تقرير
Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
العنوان: | Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge |
---|---|
المؤلفون: | Holste, Gregory, Zhou, Yiliang, Wang, Song, Jaiswal, Ajay, Lin, Mingquan, Zhuge, Sherry, Yang, Yuzhe, Kim, Dongkyun, Nguyen-Mau, Trong-Hieu, Tran, Minh-Triet, Jeong, Jaehyup, Park, Wongi, Ryu, Jongbin, Hong, Feng, Verma, Arsh, Yamagishi, Yosuke, Kim, Changhyun, Seo, Hyeryeong, Kang, Myungjoo, Celi, Leo Anthony, Lu, Zhiyong, Summers, Ronald M., Shih, George, Wang, Zhangyang, Peng, Yifan |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
الوصف: | Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" $\unicode{x2013}$ 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. Comment: Update after major revision |
نوع الوثيقة: | Working Paper |
DOI: | 10.1016/j.media.2024.103224 |
URL الوصول: | http://arxiv.org/abs/2310.16112 |
رقم الأكسشن: | edsarx.2310.16112 |
قاعدة البيانات: | arXiv |
DOI: | 10.1016/j.media.2024.103224 |
---|