International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI-Based Medical Image Disease Detection System |
|---|---|
| ABSTRACT | Medical imaging plays a vital part in disease diagnosis, but interpreting chest X-ray images accurately and on time remains difficult due to the shortage of skilled radiologists in many areas. This study proposes an AI-based medical imaging system capable of automatically detect multiple diseases, including cardiomegaly (CMVD), cardiac conditions, and rickets, chest x-ray. The system uses deep-learning model built on DenseNet121, applying transfer learning to improve the effectiveness of feature extraction and classification. To produce the predictions more understandable and trustworthy, the model incorporates Grad-CAM, which visually highlights the important regions in the X-ray that influence the decision. The answer is used as a Flask-based online application that enables people to submit pictures and get instant diagnostic results. Experimental results indicate that the system is capable of effectively identify disease patterns while maintaining efficient processing speed. Overall, The suggested system acts as a supportive tool for medical practitioners by enabling faster screening, improving access to diagnosis, and reducing reliance on expensive medical procedures, especially in resource-limited settings. |
| AUTHOR | SOMASHEKAR N S, POOJA TARAGAR PG Student, Dept. of MCA, City Engineering College, Bangaluru, India Assisstant Professor, Dept. of MCA, City Engineering College, Bangaluru, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405053 |
| pdf/53_AI-Based Medical Image Disease Detection System.pdf | |
| KEYWORDS | |
| References | 1. "CheXNet: Radiologist-Level Identification of Pneumonia Deep Learning for Chest X-Rays," Pranav Rajpurkar et al., Stanford University, 2017. 2. NIH ChestX-ray14 Dataset, “Chest X-ray Dataset,” The National Institutes of Health, Available: 3. "ChestX-ray8: Hospital-Scale Database of Chest X-rays and Benchmarks," IEEE CVPR, 2017. Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. 4. Selvaraju, R. R. et al., “Grad-CAM: Deep Network-Based Visual Explanations via Gradient-Based Localization “The International Journal of Computer Vision” (IJCV), 2020. 5. Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q., “Densely Connected Convolutional Networks,” IEEE CVPR, 2017. 6. Paszke, A. et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” NeurIPS, 2019. 7. Flask Documentation, Available: https://flask.palletsprojects.com/ 8. VinBigData Chest X-ray Abnormalities Detection Dataset, 9. Bradski, G., “The OpenCV Library,” Dr. Dobb’s Journal of Software Tools, 2000. 10. G. Litjens et al.,"A Survey on Deep Learning for Analysing Medical Images," Medical Image Analysis, 2017. 11. "CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison," J. Irvin et al., AAAI Conference, 2019. 12. Johnson, A. E. W. and associates “MIMIC-CXR: A Large Publicly Available Database of Labelled Chest Radiographs,” Scientific Data, 2019. |
