Gilani Mohamed, Mohamed Ahmed (2022) Development of hippocampus MRI image segmentation algorithm for progression detection of alzheimer’s disease (AD). Masters thesis, Universiti Tun Hussein Malaysia.
|
Text
24p MOHAMED AHMED GILANI MOHAMED.pdf Download (611kB) | Preview |
|
![[img]](http://eprints.uthm.edu.my/style/images/fileicons/text.png) |
Text (Copyright Declaration)
MOHAMED AHMED GILANI MOHAMED COPYRIGHT DECLARATION.pdf Restricted to Repository staff only Download (434kB) | Request a copy |
|
|
Text (Full Text)
MOHAMED AHMED GILANI MOHAMED WATERMARK.pdf Restricted to Registered users only Download (12MB) | Request a copy |
Abstract
Alzheimer's disease is becoming one of the most serious ailments that people face. Alzheimer's disease primarily affects those over the age of 65. is defined by the death of brain cells, which results in memory loss. as well as a lack of judgment, linguistic abilities, and decision-making capability Furthermore, no research has been conducted on developing a monitoring system for Alzheimer's disease that can continuously monitor Alzheimer's patients to identify any signs of development. Current research focuses mostly on early diagnosis and does not include disease monitoring. Monitoring is critical since it allows doctors to assess the disease development of Alzheimer's patients quantitatively. This study indicates developing an algorithm for detecting and progressing through the hippocampus of patients with Alzheimer's disease in MRI images. The active contour method (Chan-Vese) was utilized to extract the ROI parameters (hippocampus). The active contours algorithm deforms an item's initial border in an image to latch onto typical features inside the region of interest given an approximation of the object's perimeter. This is constantly stretched until it reaches the ROI's boundary. The interactive area selection approach is used to allow the user to determine the ROI depending on their needs. The algorithm will be applied once the ROI has been specified. The algorithm will be able to identify the parameters, such as the number of pixels, area pixels, and mean value, by extracting the hippocampal shape. The extraction of parameters will allow us to determine the extent of the patient's Alzheimer's progression. As a result, the study was successful in developing a semi-automated and robust model based on the Chan-Vese segmentation methodology, where it could observe the shrinking of the patient brain by the progression method using the total pixels of the hippocampus and its area by getting decreased at the second visit, one of the results showed at the first visit the total number of the pixels was 707 then at the second visit it shows 650 so the progression percentage 9%, and the proposed method produced promising segmentation results. In addition, a graphical user interface (GUI) was created to identify the progression percentage. As a future plan, this project can use machine learning to train the data for auto-detection for the hippocampus which will be significantly robust and more effective.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | R Medicine > R Medicine (General) > R858-859.7 Computer applications to medicine. Medical informatics |
| Divisions: | Faculty of Electrical and Electronic Engineering > Department of Electrical Engineering |
| Depositing User: | Mrs. Sabarina Che Mat |
| Date Deposited: | 24 Apr 2022 00:49 |
| Last Modified: | 24 Apr 2022 00:49 |
| URI: | http://eprints.uthm.edu.my/id/eprint/6981 |
Actions (login required)
 |
View Item |