Weak-Supervised Attention Fusion Network for Carotid Artery Vessel Wall Segmentation

The automatic and accurate segmentation of the carotid artery vessel wall can assist doctors in clinical diagnosis. Medical images often have complex and blurry features, which makes manual data annotation very difficult and time-consuming. 3D CNN can utilize three-dimensional spatial information to more accurately identify diseased tissues and organ structures, but its segmentation performance is limited due to the lack of global contextual information correlation. This paper proposes a network based on CNN and Transformer to segment the carotid artery vessel wall. By combining the effectiveness of CNN in dealing with 3D image segmentation problems and the global attention mechanism of Transformer, it is possible to better capture and process the features of this information. By designing Joint Attention Structure Block (JAS), semantic information in skip connections can be enhanced. The feature fusion block (FF) is used to associate input information with each layer of feature maps, enhancing the detailed information of the feature maps. The effectiveness of this method has been verified through a large number of comparative experiments.