Computer-aided abnormality detection in chest radiographs in a clinical setting via domain-adaptation
This work aims to improve the reliability of AI-aided diagnosis for radiologists by making deep learning models more robust to variations in X-ray equipment and configurations in clinical settings. This is an incremental improvement to existing deployment challenges.
This paper addresses the problem of poor generalization of deep learning models for abnormality detection in chest radiographs when moving from publicly available datasets to clinical settings, due to domain shift. They propose a domain-shift detection and removal method, demonstrating its effectiveness in deploying pre-trained models for this task.
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.