Cerebrovascular Segmentation Architecture With Channel Attention And Spatial Kernel Filtering For Tof-Mra Images

Goni, Mohammad Raihan (2024) Cerebrovascular Segmentation Architecture With Channel Attention And Spatial Kernel Filtering For Tof-Mra Images. Masters thesis, Universiti Sains Malaysia.

[img] PDF
Download (470kB)

Abstract

This thesis introduces a deep learning approach to automatically segment cerebrovascular structures in magnetic resonance angiography (MRA) images. This study utilizes an approach that excels in segmenting the entire vessel structure while placing increased emphasis on accurately capturing small vessels (< 5 mm radius). The proposed method was evaluated on the MIDAS dataset, demonstrating its competitive performance with exceptional evaluation results.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > QA75.5-76.95 Electronic computers. Computer science
Divisions: Pusat Pengajian Sains Komputer (School of Computer Sciences) > Thesis
Depositing User: Mr Aizat Asmawi Abdul Rahim
Date Deposited: 21 Oct 2025 08:56
Last Modified: 21 Oct 2025 08:56
URI: http://eprints.usm.my/id/eprint/63021

Actions (login required)

View Item View Item
Share