Computer-aided abnormality detection in chest radiographs in a clinical setting via domain-adaptation

TL;DR

This paper presents a domain-shift detection and removal method to improve the generalization of deep learning models for abnormality detection in chest radiographs in clinical settings, addressing data heterogeneity issues.

Contribution

It introduces a novel domain-shift detection and removal technique tailored for chest radiograph analysis, enhancing model deployment in real-world clinical environments.

Findings

Effective domain-shift detection and removal demonstrated

Improved model performance in clinical setting

Addresses heterogeneity in X-ray data sources

Abstract

Deep learning (DL) models are being deployed at medical centers to aid radiologists for diagnosis of lung conditions from chest radiographs. Such models are often trained on a large volume of publicly available labeled radiographs. These pre-trained DL models' ability to generalize in clinical settings is poor because of the changes in data distributions between publicly available and privately held radiographs. In chest radiographs, the heterogeneity in distributions arises from the diverse conditions in X-ray equipment and their configurations used for generating the images. In the machine learning community, the challenges posed by the heterogeneity in the data generation source is known as domain shift, which is a mode shift in the generative model. In this work, we introduce a domain-shift detection and removal method to overcome this problem. Our experimental results show the proposed method's effectiveness in deploying a pre-trained DL model for abnormality detection in chest radiographs in a clinical setting.