Segmentation of carotid vessel wall using U-Net and segmentation average network

TL;DR

This paper introduces a novel CNN architecture combining three U-Nets and a segmentation average network to improve carotid vessel wall segmentation accuracy in 3D ultrasound images, reducing manual effort and variability.

Contribution

The study proposes a new segmentation framework with three U-Nets and a segmentation average network that enhances segmentation performance over existing methods.

Findings

Improved Dice similarity coefficient from 64.8% to 67.5%.

Increased sensitivity from 63.8% to 70.5%.

Enhanced AUC from 0.89 to 0.94.

Abstract

Segmentation of carotid vessel wall is required in vessel wall volume (VWV) and local vessel-wall-plus-plaque thickness (VWT) quantification of the carotid artery. Manual segmentation of the vessel wall is time-consuming and prone to interobserver variability. In this paper, we proposed a convolution neural network to segment the common carotid artery (CCA) from 3D carotid ultrasound images. The proposed CNN involves three U-Nets that segmented the 3D ultrasound (3DUS) images in the axial, lateral and frontal orientations. The segmentation maps generated by three U-Nets were consolidated by a novel segmentation average network (SAN) we proposed in this paper. The experimental results show that the proposed CNN improved the Dice similarity coefficient (DSC) for vessel wall segmentation from 64.8% to 67.5%, the sensitivity from 63.8% to 70.5%, and the area under receiver operator characteristic curve (AUC) from 0.89 to 0.94.