Early Detection of Alzheimer's Disease

Signal Processing, Programming

Published in IEEE journal

Tools Used : Matlab, openCV
In collabaration with Chetan Patil, Madhumitha Sridhara and Varun Nayak. Mentored by Dr. Sumam David

Alzheimer's disease (AD) is an irreversible and progressive brain disease that gradually destroys memory and thinking skills to an extent that it starts affecting the daily life. It has become the most common cause of dementia among older people. This project looks at utility of image processing on the Magnetic Resonance Imaging (MRI) scans to estimate the possibility of an early detection of AD.

comparision of MRI scans of patients with and without Alzheimer's Disease

Here we built a tool to look at two main indicators. The aim of the building the tool was to reduce the manual work for the doctors, thus the tool is very easy to use and one needs to do minimum pre-work before running the diagnostics on the tool.


Brain Atrophy

Here we looked at the total brain volume and the percentage of grey and white matter in it. This percentage helped us determine the possibility of AD. Here, the user of the tools simply has to point the program to the location of the MRI scans and the volume is calculated

screenshot of the software that was developed for users to enter patient details
black screen containing the brain volume output computed by the algorithm.

Hipocampal Volume

Here we looked at particularly the size of the hippocampus in the brain. This is as, in case of AD it is one of the first regions to get affected and thus shrink in size. In this case, the user will have to isolate the ROI (region of interest) where the hippocampus is present. On doing that, the software will pull out and highlight the hippocampus.




← Back to Home