Cascaded multitask U-Net using topological loss for vessel segmentation and centerline extraction

TL;DR

This paper introduces a cascaded U-Net framework that directly predicts vessel segmentation and centerlines using a topological loss, improving 3D vascular network analysis in medical imaging.

Contribution

It replaces the soft-skeleton algorithm with a U-Net for skeleton extraction and integrates it into a cascaded model trained with clDice loss for better topology preservation.

Findings

More accurate vessel skeletons in 3D images

Enhanced topology-aware vessel segmentation and centerline extraction

Improved performance over traditional soft-skeleton methods

Abstract

Vessel segmentation and centerline extraction are two crucial preliminary tasks for many computer-aided diagnosis tools dealing with vascular diseases. Recently, deep-learning based methods have been widely applied to these tasks. However, classic deep-learning approaches struggle to capture the complex geometry and specific topology of vascular networks, which is of the utmost importance in most applications. To overcome these limitations, the clDice loss, a topological loss that focuses on the vessel centerlines, has been recently proposed. This loss requires computing, with a proposed soft-skeleton algorithm, the skeletons of both the ground truth and the predicted segmentation. However, the soft-skeleton algorithm provides suboptimal results on 3D images, which makes the clDice hardly suitable on 3D images. In this paper, we propose to replace the soft-skeleton algorithm by a U-Net which computes the vascular skeleton directly from the segmentation. We show that our method provides more accurate skeletons than the soft-skeleton algorithm. We then build upon this network a cascaded U-Net trained with the clDice loss to embed topological constraints during the segmentation. The resulting model is able to predict both the vessel segmentation and centerlines with a more accurate topology.