A fully automatic lumbar vertebral image segmentation method based on pre-emphasis strategy

Abstract

The invention relates to a fully automatic lumbar vertebral image segmentation method based on pre-emphasis strategy, The method comprises the following steps: a data generation method based on humanlumbar vertebrae structure and magnetic resonance contrast characteristics automatically generates a large number of spine magnetic resonance images with rich structural diversity and texture diversity of the spine, and completes the training of the lumbar vertebrae image segmentation model; Using the trained segmentation model, the automatic segmentation of vertebral body and intervertebral discin spinal MRI data is realized. The invention can solve the problem of the limitation of the data of the traditional training model, and has high model generalization ability. There are many kinds oflumbar magnetic resonance images which are adaptable to different hospitals, different scanning machines and different scanning parameters.

Description

technical field [0001] The present invention relates to the technical fields of computer vision and artificial intelligence, and more specifically, to a fully automatic vertebral body and intervertebral disc segmentation method based on pre-emphasis strategy and deep learning technology. Background technique [0002] Low back pain is a common clinical symptom that affects the quality of life of middle-aged and elderly people. Many orthopedic diseases can cause low back pain, and its pathogenesis has not yet been fully elucidated. A large number of studies have shown that Modic changes of the lumbar vertebrae and intervertebral disc degeneration are closely related to low back pain, and magnetic resonance imaging is an important means of lumbar imaging diagnosis. Automatically and accurately segmenting the vertebral body and intervertebral disc in lumbar MRI images is a key step for automatic analysis of vertebral Modic lesions and automatic grading of intervertebral disc deg...

AI Technical Summary

Problems solved by technology

As a deep learning method, deep convolutional network is a good method for vertebral body and intervertebral disc segmentation, but it requires a large amount of lumbar spine image data with manually drawn segmentation labels, which requires experienced doctors to label, and it is difficult to obtain a large number of high-quality images. High-quality labeled data; secondly, due to the existence of various MRI machine models and various scanning parameters in different hospitals, there are various types of lumbar spine scan data, and it is necessary to train the segmentation models for their respective data separately, and the time, manpower and material costs are very high.

Therefore, the traditional model training method has great data limitations, and it is difficult to obtain a segmentation model with strong generalization ability.

Images