CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays

Chest radiography presents a "long-tailed" distribution of findings, where a
few diseases are common, but most are rare. Diagnosis is further complicated
by its multi-label nature, as patients often exhibit multiple co-occurring
findings. While recent research has attempted to address the long-tailed
medical image classification problem, the interplay between class imbalance
and label co-occurrence remains underexplored. The **CXR-LT 2024 challenge**
builds on the success of CXR-LT 2023, expanding the dataset of 377,110 chest
X-rays (CXRs) to 45 disease labels, including 19 new rare disease findings.
This year 's challenge introduces three tasks: (i) long-tailed classification
on a large, noisy test set, (ii) long-tailed classification on a manually
annotated "gold standard" subset, and (iii) zero-shot generalization to five
previously unseen disease findings. CXR-LT 2024 addresses critical challenges
in long-tailed, multi-label, and zero-shot learning for medical imaging by
synthesizing state-of-the-art solutions from the international research
community. Further, our dataset contributions -- expanding disease coverage to
better reflect real-world clinical settings -- offer a valuable resource for
future research. This project contains labels from the CXR-LT 2024 and CXR-LT
2023 challenges, as well as a related subset used in the MICCAI 2023 paper,
"How Does Pruning Impact Multi-Label Long-Tailed Learning?"

胸部放射成像的检查结果呈现长尾分布（long-tailed distribution）特征：少数疾病较为常见，而大多数疾病则十分罕见。其多标签属性（multi-label nature）进一步加剧了诊断的复杂性——患者往往表现出多种共存的检查结果。尽管近期研究已尝试解决长尾医学图像分类问题，但类别不平衡（class imbalance）与标签共现（label co-occurrence）之间的相互作用仍未得到充分探索。**CXR-LT 2024挑战赛**在CXR-LT 2023的成功基础上，将包含377,110张胸部X光片（CXRs）的数据集扩展至45个疾病标签，其中涵盖19种新的罕见病检查结果。本年度挑战赛设置了三项任务：（i）在大型噪声测试集上进行长尾分类；（ii）在人工标注的“金标准（gold standard）”子集上进行长尾分类；（iii）对五种未见疾病结果进行零样本泛化（zero-shot generalization）。CXR-LT 2024通过整合国际研究界的最先进（state-of-the-art）解决方案，致力于解决医学成像领域中长尾、多标签及零样本学习的关键挑战。此外，我们的数据集贡献——扩展疾病覆盖范围以更真实地反映临床场景——为未来研究提供了宝贵资源。本项目包含来自CXR-LT 2024和CXR-LT 2023挑战赛的标签，以及MICCAI 2023会议论文《"How Does Pruning Impact Multi-Label Long-Tailed Learning?"》中使用的相关子集。