CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification
This addresses the problem of medical image classification with long-tailed distributions and multi-view data for healthcare applications, representing an incremental improvement with specific optimizations.
The paper tackled long-tailed chest X-ray classification by introducing CheXFusion, a transformer-based fusion module for multi-view features, achieving state-of-the-art results with 0.372 mAP on the MIMIC-CXR test set and winning the ICCV CVAMD 2023 Shared Task.
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