Brain stroke detection using medical images

Chew, Xin Ru (2025) Brain stroke detection using medical images. Final Year Project, UTAR.

Preview

PDF Download (9Mb) | Preview

Abstract

The main goal of the proposed project, "Brain Stroke Detection Using Medical Images," is to improve clot detection capabilities by analysing medical images, which will help patients and medical professionals as well. The goal of this project is to offer a complete solution that gives medical professionals the knowledge and resources they need to recognize brain strokes quickly and accurately. By combining machine learning algorithms with image processing techniques, the project introduces innovation and provides a fresh way to improve the diagnostic procedure. The technology application entails converting SWI-MRI scans from DICOM format to PNG. With a focus on feature extraction techniques, SVM the project seeks to provide a reliable brain clot detection system to assist medical professionals in their diagnostic pursuits. In order to enable automated brain clot detection and adapt to various image variations, machine learning algorithms are integrated for classification. A brain clot detection system is one of the project's outputs; it offers medical professionals automated image analysis, enabling prompt and precise diagnosis. The project aims to improve patient care by providing cutting-edge technology to healthcare professionals, enabling them to perform better neuroimaging diagnostics. This project contributes to improvements in patient outcomes and healthcare by putting cutting-edge technologies to use in the field of medical image analysis. Area of Study (Minimum 1 and Maximum 2): Medical Image Processing, Deep Learning Keywords (Minimum 5 and Maximum 10): Blood Clot Detection, Neurotechnology, AI Diagnostics, Medical Imaging, Machine Learning, Mobile Application

Actions (login required)