Authors : Maheshwari D.; Prakash O. Sarangamath; Dr. Girish Kumar D.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

---

Google Scholar : https://tinyurl.com/mpfc9yw3

Scribd : https://tinyurl.com/4rt5ydv2

DOI : https://doi.org/10.38124/ijisrt/26apr2157

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : Accurate interpretation of chest X-ray images is essential for early detection of pulmonary diseases such as pneumonia, COVID-19, and tuberculosis. However, manual diagnosis is time-consuming and dependent on expert radiological knowledge, which may not be consistently available in all healthcare environment. This paper presents PulmoLens, an explainable artificial intelligence framework that leverages a Convolutional Neural Network(CNN) for automated chest disease classification while integrating Gradient-weighted Class Activation Mapping(Grad-CAM) to provide visual explanations for model predictions. The system enhances clinical trust by highlighting disease-relevant regions in X-ray images and supports multilingual interpretation of diagnostic results and medical reports.

Keywords : Chest X-ray Analysis, Grad-CAM, Deep Learning, DenseNet, Medical Imaging, Multilingual Diagnosis, Explainable AI.

References :

1. J. Li, L. Chen, and Y. Zhao, “Vision Transformer and CNN Hybrid System for Chest X-Ray Analysis,” IEEE Trans. on Artificial Intelligence, vol. 5, pp. 770–781, 2025.
2. S. Park, J. Lee, and H. Kim, “Transformer Based Explainable AI for Multi-Label Chest X-Ray Interpretation,” IEEE J. Biomedical and Health Informatics, vol. 29, pp. 1254–1264, 2025.
3. C. S. Silva et al., “Explainability and Model Reliability Assessment in Deep Learning Medical Imaging,” IEEE Trans. on AI in Healthcare, vol. 4, pp. 399–411, 2025
4. A. C. Gonçalves, F. Silva, and J. S. Cardoso, “Explainable AI in Medical Imaging: A Systematic Review of X-ray and MRI Interpretation,” IEEE Trans. on Medical Imaging, vol. 42, pp. 1123–1138, 2024. S. Mondal and A. Bhattacharya, “Multilingual Deep Learning for Medical Report Generation,” IEEE Trans. on Neural Networks and Learning Systems, vol. 35, pp. 4795– 4808, 2024.
5. T. Nguyen et al., “Improving Chest X-Ray Disease Classification with Multi-View Feature Attention Networks,” IEEE Trans. on Medical Imaging, vol. 42, pp. 2568–2578, 2024.
6. M. Al-Qahtani and A. A. Alhejji, “Benchmarking Deep Neural Network Architectures for Chest X-Ray Classification,” IEEE Access, vol. 12, pp. 10576–10589, 2024.
7. D. Zhou et al., “Multilingual Transformer Models for Clinical Text Translation,” Proc. of the ACL Anthology, pp. 982–997, 2024.
8. X. Chen et al., “COVID-19 Identification in Chest X- Rays with Multi-Scale Convolutional Neural Networks and Transfer Learning,” IEEE J. Biomedical and Health Informatics, vol. 27, pp. 5685–5694, 2023.
9. Y. Zhang, Z. Yang, and P. Ren, “DenseNet Variants for Large-Scale Chest X-Ray Classification,” IEEE Access, vol. 11, pp. 39210–39225, 2023.
10. K. Patel and M. Das, “Contrastive Learning for COVID-and Pneumonia Detection on CXR,” Int. Journal of Computer Assisted Radiology & Surgery, vol. 18, pp. 605– 618, 2023.
11. A. Raj et al., “Explainable Chest X-Ray AI Models Using Ensemble Deep Learning Techniques,” IEEE/ACM Trans. on Computational Biology and Bioinformatics, vol. 20, pp. 3311–3322, 2023.
12. E. A. Ibraheem et al., “Self-Attention Guided DenseNet for Pneumothorax and Tuberculosis Detection,” IEEE Access, vol. 11, pp. 60322–60338, 2023.
13. M. Gupta et al., “Attention Guided Grad-CAM Fusion Based Explainability for Pneumonia Detection,” Computer Methods and Programs in Biomedicine, vol. 227, no. 107232, 2022.
14. H. Gupta et al., “Automated Chest X-Ray Diagnostics Using Self-Supervised Learning,” Medical Image Analysis, vol. 75, pp. 102259, 2022.