GAPNet: Granularity Attention Network with Anatomy-Prior-Constraint for Carotid Artery Segmentation

TL;DR

GAPNet is a novel neural network designed for accurate carotid artery segmentation in MR images, leveraging anatomical priors and attention mechanisms to handle complex neck anatomy and disease-related changes.

Contribution

The paper introduces GAPNet, a new segmentation model that incorporates anatomy-prior constraints and attention mechanisms for improved carotid artery delineation.

Findings

Achieves higher segmentation accuracy compared to existing methods.

Effectively handles complex neck anatomy and atherosclerosis variations.

Demonstrates robustness across different MR imaging conditions.

Abstract

Atherosclerosis is a chronic, progressive disease that primarily affects the arterial walls. It is one of the major causes of cardiovascular disease. Magnetic Resonance (MR) black-blood vessel wall imaging (BB-VWI) offers crucial insights into vascular disease diagnosis by clearly visualizing vascular structures. However, the complex anatomy of the neck poses challenges in distinguishing the carotid artery (CA) from surrounding structures, especially with changes like atherosclerosis. In order to address these issues, we propose GAPNet, which is a consisting of a novel geometric prior deduced from.