CAXNet: Coordinate Attention-Enhanced ResNeXt with Multi-Level Feature Fusion for Multiclass Chest X-Ray Classification | IJCT Volume 13 – Issue 3 | IJCT-V13I3P118
International Journal of Computer Techniques
ISSN 2394-2231
Author
Akshay Mool, Ashutosh Pandey, Rahul Kumar, Ankit Yadav
Abstract
Rapid and reliable COVID-19 detection from chest X-rays can aid clinical screening and radiologists’ decisions. Due to overlapping radiographic features in COVID-19, lung opacity, viral pneumonia, and normal chest X-rays, multiclass categorization is difficult. This study offers CAXNet, a Coordinate Attention-enhanced ResNeXt COVID-19 chest X-ray classification model. This architecture enhances ResNeXt50-32x4d by preserving early and intermediate residual stages and incorporating Coordinate Attention modules for improved spatial feature representations. Before categorization, attention-enhanced low- and intermediate-level characteristics are fused using multi-level feature fusion. The model was tested using the COVID-19 Radiography Database for four-class classification: disease, lung opacity, normal, and viral pneumonia. The experimental findings demonstrate that CAXNet exhibited 92.00\% accuracy, 92.15\% precision, 92.00\% recall, 92.00\% F1-score, 0.8852 Matthews Correlation Coefficient, and 0.9329 ROC-AUC on the test set. The confusion matrix and t-SNE-based feature visualization show that the proposed model learns discriminative representations, notably for COVID-19 and Viral Pneumonia. The results show that coordinate-aware attention and multi-level feature fusion enhance ResNeXt-based chest X-ray image classification models.
Keywords
COVID-19 classification; chest X-ray; deep learning; ResNeXt; Coordinate Attention; feature fusion; medical image classification
Conclusion
This paper introduces CAXNet, a Coordinate Attention-enhanced ResNeXt architecture for multiclass COVID-19 chest X-ray classification. The model alters the ResNeXt50-32×4d backbone by preserving just early and intermediate phases. After the retained residual stages, coordinate Attention modules augment spatially informative feature maps, and a multi-level feature fusion technique combines attention-enhanced low- and intermediate-level representations before classification.
The model was tested on a four-class chest X-ray classification task involving COVID-19, lung opacity, normal, and viral pneumonia. CAXNet has an overall test accuracy of 92.00%, weighted precision of 92.15%, recall of 92.00%, F1-score of 92.05%, MCC of 0.8852, and ROC-AUC of 0.9329. Results show that the suggested architecture can learn radiographic representations effectively and discriminatively.
The confusion matrix analysis indicated that the model accurately classified 240 of 250 COVID-19 images and 86 of 88 Viral Pneumonia images. The biggest categorization issue was Lung Opacity and Normal patients, where radiographic overlap caused misclassification. T-SNE showed moderately separable feature clusters for most classes and partial overlap between Lung Opacity and Normal samples, supporting this conclusion.
The results show that COVID-19 chest X-ray classification works using a compact ResNeXt-based feature extractor, Coordinate Attention-based feature refining, and multi-level feature fusion. Stratified data splitting, bigger and more diverse datasets, lung-region segmentation, external validation, and explainability approaches like Grad-CAM to further evaluate the model’s decision-making areas can increase CAXNet’s performance.
References
[1]E. F. Ohata, G. M. Bezerra, J. V. S. Chagas, A. V. L. Neto, A. B. Albuquerque, V. H. C. de Albuquerque, and P. P. R. Filho, “Automatic detection of COVID-19 infection using chest X-ray images through transfer learning,” IEEE/CAA Journal of Automatica Sinica, vol. 8, no. 1,
pp. 239–248, 2021.
[2]A. I. Khan, J. L. Shah, and M. M. Bhat, “CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest X-ray images,” Computer Methods and Programs in Biomedicine, vol. 196, p. 105581, 2020.
[3]T. Mahmud, M. A. Rahman, and S. A. Fattah, “CovXNet: A multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images with transferable multi-receptive feature optimization,” Computers in Biology and Medicine, vol. 122, p. 103869, 2020.
[4]A. Abbas, M. M. Abdelsamea, and M. M. Gaber, “Classification of COVID-
19 in chest X-ray images using DeTraC deep convolutional neural network,” Applied Intelligence, vol. 51, no. 2, pp. 854–864, 2021.
[5]R. Jain, M. Gupta, S. Taneja, and D. J. Hemanth, “Deep learning based detection and analysis of COVID-19 on chest X-ray images,” Applied Intelligence, vol. 51, pp. 1690–1700, 2021.
[6]T. Rahman, A. Khandakar, Y. Qiblawey, A. Tahir, S. Kiranyaz, S. B. A. Kashem, M. T. Islam, S. Al Maadeed, S. M. Zughaier, M. S. Khan, and
M. E. H. Chowdhury, “Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images,” Computers in Biology and Medicine, vol. 132, p. 104319, 2021.
[7]L. Kong and J. Cheng, “Classification and detection of COVID-19 X-ray images based on DenseNet and VGG16 feature fusion,” Biomedical Signal Processing and Control, vol. 77, p. 103772, 2022.
[8]M. Bhandari, T. B. Shahi, B. Siku, and A. Neupane, “Explanatory classification of CXR images into COVID-19, pneumonia and tuberculosis using deep learning and XAI,” Computers in Biology and Medicine, vol. 150, p. 106156, 2022.
[9]T. D. Pham, “Classification of COVID-19 chest X-rays with deep learning: New models or fine tuning?” Health Information Science and Systems, vol. 9, Art. no. 2, 2021.
B. Oltu, S. Guney, S. E. Yuksel, and B. Dengiz, “Automated classification of chest X-rays: A deep learning approach with attention mechanisms,” BMC Medical Imaging, vol. 25, p. 71, 2025.
How to Cite This Paper
Akshay Mool, Ashutosh Pandey, Rahul Kumar, Ankit Yadav (2026). CAXNet: Coordinate Attention-Enhanced ResNeXt with Multi-Level Feature Fusion for Multiclass Chest X-Ray Classification. International Journal of Computer Techniques, 13(3). ISSN: 2394-2231.
CAXNet Coordinate Attention-Enhanced ResNeXt with Multi-Level Feature Fusion for Multiclass Chest X-Ray ClassificationDownload
Related Posts:
