Title | Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge. |
Publication Type | Journal Article |
Year of Publication | 2023 |
Authors | Holste G, Zhou Y, Wang S, Jaiswal A, Lin M, Zhuge S, Yang Y, Kim D, Nguyen-Mau T-H, Tran M-T, Jeong J, Park W, Ryu J, Hong F, Verma A, Yamagishi Y, Kim C, Seo H, Kang M, Celi LAnthony, Lu Z, Summers RM, Shih G, Wang Z, Peng Y |
Journal | ArXiv |
Date Published | 2023 Oct 24 |
ISSN | 2331-8422 |
Abstract | Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" - there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple findings simultaneously. While researchers have begun to study the problem of long-tailed learning in medical image recognition, few have studied the interaction of label imbalance and label co-occurrence posed by long-tailed, multi-label disease classification. To engage with the research community on this emerging topic, we conducted an open challenge, CXR-LT, on long-tailed, multi-label thorax disease classification from chest X-rays (CXRs). We publicly release a large-scale benchmark dataset of over 350,000 CXRs, each labeled with at least one of 26 clinical findings following a long-tailed distribution. We synthesize common themes of top-performing solutions, providing practical recommendations for long-tailed, multi-label medical image classification. Finally, we use these insights to propose a path forward involving vision-language foundation models for few- and zero-shot disease classification. |
DOI | 10.1109/ICHI54592.2022.00050 |
Alternate Journal | ArXiv |
PubMed ID | 37986726 |
PubMed Central ID | PMC10659524 |
Grant List | R01 LM014306 / LM / NLM NIH HHS / United States |