

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

6 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention – MICCAI 2024 - 27th International Conference, Proceedings
EditorsMarius George Linguraru, Qi Dou, Aasa Feragen, Stamatia Giannarou, Ben Glocker, Karim Lekadir, Julia A. Schnabel
PublisherSpringer Science and Business Media Deutschland GmbH
Pages675-684
Number of pages10
ISBN (Print)9783031721168
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024 - Marrakesh, Morocco
Duration: 6 Oct 2024 → 10 Oct 2024

Publication series

NameLecture Notes in Computer Science
Volume15010 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024
Country/TerritoryMorocco
CityMarrakesh
Period6/10/24 → 10/10/24

Keywords

  • Bayesian Networks
  • Classification
  • Segmentation
  • Sensitivty Analysis
  • Sparsity
  • Uncertainty

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this