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

Dongkyun Kim
8/8/2023
cs.CVcs.AI

No official code found. Best implementation: dongkyunk/CheXFusion (53 stars, MIT, last commit 2024-08-03).

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

View on arXivView PDF

Code Implementations(1)

dongkyunk/CheXFusionCommunity100%
MIT

[ ICCV CVAMD 2023] Official implementation of "CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification" 🏆 1st place solution 🏆 for the ICCV CVAMD 2023 Shared Task: CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays.

534Shell, PythonSep 1, 20232 years agoMIT

Similar Papers

XFMamba: Cross-Fusion Mamba for Multi-View Medical Image Classification

89% match1 repo232025

SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation

88% match1 repo1232023

A Novel Vision Transformer with Residual in Self-attention for Biomedical Image Classification

86% match2023

Parkinson's Disease Classification Using Contrastive Graph Cross-View Learning with Multimodal Fusion of SPECT Images and Clinical Features

85% match2023

MedMimic: Physician-Inspired Multimodal Fusion for Early Diagnosis of Fever of Unknown Origin

85% match2025

Random Token Fusion for Multi-View Medical Diagnosis

85% match2024

Cite this paper

@article{kim2023chexfusion,
  title  = {CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification},
  author = {Dongkyun Kim},
  year   = {2023},
  eprint = {2308.03968},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.03968v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.03968.svg)](https://codeofpaper.com/paper/2308.03968)

Discussion