Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation

DOI10.1016/J.CSDA.2019.106816OpenAlexW2965563166MaRDI QIDQ2008102FDOQ2008102

Authors: Yongchan Kwon, Joong-Ho Won, Beom Joon Kim, Myunghee Cho Paik 

Publication date: 22 November 2019

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.csda.2019.106816

Recommendations

• Neural Network Uncertainty Assessment Using Bayesian Statistics: A Remote Sensing Application
• Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
• Bayesian MLP neural networks for image analysis
• Scaling Up Bayesian Uncertainty Quantification for Inverse Problems Using Deep Neural Networks
• scientific article; zbMATH DE number 7326170
• Bayesian neural networks for uncertainty quantification in data-driven materials modeling
• Bayesian inference and uncertainty quantification for medical image reconstruction with Poisson data

zbMATH Keywords

uncertainty quantificationBayesian neural networkaleatoric and epistemic uncertaintyischemic stroke lesion segmentationretinal blood vessel segmentation

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Applications of statistics to biology and medical sciences; meta analysis (62P10) Artificial neural networks and deep learning (68T07) Biomedical imaging and signal processing (92C55)

Cites Work

• Statistical Methods for Rates and Proportions

Cited In (6)

• Quantifying predictive uncertainty in damage classification for nondestructive evaluation using Bayesian approximation and deep learning
• Information aware max-norm Dirichlet networks for predictive uncertainty estimation
• Improved quasi-uniform stability criterion of fractional-order neural networks with discrete and distributed delays
• Bayesian image segmentation under varying blur with triplet Markov random field
• Numerical Analysis for Convergence of a Sample-Wise Backpropagation Method for Training Stochastic Neural Networks
• Epistemic uncertainty quantification in deep learning classification by the delta method

Uses Software

• U-Net

This page was built for publication: Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2008102)