Efficient Bayesian Uncertainty Estimation for nnU-Net

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Yidong, Yang, Changchun, Schweidtmann, Artur, Tao, Qian
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914777994887168
author Zhao, Yidong
Yang, Changchun
Schweidtmann, Artur
Tao, Qian
author_facet Zhao, Yidong
Yang, Changchun
Schweidtmann, Artur
Tao, Qian
contents The self-configuring nnU-Net has achieved leading performance in a large range of medical image segmentation challenges. It is widely considered as the model of choice and a strong baseline for medical image segmentation. However, despite its extraordinary performance, nnU-Net does not supply a measure of uncertainty to indicate its possible failure. This can be problematic for large-scale image segmentation applications, where data are heterogeneous and nnU-Net may fail without notice. In this work, we introduce a novel method to estimate nnU-Net uncertainty for medical image segmentation. We propose a highly effective scheme for posterior sampling of weight space for Bayesian uncertainty estimation. Different from previous baseline methods such as Monte Carlo Dropout and mean-field Bayesian Neural Networks, our proposed method does not require a variational architecture and keeps the original nnU-Net architecture intact, thereby preserving its excellent performance and ease of use. Additionally, we boost the segmentation performance over the original nnU-Net via marginalizing multi-modal posterior models. We applied our method on the public ACDC and M&M datasets of cardiac MRI and demonstrated improved uncertainty estimation over a range of baseline methods. The proposed method further strengthens nnU-Net for medical image segmentation in terms of both segmentation accuracy and quality control.
format Preprint
id arxiv_https___arxiv_org_abs_2212_06278
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Efficient Bayesian Uncertainty Estimation for nnU-Net
Zhao, Yidong
Yang, Changchun
Schweidtmann, Artur
Tao, Qian
Computer Vision and Pattern Recognition
Artificial Intelligence
The self-configuring nnU-Net has achieved leading performance in a large range of medical image segmentation challenges. It is widely considered as the model of choice and a strong baseline for medical image segmentation. However, despite its extraordinary performance, nnU-Net does not supply a measure of uncertainty to indicate its possible failure. This can be problematic for large-scale image segmentation applications, where data are heterogeneous and nnU-Net may fail without notice. In this work, we introduce a novel method to estimate nnU-Net uncertainty for medical image segmentation. We propose a highly effective scheme for posterior sampling of weight space for Bayesian uncertainty estimation. Different from previous baseline methods such as Monte Carlo Dropout and mean-field Bayesian Neural Networks, our proposed method does not require a variational architecture and keeps the original nnU-Net architecture intact, thereby preserving its excellent performance and ease of use. Additionally, we boost the segmentation performance over the original nnU-Net via marginalizing multi-modal posterior models. We applied our method on the public ACDC and M&M datasets of cardiac MRI and demonstrated improved uncertainty estimation over a range of baseline methods. The proposed method further strengthens nnU-Net for medical image segmentation in terms of both segmentation accuracy and quality control.
title Efficient Bayesian Uncertainty Estimation for nnU-Net
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2212.06278