A Dual-Stream Centerline-Guided Network for Segmentation of the Common and Internal Carotid Arteries From 3D Ultrasound Images

Segmentation of the carotid section encompassing the common carotid artery (CCA), the bifurcation and the internal carotid artery (ICA) from three-dimensional ultrasound (3DUS) is required to measure the vessel wall volume (VWV) and localized vessel-wall-plus-plaque thickness (VWT), shown to be sensitive to treatment effect. We proposed an approach to combine a centerline extraction network (CHG-Net) and a dual-stream centerline-guided network (DSCG-Net) to segment the lumen-intima (LIB) and media-adventitia boundaries (MAB) from 3DUS images. Correct arterial location is essential for successful segmentation of the carotid section encompassing the bifurcation. We addressed this challenge by using the arterial centerline to enhance the localization accuracy of the segmentation network. The CHG-Net was developed to generate a heatmap indicating high probability regions for the centerline location, which was then integrated with the 3DUS image by the DSCG-Net to generate the MAB and LIB. The DSCG-Net includes a scale-based and a spatial attention mechanism to fuse multi-level features extracted by the encoder, and a centerline heatmap reconstruction side-branch connected to the end of the encoder to increase the generalization ability of the network. Experiments involving 224 3DUS volumes produce a Dice similarity coefficient (DSC) of 95.8 +/- 1.9% and 92.3 +/- 5.4% for CCA MAB and LIB, respectively, and 93.2 +/- 4.4% and 89.0 +/- 10.0% for ICA MAB and LIB, respectively. Our approach outperformed four state-of-theart 3D CNN models, even after their performances were boosted by centerline guidance. The efficiency afforded by the framework would allow it to be incorporated into the clinical workflow for improved quantification of plaque change.

Automated summary

This study proposes an approach that combines a centerline extraction network and a dual-stream centerline-guided network for segmenting the carotid section from 3D ultrasound images. By utilizing the arterial centerline, the segmentation network achieves improved accuracy in segmenting the vessel wall and plaque boundaries. Experimental results demonstrate that the proposed approach outperforms other methods and has the potential to be integrated into clinical workflows.