Automatic Landmark-Based Segmentation of Human Subcortical Structures in MRI
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911683938615296 |
|---|---|
| author | Rekik, Ahmed Rushmore, R. Jarrett Bouix, Sylvain Marrakchi-Kacem, Linda |
| author_facet | Rekik, Ahmed Rushmore, R. Jarrett Bouix, Sylvain Marrakchi-Kacem, Linda |
| contents | Precise segmentation of brain structures in magnetic resonance imaging (MRI) is essential for reliable neuroimaging analysis, yet voxel-wise deep models often yield anatomically inconsistent results that diverge from expert-defined boundaries. In this research, we propose a landmark-guided 3D brain segmentation approach that explicitly mimics the manual segmentation protocol of the Harvard--Oxford Atlas. A Global-to-Local network automatically detects 16 landmarks representing key subcortical reference points. Then, a semantic segmentation model produces a coarse segmentation of 12 anatomical labels, each grouping multiple subcortical regions. Finally, a landmark-driven post-processing step separates these 12 labels into 26 distinct structures by enforcing local anatomical constraints. Experimental results demonstrate consistent improvements in boundary accuracy. Overall, integrating learned landmarks aligns segmentations more closely with manual protocols. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14221 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Automatic Landmark-Based Segmentation of Human Subcortical Structures in MRI Rekik, Ahmed Rushmore, R. Jarrett Bouix, Sylvain Marrakchi-Kacem, Linda Computer Vision and Pattern Recognition Precise segmentation of brain structures in magnetic resonance imaging (MRI) is essential for reliable neuroimaging analysis, yet voxel-wise deep models often yield anatomically inconsistent results that diverge from expert-defined boundaries. In this research, we propose a landmark-guided 3D brain segmentation approach that explicitly mimics the manual segmentation protocol of the Harvard--Oxford Atlas. A Global-to-Local network automatically detects 16 landmarks representing key subcortical reference points. Then, a semantic segmentation model produces a coarse segmentation of 12 anatomical labels, each grouping multiple subcortical regions. Finally, a landmark-driven post-processing step separates these 12 labels into 26 distinct structures by enforcing local anatomical constraints. Experimental results demonstrate consistent improvements in boundary accuracy. Overall, integrating learned landmarks aligns segmentations more closely with manual protocols. |
| title | Automatic Landmark-Based Segmentation of Human Subcortical Structures in MRI |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.14221 |