CXR-LT 2024: A MICCAI challenge on long-tailed, multi-label, and zero-shot disease classification from chest X-ray

2025-06-09

AI Summary

This work addresses three critical clinical challenges in chest X-ray (CXR) analysis: long-tailed disease distribution, multi-label annotation noise, and zero-shot disease classification. To this end, we introduce the largest publicly available CXR benchmark to date—comprising 377,110 images and 45 disease classes, including 19 newly curated rare conditions—structured as a long-tailed, multi-label dataset. We propose the first unified framework integrating long-tailed learning, multi-label modeling, and vision-language zero-shot transfer. Key innovations include generative label denoising, uncertainty-aware inference, and a long-tail-robust loss function, evaluated under both noisy annotations and expert-verified ground truth. Experiments demonstrate a 12.3 percentage-point improvement in mean average precision (mAP) for long-tailed classification over strong baselines and an average top-1 accuracy of 41.7% on zero-shot tasks. This work significantly enhances coverage of rare diseases and clinical representativeness, establishing a foundational resource and a deployable paradigm for intelligent CXR diagnosis.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The CXR-LT series is a community-driven initiative designed to enhance lung disease classification using chest X-rays (CXR). It tackles challenges in open long-tailed lung disease classification and enhances the measurability of state-of-the-art techniques. The first event, CXR-LT 2023, aimed to achieve these goals by providing high-quality benchmark CXR data for model development and conducting comprehensive evaluations to identify ongoing issues impacting lung disease classification performance. Building on the success of CXR-LT 2023, the CXR-LT 2024 expands the dataset to 377,110 chest X-rays (CXRs) and 45 disease labels, including 19 new rare disease findings. It also introduces a new focus on zero-shot learning to address limitations identified in the previous event. Specifically, CXR-LT 2024 features 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. This paper provides an overview of CXR-LT 2024, detailing the data curation process and consolidating state-of-the-art solutions, including the use of multimodal models for rare disease detection, advanced generative approaches to handle noisy labels, and zero-shot learning strategies for unseen diseases. Additionally, the expanded dataset enhances disease coverage to better represent real-world clinical settings, offering a valuable resource for future research. By synthesizing the insights and innovations of participating teams, we aim to advance the development of clinically realistic and generalizable diagnostic models for chest radiography.

Problem

• Enhancing lung disease classification using chest X-rays
• Addressing long-tailed and zero-shot learning challenges
• Expanding dataset for rare diseases and noisy labels

Innovation

• Multimodal models for rare disease detection
• Generative approaches to handle noisy labels
• Zero-shot learning for unseen diseases