Improving Imbalanced Multi-Label Chest X-Ray Diagnosis via CBAM-Enhanced CNN Backbones

TL;DR

This paper introduces a CBAM-enhanced CNN approach to improve multi-label chest X-ray diagnosis, addressing class imbalance and pathology localization challenges, achieving higher AUC scores.

Contribution

The study proposes integrating CBAM into CNNs to enhance feature refinement and classification performance in imbalanced multi-label chest X-ray datasets.

Findings

Achieved a mean AUC of 0.8695 on ChestXray14 dataset.

Outperformed several state-of-the-art baseline methods.

Demonstrated effectiveness of CBAM integration in medical image classification.

Abstract

Chest radiography is a widely used imaging modality for thoracic disease diagnosis, yet its conventional interpretation remains time-consuming and heavily dependent on expert knowledge. While deep learning has improved diagnostic efficiency through automated feature extraction, challenges such as class imbalance and the localization of multiple co-existing pathologies remain unsolved. In this paper, inspired by the strength of Convolutional Block Attention Module (CBAM) in feature refinement and the capability of CNN blocks in feature extraction, we propose a strategy to integrate CBAM into traditional CNN blocks to enhance performance in multi-label classification tasks. Our method achieves a mean AUC of 0.8695 on ChestXray14 dataset, outperforming several state-of-the-art baselines.Our source code is available at: https://github.com/NNNguyenDuyyy/FETC_CBAM_Enhanced_CNN.git