Cerebrovascular Segmentation Architecture With Channel Attention And Spatial Kernel Filtering For Tof-Mra Images
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 ves...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/63021/ http://eprints.usm.my/63021/1/Pages%20from%20MD%20RAIHAN%20GONI%20-%20TESIS.pdf |
| Summary: | 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. |
|---|