Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/451A65F7-4C25-41BD-B673-C3468779A107 | ||
| Year | 2025 | ||
| Type of Item | Diploma Work | ||
| License |
|
||
| Bibliographic Citation | Chrysostomos Ioannou, "Creation of a platform for processing magnetic resonance imaging (MRI) images from patients with multiple sclerosis", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2025 https://doi.org/10.26233/heallink.tuc.103646 | ||
| Appears in Collections |
Multiple sclerosis is an autoimmune disease that disrupts communication between the central nervous system and the body, leading to symptoms like seizures, paresthesias, loss of balance, vision problems, and motor issues. Magnetic resonance imaging (MRI) is used to monitor patients' brains and identify plaques, which can increase their disability. This thesis presents a modular software system for handling MRI data on multiple sclerosis, which can be administered, visualized, annotated, and preprocessed using PyQt5-based tools. The platform supports deep learning-based segmentation, allowing for pixel-wise segmentation of lesions through automatic analysis leveraging a U-Net convolutional neural network. Moreover, manual segmentation is supported in this platform. Modern loss functions and class weighting divide the dataset into training, validation, and testing subsets to maximize model performance and guarantee objective evaluation. The dual-pathway architecture makes lesion detection effective, enabling the gathering and evaluation of high-quality neuroimaging datasets for MS research and treatment.
Copyright © DIAS 2013
