NVNet: An Enhanced Attention Network for Segmenting Neck Vascular from Ultrasound Images

Bohao Zhang, Changbo Wang, Chenhui Li

Abstract: Ultrasound images often contain much noise, and the examination process is easily affected by many factors. Therefore, it is often necessary for ultrasound surgeons to have rich experience in accurately identifying neck vascular from ultrasound images. The NVNet proposed in this paper can accurately segment neck vessels and accurately segment carotid intima-media from ultrasound images. We use an improved full-scale skip connection to obtain richer feature information from the encoder and introduce enhanced attention mechanism, making it possible for NVNet to identify neck vascular from ultrasound images containing much noise accurately. Due to the lack of available datasets, we collate an entirely new carotid longitudinal sectional ultrasound dataset and carry out data annotation under ultrasound surgeons' guidance. The experiment is carried out on the collated dataset and another public dataset of cross-sectional ultrasound images, including carotid artery and internal jugular vein. The final experimental results prove that the segmentation accuracy of NVNet exceeds that of many well-known models in recent years.