|
Document Type |
: |
Thesis |
|
Document Title |
: |
CORPUS CALLOSUM RECOGNITION IN BRAIN MAGNETIC RESONANCE IMAGES التعرف على الجسم الثفني في صور الرنين المغناطيسي للدماغ |
|
Subject |
: |
Faculty of Computing and Information Technology |
|
Document Language |
: |
Arabic |
|
Abstract |
: |
A significant area of study in the field of neurological disorders is the Corpus Callosum (CC), and more specifically, anomalies of the CC. The development of technologies to assist doctors in longitudinal reviews becomes crucial and indispensable for the advancement of knowledge and care for these pathologies. When analyzing various neurological disorders, it is crucial to take into account the size and appearance of the CC in the midsagittal plane. A commissural fiber bundle in CC has a unique diffusion pattern that can be recorded as prior information in a segmentation framework. The segmentation of the Corpus Callosum plays a vital step in the identification of numerous brain illnesses using brain magnetic resonance images. Robust CC segmentation is critical for quantitative and qualitative analyses of CC in brain MR images. In this thesis, an attention U-net-based deep learning method for the semantic segmentation of the corpus callosum from brain Magnetic Resonance Imaging (MRI) scans is proposed and implemented. Most neurological analyses benefit greatly from the structural data that can be obtained from the segmentation of brain MRI images. The proposed technique has a revised attention network and a deep supervised encoder-decoder configuration. Slice by slice, the model analyzes an entire MRI image to determine the ideal mask for the corpus callosum. The model was trained using the ABIDE and OASIS datasets, and its performance was analyzed for different test samples using a standard measure of dice coefficient, yielding a dice accuracy of 97.8 percent. Visual samples of predicted CC from brain MRI are given and contrasted with the original ground truth to help understand how well the model performs. The findings demonstrate that the suggested approach is one of the best segmentation techniques, as it achieved very competitive CC segmentation performance even with a single model.
Key Word: attention U-net, corpus callosum, deep learning, dice coefficient, MRI, segmentation |
|
Supervisor |
: |
Dr Kawthar Moria |
|
Thesis Type |
: |
Master Thesis |
|
Publishing Year |
: |
1444 AH
2023 AD |
|
Added Date |
: |
Monday, June 5, 2023 |
|
Researchers
| مصباح خانم | Khanam, Missba | Researcher | Master | |
|