Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation - Institut Brestois Santé Agro Matière Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

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

Résumé

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.
Fichier non déposé

Dates et versions

hal-03953223 , version 1 (23-01-2023)

Identifiants

Citer

Amine Sadikine, Bogdan Badic, Jean-Pierre Tasu, Vincent Noblet, Pascal Ballet, et al.. Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation. ISBI 2023: IEEE 20th International Symposium on Biomedical Imaging, Apr 2023, Cartagena de Indias, Colombia. ⟨10.1109/ISBI53787.2023.10230364⟩. ⟨hal-03953223⟩
94 Consultations
1 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More