An automated vertebral body recognition method based on spine ultrasound coronal images

Abstract

An automatic vertebral body recognition method based on spinal ultrasound coronal images, said method comprising the following steps: 1) utilizing ultrasound image segmentation technology to realize segment-by-section segmentation of vertebral bodies in target spinal segmental ultrasound images; 2) according to characteristic anatomy Identify the structure, characteristic vertebral body and characteristic vertebral body structure, judge and identify the characteristic vertebral body according to the characteristic anatomical structure, and then calculate other vertebral bodies from the characteristic vertebral body; 3) verify and calibrate through the characteristic anatomical structure and vertebral body characteristics. The present invention takes into account the accurate and efficient identification of ultrasonic bone image features, and uses the original spine ultrasonic image segmentation technology to identify the characteristic anatomical structures of the spine in different segments, and thereby judge and identify the characteristic vertebral body, and then according to the long axis of the spine direction, deduce other vertebral bodies from the characteristic vertebral body counting until the target surgical segment, and finally identify the characteristic anatomical structure and characteristic vertebral body through bidirectional counting derivation, and complete the recognition verification and calibration.

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to an automatic vertebral body recognition method based on a spinal ultrasound coronal image. Background technique [0002] With the vigorous development of computer navigation systems, intraoperative navigation of the spinal cord has attracted more and more attention. Through precise positioning, it is expected to greatly solve the positioning problems in spinal cord-related operations, especially in minimally invasive operations, and reduce the technical threshold to promote this advanced technology. promotion and popularization. At the same time, in order to solve the radiation damage in the current mainstream navigation technology, the navigation method based on ultrasound images has gradually become a research hotspot in the industry. Although ultrasound has many advantages such as non-invasive, non-radiation, real-time and economical, it has a large attenuation and diffr...

AI Technical Summary

Problems solved by technology

Unfortunately, no mature models and algorithms have been applied so far. The main difficulty lies in the contradiction between the comprehensiveness and efficiency of the learning set, and the contradiction between the cumbersomeness of supervised segmentation and the reliability of unsupervised segmentation.

Therefore, there is currently no effective segmentation method for human spine ultrasound images, which can take into account the accurate and efficient recognition of ultrasound bone image features

Images