CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification

TL;DR

This paper presents CheXFusion, a transformer-based method for effectively fusing multi-view chest X-ray features to improve long-tailed disease classification, achieving state-of-the-art results in a competitive challenge.

Contribution

Introduces CheXFusion, a novel transformer-based multi-view feature fusion module that incorporates label co-occurrence and balances data for improved long-tailed chest X-ray classification.

Findings

Achieved 0.372 mAP on MIMIC-CXR test set

Secured 1st place in ICCV CVAMD 2023 Shared Task

Demonstrated effectiveness of multi-view fusion and data balancing

Abstract

Medical image classification poses unique challenges due to the long-tailed distribution of diseases, the co-occurrence of diagnostic findings, and the multiple views available for each study or patient. This paper introduces our solution to the ICCV CVAMD 2023 Shared Task on CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays. Our approach introduces CheXFusion, a transformer-based fusion module incorporating multi-view images. The fusion module, guided by self-attention and cross-attention mechanisms, efficiently aggregates multi-view features while considering label co-occurrence. Furthermore, we explore data balancing and self-training methods to optimize the model's performance. Our solution achieves state-of-the-art results with 0.372 mAP in the MIMIC-CXR test set, securing 1st place in the competition. Our success in the task underscores the significance of considering multi-view settings, class imbalance, and label co-occurrence in medical image classification. Public code is available at https://github.com/dongkyuk/CXR-LT-public-solution