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

arXiv: https://arxiv.org/abs/2602.22092 · HTML: https://mlsanity.com/paper/2602.22092/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [PadChest: A large chest x-ray image dataset with multi-label annotated reports](https://mlsanity.com/paper/1901.07441/) (2019)
- [A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises](https://mlsanity.com/paper/2008.09104/) (2020)
- [Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform](https://mlsanity.com/paper/2110.05802/) (2021)
- [Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study](https://mlsanity.com/paper/2208.13365/) (2022)
- [PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generation](https://mlsanity.com/paper/2411.05085/) (2024)
- [Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition](https://mlsanity.com/paper/2104.11057/) (2021)
- [ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classification](https://mlsanity.com/paper/2209.00183/) (2022)

## Built on by (most cited first, 3 of 3)

- [Loss Design and Architecture Selection for Long-Tailed Multi-Label Chest X-Ray Classification](https://mlsanity.com/paper/2603.02294/) (2026)
- [CXR-LT 2026 Challenge: Projection-Aware Multi-Label and Zero-Shot Chest X-Ray Classification](https://mlsanity.com/paper/2604.02185/) (2026)
- [TRCGL-Net: A Long-Tailed Multi-Label Chest X-Ray Classification Framework with Generative Data Augmentation and Label Co-Occurrence Modeling](https://mlsanity.com/paper/2607.00975/) (2026)

## Abstract (arXiv)

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 single institutions, failing to capture the prevalence of rare diseases or the appearance of novel findings. To address this, we present the CXR-LT 2026 challenge. This third iteration of the benchmark introduces a multi-center dataset comprising over 145,000 images from PadChest and NIH Chest X-ray datasets. The challenge defines two core tasks: (1) Robust Multi-Label Classification on 30 known classes and (2) Open-World Generalization to 6 unseen (out-of-distribution) rare disease classes. We report the results of the top-performing teams, evaluating them via mean Average Precision (mAP), AUROC, and F1-score. The winning solutions achieved an mAP of 0.5854 on Task 1 and 0.4315 on Task 2, demonstrating that large-scale vision-language pre-training significantly mitigates the performance drop typically associated with zero-shot diagnosis.