In the ultrasound assisted navigation of orthopaedics,the bone structure needs to be segmented accur-ately from the collected ultrasound images and displayed to the doctor to assist the intraoperative decision-making.However,it is difficult to segment bone structures from ultrasound images because of imaging noises,shadow arti-facts and blurred bone boundaries.For solving this problem,this paper proposes a bone ultrasound image segmenta-tion network based on sequential attention and local phase guidance.On the one hand,the network adaptively uses the relationship between frames of ultrasound sequence,that is,sequence attention,to assist the semantic segmenta-tion of bone structures.On the other hand,the local phase guidance module is introduced to highlight the bone edge information and further improve the segmentation accuracy.We performed the cross validation,ablation ex-periments and the comparison experiments with the state-of-arts by using a dataset that contained 19 050 bone ul-trasound images.The experimental results show that the proposed method has high accuracy and is superior to the existing bone segmentation methods.
维普
万方数据