Improving Fairness of Automated Chest Radiograph Diagnosis by Contrastive Learning.

Abstract

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop an artificial intelligence model that utilizes supervised contrastive learning to minimize bias in chest radiograph (CXR) diagnosis. Materials and Methods In this retrospective study, the proposed method was evaluated on two datasets: the Medical Imaging and Data Resource Center (MIDRC) dataset with 77,887 CXRs from 27,796 patients collected as of April 20, 2023 for COVID-19 diagnosis, and the NIH Chest x-ray 14 (NIH-CXR) dataset with 112,120 CXRs from 30,805 patients collected between 1992 and 2015. In the NIH-CXR dataset, thoracic abnormalities included atelectasis, cardiomegaly, effusion, infiltration, mass, nodule, pneumonia, pneumothorax, consolidation, edema, emphysema, fibrosis, pleural thickening, or hernia. The proposed method utilized supervised contrastive learning with carefully selected positive and negative samples to generate fair image embeddings, which were fine-tuned for subsequent tasks to reduce bias in CXR diagnosis. The method was evaluated using the marginal area under the receiver operating characteristic curve (AUC) difference (ΔmAUC). Results The proposed model showed a significant decrease in bias across all subgroups compared with the baseline models, as evidenced by a paired T-test (P < .001). The ΔmAUCs obtained by the proposed method were 0.01 (95% CI, 0.01-0.01), 0.21 (95% CI, 0.21-0.21), and 0.10 (95% CI, 0.10-0.10) for sex, race, and age subgroups, respectively, on MIDRC, and 0.01 (95% CI, 0.01-0.01) and 0.05 (95% CI, 0.05-0.05) for sex and age subgroups, respectively, on NIH-CXR. Conclusion Employing supervised contrastive learning can mitigate bias in CXR diagnosis, addressing concerns of fairness and reliability in deep learning-based diagnostic methods. ©RSNA, 2024.