| Medical Report Generation for Chest X Ray using CNN and LSTM | |
|
MSRDG International Journal of Computer Scientific Technology & Electronics Engineering
© 2025 by MSRDG IJCSTEE Journal Volume 1 Issue 5 Year of Publication: 2025 |
Paper Download Article ID MSRDG-IJCSTEE-V1I5P101 |
|
Abstract: Chest X-ray interpretation remains one of the most critical yet challenging tasks in clinical radiology, requiring both precision and significant expertise. Manual analysis is often time-intensive and prone to variability based on human judgment. To overcome these limitations, this study proposes an automated framework for generating medical diagnostic reports from chest X-ray images using a deep learning approach that combines Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The CNN component is responsible for extracting rich visual and spatial features from the input X-ray images, while the LSTM network sequentially generates descriptive textual reports, thereby bridging the gap between visual understanding and language generation. Extensive preprocessing, including image enhancement and normalization, is applied to improve feature extraction. The system is trained and evaluated using publicly available datasets, demonstrating strong performance in producing clinically accurate and coherent reports that align with radiologist interpretations. The proposed model significantly reduces report generation time while maintaining high diagnostic quality, offering a scalable solution for deployment in medical imaging workflows |
|
| Keywords: Chest X-ray, Medical Report Generation, Deep Learning, Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Medical Image Analysis, Radiology Report Automation, Natural Language Processing (NLP), Image Preprocessing, Clinical Decision Support | |
