CheX-DS: Improving Chest X-ray Image Classification with Ensemble Learning Based on DenseNet and Swin Transformer

TL;DR

CheX-DS is a novel ensemble deep learning model combining DenseNet and Swin Transformer to improve chest X-ray classification, effectively handling data imbalance and outperforming previous methods on NIH dataset.

Contribution

This paper introduces CheX-DS, a new ensemble model that integrates CNN and Transformer architectures for better chest X-ray diagnosis.

Findings

Achieved an average AUC of 83.76% on NIH dataset.

Effectively addresses data imbalance with combined loss functions.

Outperforms previous state-of-the-art methods.

Abstract

The automatic diagnosis of chest diseases is a popular and challenging task. Most current methods are based on convolutional neural networks (CNNs), which focus on local features while neglecting global features. Recently, self-attention mechanisms have been introduced into the field of computer vision, demonstrating superior performance. Therefore, this paper proposes an effective model, CheX-DS, for classifying long-tail multi-label data in the medical field of chest X-rays. The model is based on the excellent CNN model DenseNet for medical imaging and the newly popular Swin Transformer model, utilizing ensemble deep learning techniques to combine the two models and leverage the advantages of both CNNs and Transformers. The loss function of CheX-DS combines weighted binary cross-entropy loss with asymmetric loss, effectively addressing the issue of data imbalance. The NIH ChestX-ray14 dataset is selected to evaluate the model's effectiveness. The model outperforms previous studies with an excellent average AUC score of 83.76\%, demonstrating its superior performance.