arXiv：cs.AI· Amine Sadikine, Bogdan Badic, Jean-Pierre Tasu, Vincent Noblet, Pascal Ballet, Dimitris Visvikis, Pierre-Henri Conze·· 5 小时前
面向深度肝脏血管分割的尺度特定辅助多任务对比学习
Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
AI 导读
该论文提出一种深度监督的肝脏血管分割方法，通过新的聚类技术将血管树分解为从细小到粗大的多个尺度层级，并将标准 3D UNet 扩展为多任务学习框架，引入尺度特定辅助任务与对比学习以增强共享表征中的尺度区分度。在公开 3D-IRCADb 数据集上，多项评测指标均取得良好结果。
正文
Abstract:Extracting hepatic vessels from abdominal images is of high interest for clinicians since it allows to divide the liver into functionally-independent Couinaud segments. In this respect, an automated liver blood vessel extraction is widely summoned. Despite the significant growth in performance of semantic segmentation methodologies, preserving the complex multi-scale geometry of main vessels and ramifications remains a major challenge. This paper provides a new deep supervised approach for vessel segmentation, with a strong focus on representations arising from the different scales inherent to the vascular tree geometry. In particular, we propose a new clustering technique to decompose the tree into various scale levels, from tiny to large vessels. Then, we extend standard 3D UNet to multi-task learning by incorporating scale-specific auxiliary tasks and contrastive learning to encourage the discrimination between scales in the shared representation. Promising results, depicted in several evaluation metrics, are revealed on the public 3D-IRCADb dataset.
| Comments: | 5 pages, 5 figures, IEEE ISBI 2023. v2: fixed a figure reference. Code for the multi-scale vessel clustering (Sect. 2.1): this https URL |
| Subjects: | Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2409.12333 [eess.IV] |
| (or arXiv:2409.12333v2 [eess.IV] for this version) | |
| https://doi.org/10.48550/arXiv.2409.12333 arXiv-issued DOI via DataCite |
|
| Journal reference: | 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Cartagena, Colombia, 2023, pp. 1-5 |
| Related DOI: | https://doi.org/10.1109/ISBI53787.2023.10230364
DOI(s) linking to related resources |
Submission history
From: Amine Sadikine [view email]
[v1]
Wed, 18 Sep 2024 22:03:22 UTC (9,879 KB)
[v2]
Fri, 9 Oct 2026 20:17:59 UTC (6,246 KB)
来源：arXiv：cs.AI · arxiv.org