Knowing what you know in brain segmentation using Bayesian deep neural networks
Abstract
In this paper, we describe a Bayesian deep neural network (DNN) for predicting FreeSurfer segmentations of structural MRI volumes, in minutes rather than hours. The network was trained and evaluated on a large dataset (n = 11,480), obtained by combining data from more than a hundred different sites, and also evaluated on another completely held-out dataset (n = 418). The network was trained using a novel spike-and-slab dropout-based variational inference approach. We show that, on these datasets, the proposed Bayesian DNN outperforms previously proposed methods, in terms of the similarity between the segmentation predictions and the FreeSurfer labels, and the usefulness of the estimate uncertainty of these predictions. In particular, we demonstrated that the prediction uncertainty of this network at each voxel is a good indicator of whether the network has made an error and that the uncertainty across the whole brain can predict the manual quality control ratings of a scan. The proposed Bayesian DNN method should be applicable to any new network architecture for addressing the segmentation problem.
Cite
@article{arxiv.1812.01719,
title = {Knowing what you know in brain segmentation using Bayesian deep neural networks},
author = {Patrick McClure and Nao Rho and John A. Lee and Jakub R. Kaczmarzyk and Charles Zheng and Satrajit S. Ghosh and Dylan Nielson and Adam G. Thomas and Peter Bandettini and Francisco Pereira},
journal= {arXiv preprint arXiv:1812.01719},
year = {2022}
}
Comments
Submitted to Frontiers in Neuroinformatics