CXR-Next: An Explainable Multi-Class Deep Learning Framework for Thoracic Disease Classification from Chest X-Rays

DOI

10.2991/978-94-6239-664-7_7How to use a DOI?

Keywords

Deep learning; Chest X-ray; ConvNeXt; Explainable AI; Grad-CAM

Abstract

Chest X-ray imaging remains a frontline tool for diagnosing thoracic diseases, yet manual reading is labor-intensive and susceptible to inter-reader variability. This work proposes CXR-Next, an explainable deep learning framework built upon a ConvNeXt-Base backbone to perform six-class classification—Normal, Viral Pneumonia, Bacterial Pneumonia, COVID-19, Tuberculosis, and Emphysema—from chest radiographs. We curate an 18,036-image subset (“ChestX6”) and apply standardized preprocessing, cross-split de-duplication via MD5 hashing, class-balanced sampling, and data augmentation. Our model achieves 94.99% accuracy, 95.11 macro F1, and an AUC-ROC of 0.98, outperforming ResNet-50 and EfficientNet baselines by 5–7%. To enhance interpretability, Grad-CAM heatmaps highlight imaging regions that influence class decisions, facilitating clinical review and trust. While results are promising, further validation on larger and more diverse datasets, along with prospective clinical trials, is necessary before deployment. CXR-Next represents a step toward transparent, automated screening in resource-constrained settings.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Md Faisal Hasan
AU  - Mst Rokshanara Toma
AU  - Md Ataullha
AU  - Sharifur Rahman
AU  - M. Shahidur Rahman
PY  - 2026
DA  - 2026/06/08
TI  - CXR-Next: An Explainable Multi-Class Deep Learning Framework for Thoracic Disease Classification from Chest X-Rays
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 76
EP  - 87
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_7
DO  - 10.2991/978-94-6239-664-7_7
ID  - Hasan2026
ER  -