IRO Journals
Journal of Artificial Intelligence and Capsule Networks

An Integrated Deep Learning Approach for Chest X-Ray Abnormality Recognition and Automated Radiological Report Synthesis

Open Access
Published: 14 October, 2026
Pages: 346-360
  • Haragopal V.P. , Haragopal V.P.
    Assistant professor, Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, India
    Assistant professor, Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, India
  • Shaik Munna , Shaik Munna
    Student, Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, India
    Student, Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, India
  • Penujuvi Sandeep , Penujuvi Sandeep
    Student, Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, India
    Student, Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, India
  • Thummaluru Soumith Reddy Thummaluru Soumith Reddy
    Student, Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, India
    Student, Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, India
view PDF
view PDF

How to Cite

V.P., Haragopal, Shaik Munna, Penujuvi Sandeep, and Thummaluru Soumith Reddy. 2026. “An Integrated Deep Learning Approach for Chest X-Ray Abnormality Recognition and Automated Radiological Report Synthesis”. Journal of Artificial Intelligence and Capsule Networks 8 (4): 346-60. https://doi.org/10.36548/jaicn.2026.4.004.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Chest Radiography
Thoracic Abnormality Classification
Vision-Language Modeling
Multimodal Report Generation
Hierarchical Visual Representation
Explainable Artificial Intelligence
Radiological Text Synthesis

Abstract

Chest X-ray (CXR) interpretation and radiology report creation depend on efficient feature extraction and report creation in medical terms. This research work proposes a multimodal AI framework for the automatic analysis of CXRs, which includes deep learning techniques to represent visual data, vision-language models, generate reports, and interpretability via Grad-CAM. For chest abnormality classification, this study uses visual deep neural network architectures as Swin Transformer, ConvNeXt, EfficientNet, and ResNet. This research utilizes ViT+BART, ViT+GPT-2, Swin+BART, and Swin+GPT-2 for the input image to generate report. The performance of visual classifiers is measured in Accuracy, Precision, Recall, and Macro F1-score. The generated reports are evaluated by BLEU, ROUGE-1, ROUGE-2, ROUGE-L, and BERT-F1. Swin Transformer achieved an accuracy of 0.77, while ViT+BART achieved BLEU, ROUGE-1, ROUGE-2, ROUGE-L, and BERT-F1 scores of 0.13, 0.42, 0.17, 0.33, and 0.89 respectively

References

  1. Sandi, Gitarja, and Suhono Harso Supangkat. "Automated AI-Driven Report Generation for Chest X-Ray Interpretation in Teleradiology: Towards Enhanced Personalized Healthcare." In 2025 International Conference on ICT for Smart Society (ICISS), IEEE, 2025, 1-5.
  2. Singh, Prateek, and Sudhakar Singh. "Chestx-Transcribe: A Multimodal Transformer for Automated Radiology Report Generation from Chest X-Rays." Frontiers in Digital Health, 2025, vol. 7: 1535168
  3. Fahmy, Ahmed Maged, and Manar Mahmoud El Mashaad. "Automated X-Ray Chest Report Generation." In 2025 Twelfth International Conference on Intelligent Computing and Information Systems (ICICIS), IEEE, 2025, 651-658.
  4. Jeong, Won Gi, Eui Jin Hwang, Gong Yong Jin, Ju-Hyung Lee, Se Ri Kang, Hongseok Ko, Bomi Gil et al. "Artificial Intelligence-Driven Drafting of Chest X-Ray Reports: 2025 Position Statement from The Korean Society of Thoracic Radiology Based on an Expert Survey." Korean Journal of Radiology, 2025, vol. 26, no. 11: 1100.
  5. Zhang, Xiaoman, Julian Nicolas Acosta, Xiaoli Yang, Subathra Adithan, Luyang Luo, Hong-Yu Zhou, Joshua Miller et al. "Automated Chest X-Ray Report Generation Remains Unsolved." In Biocomputing: Proceedings of the Pacific Symposium, 2025, 236-250.
  6. De Castro, Daniel Coelho, Aurelia Bustos, Shruthi Bannur, Stephanie L. Hyland, Kenza Bouzid, Maria Teodora Wetscherek, Maria Dolores Sánchez-Valverde et al. "Padchest-Gr: A Bilingual Chest X-Ray Dataset for Grounded Radiology Report Generation." The New England Journal of Medicine, 2025, vol. 2, no. 7: AIdbp2401120.
  7. Bai, Yaowei, Ruiheng Zhang, Yu Lei, Jingfeng Yao, Shuguang Ju, Chaoyang Wang, Wei Yao et al. "From Bench to Bedside: A Deepseek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice." arXiv preprint, 2025, arXiv:2507.19493.
  8. Aurangzeb, Brekhna, Dennis Robert, Cynthia Baard, Abid Ali Qureshi, Aneela Shaheen, Atiqa Ambreen, David McFarlane et al. "Evaluating The Accuracy of Artificial Intelligence-Powered Chest X-Ray Diagnosis for Paediatric Pulmonary Tuberculosis (EVAL-PAEDTBAID): Study Protocol for A Multi-Centre Diagnostic Accuracy Study." BMJ Open, 2025, vol. 15, no. 7: e105881.
  9. Saleh, Ahmed, Ahmed Mohamed Sied, Rahma Gharib, Alaa Elsaid, Ahmed Mabrouk, and Hoda Atef Elbatrawy. "AI-Driven Intelligent Medical System: Deep Learning for Chest X-Ray/CT Disease Recognition." Damanhour Journal of Intelligent Systems and Informatics, 2025, vol. 1, no. 1.
  10. Edirisinghe, Dasith, Wimukthi Nimalsiri, Mahela Hennayake, Dulani Meedeniya, and Gilbert Lim. "Chest X-Ray Report Generation using Abnormality Guided Vision Language Model." IEEE Access, 2025, vol. 13: 157651-157673.
  11. Fetiler, Bengü, Ömer Atılım Koca, and Volkan Kılıç. "Report Generation From X-Ray Images: an Evaluation with Transformer Architectures." Artificial Intelligence Theory and Applications,2025, vol. 5, no. 2: 1-10.
  12. Akbar, Wajahat, Shuguang Li, Abdullah Soomro, Altaf Hussain, Razaz Waheeb Attar, Tariq Hussain, Amal Hassan Alhazmi, and Reem Alsagri. "Trahealrg: Transformative Healthcare Leveraging Lstm and Gru Models Toward Improved Accuracy for Chest X-Ray Report Generation." International Journal of Pattern Recognition and Artificial Intelligence, 2025, vol. 39, no. 15: 2540005.
  13. Yoon, Sung-Hyun, Jihang Kim, Junghoon Kim, Jong-Hyuk Lee, Ilwoong Choi, Choul-Woo Shin, and Chang-Min Park. "Improving Image Quality of Chest Radiography with Artificial Intelligence-Supported Dual-Energy X-Ray Imaging System: An Observer Preference Study in Healthy Volunteers." Journal of Clinical Medicine, 2025, vol. 14, no. 6: 2091.
  14. Sharma, Harshita, Maxwell C. Reynolds, Valentina Salvatelli, Anne-Marie G. Sykes, Kelly K. Horst, Anton Schwaighofer, Maximilian Ilse et al. "Closing The Performance Gap Between AI and Radiologists in Chest X-Ray Reporting." arXiv preprint, 2025, arXiv:2511.21735.
  15. Wang, Xiao, Fuling Wang, Yuehang Li, Qingchuan Ma, Shiao Wang, Bo Jiang, and Jin Tang. "Cxpmrg-Bench: Pre-Training and Benchmarking for X-Ray Medical Report Generation on Chexpert Plus Dataset." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2025, 5123-5133.
  16. Ali, Haider, Rashadul Islam Sumon, Abdul Rehman Khalid, Kounen Fathima, and Hee Cheol Kim. "A Semantic Evaluation Framework for Medical Report Generation using Large Language Models." Computers, Materials Continua, 2025, vol. 84, no. 3: 5445-5462.
  17. Zou, Jing, Qingqiu Li, Chenyu Lian, Lihao Liu, Xiaohan Yan, Shujun Wang, and Jing Qin. "Corbenchx: Large-Scale Chest X-Ray Error Dataset and Vision-Language Model Benchmark for Report Error Correction." arXiv preprint, 2025 arXiv:2505.12057.
  18. Ng, Chee, Liliang Sun, and Shaoqing Tang. "X-Ray-Cot: Interpretable Chest X-Ray Diagnosis with Vision-Language models Via Chain-Of-Thought Reasoning." arXiv preprint, 2025, arXiv:2508.12455.
  19. Yadav, Priti, and Anujkumarsinh Donvir. "Enhancing Medical Imaging Accessibility: An AI-Powered Automated Tactile and 3D-Printable X-Ray System." In IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC), IEEE, 2025, 00508-00515.
  20. Yang, Yan, Xiaoxing You, Ke Zhang, Zhenqi Fu, Xianyun Wang, Jiajun Ding, Jiamei Sun et al. "Spatio-Temporal and Retrieval-Augmented Modeling for Chest X-Ray Report Generation." IEEE Transactions on Medical Imaging, 2025, vol. 44, no. 7: 2892-2905.
  21. Zhao, Jian, Wei Yao, Lei Sun, Lijuan Shi, Zhejun Kuang, Changwu Wu, and Qiulei Han. "Automated Chest X-Ray Diagnosis Report Generation with Cross-Attention Mechanism." Applied Sciences, 2025, vol. 15, no. 1: 343.
  22. Thakur, Amit, and Nilamadhab Mishra. "AI-Driven Synthetic Data Generation using Conditional Gans to Mitigate Class Imbalance in COVID-19 X-Ray Imaging." In International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC), IEEE, 2025, 1-6.
  23. Mamdouh, Dima, Mariam Attia, Mohamed Osama, Nesma Mohamed, Abdelrahman Lotfy, Tamer Arafa, Essam A. Rashed, and Ghada Khoriba. "Advancements in Radiology Report Generation: A Comprehensive Analysis." Bioengineering, 2025, vol. 12, no. 7: 693.
  24. Yazdani, Elmira, Aryan Neizehbaz, Najme Karamzade-Ziarati, and Saeed Reza Kheradpisheh. "Explainable Artificial Intelligence for Pneumonia Classification: Clinical Insights into Deformable Prototypical Part Network in Pediatric Chest X-Ray Images." Journal of Medical Imaging and Radiation Sciences, 2025, vol. 56, no. 5: 102023.
  25. Chen, Wenting, Yi Dong, Zhaojun Ding, Yucheng Shi, Yifan Zhou, Fang Zeng, Yijun Luo et al. "Radfabric: Agentic Ai System with Reasoning Capability for Radiology." arXiv preprint, 2025, arXiv:2506.14142.
  26. Raddar,“ChesXrays(IndianaUniversity),” KagglAvailable: https://www.kaggle.com/dataset/raddar/chest-xrays-indiana-university