Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
This work addresses the problem of accurate liver vessel segmentation for clinicians, enabling division into Couinaud segments, but it appears incremental as it builds on existing methods like 3D UNet with multi-task and contrastive learning enhancements.
The paper tackled the challenge of preserving the complex multi-scale geometry in automated liver blood vessel segmentation by proposing a deep supervised approach that decomposes the vascular tree into scale levels and incorporates scale-specific auxiliary tasks and contrastive learning into a 3D UNet. Promising results were reported on the public 3D-IRCADb dataset, though no concrete numbers were provided.
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.