Many real-world problems, including diagnostic medical imaging exams, are “long-tailed” – there are a few common findings followed by more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple disease findings simultaneously. This is distinct from most large-scale image classification benchmarks, where each image only belongs to one label and the distribution of labels is relatively balanced. While researchers have begun to study the problem of long-tailed learning in medical image recognition [1-3], few have studied its interplay with label co-occurrence. This competition will provide a challenging large-scale multi-label long-tailed learning task on chest X-rays (CXRs), encouraging community engagement with this emerging interdisciplinary topic.

This competition is hosted in conjunction with the ICCV 2023 workshop, Computer Vision for Automated Medical Diagnosis (CVAMD). Upon completion of the competition, we will invite participants to submit their solutions for porential presentation at CVAMD 2023 and publication in the ICCV 2023 workshop proceedings. We intend to accept 5-6 papers for publication and select 3 of the accepted papers for oral presentation at CVAMD. For more information about CVAMD, see https://cvamd2023.github.io/.

Dataset

This challenge will use an expanded version of MIMIC-CXR-JPG [4], a large benchmark dataset for automated thorax disease classification. Following [1], each CXR study in the dataset is labeled with a total of 12 new rare disease findings extracted from radiology reports. The resulting long-tailed (LT) dataset contains 377,110 CXRs, each labeled with at least one of 26 clinical findings (including a "No Finding" class).

Task

Given a CXR, detect all pathologies present (or predict “No Finding” if none present). To do this, you will train multi-label thorax disease classifiers on the provided labeled training data.

Evaluation

Models will be evaluated on the provided testing set using “macro-averaged” mean Average Precision (mAP).

Online Evaluation

The competition will be conducted through the CodaLab platform.

1. Holste, Gregory, et al. "Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study." Data Augmentation, Labelling, and Imperfections: Second MICCAI Workshop, DALI 2022, Held in Conjunction with MICCAI 2022, Singapore, September 22, 2022, Proceedings. Cham: Springer Nature Switzerland, 2022.
2. Yang, Zhixiong, et al. "ProCo: Prototype-Aware Contrastive Learning for Long-Tailed Medical Image Classification." Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part VIII. Cham: Springer Nature Switzerland, 2022.
3. Ju, Lie, et al. "Relational subsets knowledge distillation for long-tailed retinal diseases recognition." Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part VIII 24. Springer International Publishing, 2021.
4. Johnson, Alistair EW, et al. "MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs." arXiv preprint arXiv:1901.07042 (2019).