Novel automated spinal ultrasound segmentation approach for scoliosis visualization.

Scoliosis is a 3D deformity of the spine in which one or more segments of the spine curve laterally, usually with rotation of the vertebral body. Generally, having a Cobb angle (Cobb) greater than 10° can be considered scoliosis. In spine imaging, reliable and accurate identification and segmentation of bony features are crucial for scoliosis assessment, disease diagnosis, and treatment planning. Compared with commonly used X-ray detection methods, ultrasound has received extensive attention from researchers in the past years because of its lack of radiation, high real-time performance, and low price. On the basis of our previous research on spinal ultrasound imaging, this work combines artificial intelligence methods to create a new spine ultrasound image segmentation model called ultrasound global guidance block network (UGBNet), which provides a completely automatic and reliable spine segmentation and scoliosis visualization approach. Our network incorporates a global guidance block module that integrates spatial and channel attention, through which long-range feature dependencies and contextual scale information are learned. We evaluate the performance of the proposed model in semantic segmentation on spinal ultrasound datasets through extensive experiments with several classical learning segmentation methods, such as UNet. Results show that our method performs better than other approaches. Our UGBNet significantly improves segmentation precision, which can reach 74.2% on the evaluation metric of the Dice score.