aiqbench analysis
This paper introduces a novel deep learning framework for hepatic vessel segmentation that leverages scale-specific auxiliary tasks and contrastive learning to better capture multi-scale vascular geometry. By extending the 3D UNet architecture with these techniques, the method improves discrimination between different vessel sizes on standard biomedical imaging datasets. The core contribution lies in advancing computer vision methodologies specifically tailored for complex medical image analysis rather than introducing new AI infrastructure or policy shifts.
Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
arXiv:2409.12333v2 Announce Type: replace-cross 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.
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.
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
Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2409.12333 [eess.IV]
(or arXiv:2409.12333v2 [eess.IV] for this version)
https://doi.org/10.48550/arXiv.2409.12333 Focus to learn more arXiv-issued DOI via DataCite
2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Cartagena, Colombia, 2023, pp. 1-5
https://doi.org/10.1109/ISBI53787.2023.10230364 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 302 words
Related coverage
[AINews] The Future of Latent Space
Latent Space · Sep 25, 2026
[AINews] Opus 5.5 is good at explainer videos
Latent Space · Sep 29, 2026
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · Sep 23, 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026