Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sadikine, Amine, Badic, Bogdan, Tasu, Jean-Pierre, Noblet, Vincent, Ballet, Pascal, Visvikis, Dimitris, Conze, Pierre-Henri
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912034008858624
author Sadikine, Amine
Badic, Bogdan
Tasu, Jean-Pierre
Noblet, Vincent
Ballet, Pascal
Visvikis, Dimitris
Conze, Pierre-Henri
author_facet Sadikine, Amine
Badic, Bogdan
Tasu, Jean-Pierre
Noblet, Vincent
Ballet, Pascal
Visvikis, Dimitris
Conze, Pierre-Henri
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12333
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
Sadikine, Amine
Badic, Bogdan
Tasu, Jean-Pierre
Noblet, Vincent
Ballet, Pascal
Visvikis, Dimitris
Conze, Pierre-Henri
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
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.
title Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2409.12333