Guardado en:
Detalles Bibliográficos
Autores principales: Lin, Xi, Zhao, Shixuan, Wei, Xinxu, Shmuel, Amir, Li, Yongjie
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2411.09567
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916480258408448
author Lin, Xi
Zhao, Shixuan
Wei, Xinxu
Shmuel, Amir
Li, Yongjie
author_facet Lin, Xi
Zhao, Shixuan
Wei, Xinxu
Shmuel, Amir
Li, Yongjie
contents 3D microscopic cerebrovascular images are characterized by their high resolution, presenting significant annotation challenges, large data volumes, and intricate variations in detail. Together, these factors make achieving high-quality, efficient whole-brain segmentation particularly demanding. In this paper, we propose a novel Vessel-Pattern-Based Semi-Supervised Distillation pipeline (VpbSD) to address the challenges of 3D microscopic cerebrovascular segmentation. This pipeline initially constructs a vessel-pattern codebook that captures diverse vascular structures from unlabeled data during the teacher model's pretraining phase. In the knowledge distillation stage, the codebook facilitates the transfer of rich knowledge from a heterogeneous teacher model to a student model, while the semi-supervised approach further enhances the student model's exposure to diverse learning samples. Experimental results on real-world data, including comparisons with state-of-the-art methods and ablation studies, demonstrate that our pipeline and its individual components effectively address the challenges inherent in microscopic cerebrovascular segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09567
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VPBSD:Vessel-Pattern-Based Semi-Supervised Distillation for Efficient 3D Microscopic Cerebrovascular Segmentation
Lin, Xi
Zhao, Shixuan
Wei, Xinxu
Shmuel, Amir
Li, Yongjie
Computer Vision and Pattern Recognition
3D microscopic cerebrovascular images are characterized by their high resolution, presenting significant annotation challenges, large data volumes, and intricate variations in detail. Together, these factors make achieving high-quality, efficient whole-brain segmentation particularly demanding. In this paper, we propose a novel Vessel-Pattern-Based Semi-Supervised Distillation pipeline (VpbSD) to address the challenges of 3D microscopic cerebrovascular segmentation. This pipeline initially constructs a vessel-pattern codebook that captures diverse vascular structures from unlabeled data during the teacher model's pretraining phase. In the knowledge distillation stage, the codebook facilitates the transfer of rich knowledge from a heterogeneous teacher model to a student model, while the semi-supervised approach further enhances the student model's exposure to diverse learning samples. Experimental results on real-world data, including comparisons with state-of-the-art methods and ablation studies, demonstrate that our pipeline and its individual components effectively address the challenges inherent in microscopic cerebrovascular segmentation.
title VPBSD:Vessel-Pattern-Based Semi-Supervised Distillation for Efficient 3D Microscopic Cerebrovascular Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.09567