Bayesian uncertainty estimation for detection of long-tailed and unseen conditions in medical images

Mina Rezaei; Janne J. Näppi; Bernd Bischl; Hiroyuki Yoshida

doi:10.1117/1.JMI.10.5.054501

9 October 2023 Bayesian uncertainty estimation for detection of long-tailed and unseen conditions in medical images

Mina Rezaei, Janne J. Näppi, Bernd Bischl, Hiroyuki Yoshida

Author Affiliations +

Journal of Medical Imaging, Vol. 10, Issue 5, 054501 (October 2023). https://doi.org/10.1117/1.JMI.10.5.054501

Abstract

Purpose

Deep supervised learning provides an effective approach for developing robust models for various computer-aided diagnosis tasks. However, there is often an underlying assumption that the frequencies of the samples between the different classes of the training dataset are either similar or balanced. In real-world medical data, the samples of positive classes often occur too infrequently to satisfy this assumption. Thus, there is an unmet need for deep-learning systems that can automatically identify and adapt to the real-world conditions of imbalanced data.

Approach

We propose a deep Bayesian ensemble learning framework to address the representation learning problem of long-tailed and out-of-distribution (OOD) samples when training from medical images. By estimating the relative uncertainties of the input data, our framework can adapt to imbalanced data for learning generalizable classifiers. We trained and tested our framework on four public medical imaging datasets with various imbalance ratios and imaging modalities across three different learning tasks: semantic medical image segmentation, OOD detection, and in-domain generalization. We compared the performance of our framework with those of state-of-the-art comparator methods.

Results

Our proposed framework outperformed the comparator models significantly across all performance metrics (pairwise t-test: p < 0.01) in the semantic segmentation of high-resolution CT and MR images as well as in the detection of OOD samples (p < 0.01), thereby showing significant improvement in handling the associated long-tailed data distribution. The results of the in-domain generalization also indicated that our framework can enhance the prediction of retinal glaucoma, contributing to clinical decision-making processes.

Conclusions

Training of the proposed deep Bayesian ensemble learning framework with dynamic Monte-Carlo dropout and a combination of losses yielded the best generalization to unseen samples from imbalanced medical imaging datasets across different learning tasks.

CC BY: © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Citation Download Citation

Mina Rezaei, Janne J. Näppi, Bernd Bischl, and Hiroyuki Yoshida "Bayesian uncertainty estimation for detection of long-tailed and unseen conditions in medical images," Journal of Medical Imaging 10(5), 054501 (9 October 2023). https://doi.org/10.1117/1.JMI.10.5.054501

Received: 10 January 2023; Accepted: 20 September 2023; Published: 9 October 2023

ACCESS THE FULL ARTICLE

JOURNAL ARTICLE
14 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Gallium nitride

Education and training

Image segmentation

Data modeling

Machine learning

Semantics

Performance modeling

Purpose

Approach

Results

Conclusions

Show All Keywords

Keywords/Phrases

Search In:

Publication Years