Learning Wall Segmentation in 3D Vessel Trees using Sparse Annotations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909572515495936 |
|---|---|
| author | Rahlfs, Hinrich Hüllebrand, Markus Schmitter, Sebastian Strecker, Christoph Harloff, Andreas Hennemuth, Anja |
| author_facet | Rahlfs, Hinrich Hüllebrand, Markus Schmitter, Sebastian Strecker, Christoph Harloff, Andreas Hennemuth, Anja |
| contents | We propose a novel approach that uses sparse annotations from clinical studies to train a 3D segmentation of the carotid artery wall. We use a centerline annotation to sample perpendicular cross-sections of the carotid artery and use an adversarial 2D network to segment them. These annotations are then transformed into 3D pseudo-labels for training of a 3D convolutional neural network, circumventing the creation of manual 3D masks. For pseudo-label creation in the bifurcation area we propose the use of cross-sections perpendicular to the bifurcation axis and show that this enhances segmentation performance. Different sampling distances had a lesser impact. The proposed method allows for efficient training of 3D segmentation, offering potential improvements in the assessment of carotid artery stenosis and allowing the extraction of 3D biomarkers such as plaque volume. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12801 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Wall Segmentation in 3D Vessel Trees using Sparse Annotations Rahlfs, Hinrich Hüllebrand, Markus Schmitter, Sebastian Strecker, Christoph Harloff, Andreas Hennemuth, Anja Computer Vision and Pattern Recognition I.2.1; I.4.6; J.3 We propose a novel approach that uses sparse annotations from clinical studies to train a 3D segmentation of the carotid artery wall. We use a centerline annotation to sample perpendicular cross-sections of the carotid artery and use an adversarial 2D network to segment them. These annotations are then transformed into 3D pseudo-labels for training of a 3D convolutional neural network, circumventing the creation of manual 3D masks. For pseudo-label creation in the bifurcation area we propose the use of cross-sections perpendicular to the bifurcation axis and show that this enhances segmentation performance. Different sampling distances had a lesser impact. The proposed method allows for efficient training of 3D segmentation, offering potential improvements in the assessment of carotid artery stenosis and allowing the extraction of 3D biomarkers such as plaque volume. |
| title | Learning Wall Segmentation in 3D Vessel Trees using Sparse Annotations |
| topic | Computer Vision and Pattern Recognition I.2.1; I.4.6; J.3 |
| url | https://arxiv.org/abs/2502.12801 |