LTCXNet: Advancing Chest X-Ray Analysis with Solutions for Long-Tailed Multi-Label Classification and Fairness Challenges

TL;DR

This paper introduces LTCXNet, a new framework for chest X-ray analysis that addresses long-tailed, multi-label data challenges and fairness issues, significantly improving detection of rare diseases.

Contribution

LTCXNet combines ConvNeXt, ML-Decoder, data augmentation, and ensemble methods to enhance multi-label classification and fairness in medical imaging.

Findings

Improved detection of rare classes like Pneumoperitoneum by 79%.

Enhanced overall CXR interpretation performance.

Identified fairness impacts of different methods.

Abstract

Chest X-rays (CXRs) often display various diseases with disparate class frequencies, leading to a long-tailed, multi-label data distribution. In response to this challenge, we explore the Pruned MIMIC-CXR-LT dataset, a curated collection derived from the MIMIC-CXR dataset, specifically designed to represent a long-tailed and multi-label data scenario. We introduce LTCXNet, a novel framework that integrates the ConvNeXt model, ML-Decoder, and strategic data augmentation, further enhanced by an ensemble approach. We demonstrate that LTCXNet improves the performance of CXR interpretation across all classes, especially enhancing detection in rarer classes like `Pneumoperitoneum' and `Pneumomediastinum' by 79\% and 48\%, respectively. Beyond performance metrics, our research extends into evaluating fairness, highlighting that some methods, while improving model accuracy, could inadvertently affect fairness across different demographic groups negatively. This work contributes to advancing the understanding and management of long-tailed, multi-label data distributions in medical imaging, paving the way for more equitable and effective diagnostic tools.