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

Simple item page
dc.contributor.authorGoni, Mohammad Raihan
dc.date.accessioned2025-10-21T08:51:27Z
dc.date.available2025-10-21T08:51:27Z
dc.date.issued2024-01
dc.description.abstractThis 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.
dc.identifier.urihttps://erepo.usm.my/handle/123456789/22872
dc.language.isoen
dc.subjectMagnetic resonance imaging
dc.subjectMIDAS (Computer system)
dc.titleCerebrovascular Segmentation Architecture With Channel Attention And Spatial Kernel Filtering For Tof-Mra Images
dc.typeResource Types::text::thesis::master thesis
dspace.entity.typePublication
oairecerif.author.affiliationUniversiti Sains Malaysia
Files
Collections
Pusat Pengajian Sains Komputer - Tesis