Year: 2025
Type: article
Abstract: The Brain Stroke Detection System utilizes deep learning to enhance stroke diagnosis accuracy from CT images. Developed in Python with Flask as the web framework, the system features an intuitive user interface using HTML, CSS, and JavaScript for medical professionals. Two deep learning models—Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM)—analyze CT images. The CNN, known for its powerful image processing capabilities, achieves training accuracy and validation accuracy, demonstrating robust stroke detection. The LSTM model, effective in handling sequential data, attains high training and validation accuracy, providing additional insights to improve detection reliability. The dataset consists of CT images, including normal and stroke-affected images, ensuring model generalizability and reducing overfitting risks. The integration of these models results in a highly accurate, scalable, and clinically applicable detection system. This project highlights the potential of deep learning in medical diagnostics, offering a tool that aids healthcare professionals in timely and precise stroke detection, ultimately improving patient outcomes.
Authors: SHANJANA J, SAKTHINI G, PARIMALA S, KALAIVANI V
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4410029772