Spine MRI image key point detection method based on deep learning

Abstract

The invention provides a spine MRI image key point detection method based on deep learning. The invention discloses the spine MRI image key point detection method based on deep learning, and the method comprises the steps: firstly detecting and positioning vertebrae in a spine MRI image through a depth target detection network, recognizing S1 (sacral 1) as a positioning spine, filtering a false positive detection result through combining with the structural information of the spine, and judging the fine granularity label of each vertebra; using a key point detection network for detecting six key points including UA, UM, UP, LA, LM and LP of the upper boundary and the lower boundary of each vertebra, determining and correcting the key point positions of all the vertebrae in combination withedge information, and finally developing interactive visual MRI spine image key point automatic labeling software. Spine MRI image key points can be automatically extracted, and the spine MRI image key point extraction method has huge application value in the aspects of medical image analysis, auxiliary medical treatment and the like.

Description

technical field [0001] The invention belongs to the fields of computer vision and artificial intelligence, and in particular relates to a method for detecting key points of spine MRI images based on deep learning. Background technique [0002] Artificial intelligence technology has been widely used in the medical field in recent years, among which computer vision has great application potential in medical image analysis. The present invention is aimed at key point detection of spine MRI images. The previous work of key point detection of spine MRI images mostly relied on manual annotation by experts. Manual labeling is inefficient and subject to expert subjective influence, especially not suitable for large-scale data processing and analysis. At present, most of the methods that try to use artificial intelligence technology to detect are to use the underlying features of the image, such as the paper (Ebrahimi S, Angelini E, Gajny L, et al.Lumbar spine posterior corner detec...

AI Technical Summary

Problems solved by technology

Manual labeling is inefficient and subject to expert subjective influence, especially not suitable for large-scale data processing and analysis

At present, most of the methods that try to use artificial intelligence technology to detect are to use the underlying features of the image, such as the paper (Ebrahimi S, Angelini E, Gajny L, et al.Lumbar spine posterior corner detection in X-rays using Haar-based features[C] / / 2016IEEE13th international symposium on biomedical imaging (ISBI).IEEE,2016:180-183.) uses Harr features to detect the corners of vertebrae, but this kind of method only uses the underlying information of the image, which has poor robustness and is only suitable for some specific It is not suitable for complex and changeable medical scenarios

Images