CXR-LT 2026 Challenge: Multi-Center Long-Tailed and Zero Shot Chest X-ray Classification

2026-04-16

AI Summary

This study addresses the challenges of long-tailed pathological distributions, difficulty in identifying rare diseases, and limited open-world generalization in chest X-ray analysis. The authors construct a large-scale, multi-center dataset and define two core tasks: robust multi-label classification across 30 known diseases and zero-shot detection of six unseen rare conditions. For the first time, the project integrates high-quality annotations from radiologists across multiple centers to systematically evaluate model performance on head versus tail classes under long-tailed distributions, calibration quality, and cross-center generalization gaps. Leveraging vision–language foundation models combined with multi-label learning and zero-shot techniques, the proposed approach outperforms existing methods on both in-distribution and open-world tasks, establishing the first benchmark that simultaneously accounts for long-tailed data, multi-center variability, and open-world generalization for clinical AI systems.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Chest X-ray (CXR) interpretation is hindered by the long-tailed distribution of pathologies and the open-world nature of clinical environments. Existing benchmarks often rely on closed-set classes from a single institution, failing to capture the prevalence of rare diseases or the appearance of novel findings. To address this, we present the CXR-LT challenge. The first event, CXR-LT 2023, established a large-scale benchmark for long-tailed multi-label CXR classification and identified key challenges in rare disease recognition. CXR-LT 2024 further expanded the label space and introduced a zero-shot task to study generalization to unseen findings. Building on the success of CXR-LT 2023 and 2024, this third iteration of the benchmark introduces a multi-center dataset comprising over 145,000 images from PadChest and NIH Chest X-ray datasets. Additionally, all development and test sets in CXR-LT 2026 are annotated by radiologists, providing a more reliable and clinically grounded evaluation than report-derived labels. The challenge defines two core tasks this year: (1) Robust Multi-Label Classification on 30 known classes and (2) Open-World Generalization to 6 unseen (out-of-distribution) rare disease classes. This paper summarizes the overview of the CXR-LT 2026 challenge. We describe the data collection and annotation procedures, analyze solution strategies adopted by participating teams, and evaluate head-versus-tail performance, calibration, and cross-center generalization gaps. Our results show that vision-language foundation models improve both in-distribution and zero-shot performance, but detecting rare findings under multi-center shift remains challenging. Our study provides a foundation for developing and evaluating AI systems in realistic long-tailed and open-world clinical conditions.

Problem

• long-tailed distribution
• zero-shot classification
• chest X-ray
• multi-center
• open-world generalization

Innovation

• long-tailed classification
• zero-shot learning
• multi-center dataset
• radiologist-annotated labels
• open-world generalization