Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

MRI spine image intervertebral disc scanning positioning and vertebra identification method based on deep learning

A technology of scanning positioning and deep learning, which is applied in the field of MRI spine image scanning positioning and vertebral identification based on deep learning, can solve the problems of time-consuming vertebral labeling, misdiagnosis, and long time consumption, so as to reduce operation steps and time, reduce The effect of reducing workload and work fatigue

Pending Publication Date: 2022-05-27
ALLTECH MEDICAL SYST
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] 1. It takes a long time to manually perform the operation. It usually takes several minutes to perform the positioning operation manually for scanning a sequence of intervertebral discs;
[0010] 2. In the diagnosis of film reading, it is also very time-consuming to manually determine the vertebral label, and a lot of manual work is repeated, which is very easy to cause fatigue and lead to errors and misdiagnosis

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • MRI spine image intervertebral disc scanning positioning and vertebra identification method based on deep learning
  • MRI spine image intervertebral disc scanning positioning and vertebra identification method based on deep learning
  • MRI spine image intervertebral disc scanning positioning and vertebra identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings.

[0048] A deep learning-based MRI spine image intervertebral disc scanning positioning and vertebral identification method, comprising the following steps:

[0049] Step s1: Semantically segment the pre-prepared MRI spine images using a convolutional neural network model.

[0050] In step s1, the convolutional neural network model is a DUnet model, and the output of the DUnet model is a matrix, the matrix is ​​the same size as the MRI spine image, and the matrix is ​​a Mask image.

[0051] The DUnet model includes a 4-layer Encoder module, a 1-layer hole convolution module and a 2-layer Decoder module. The Encoder module includes 2 layers of 3x3 convolutions. The Encoder module is activated using the Leaky Relu function and normalized using BatchNormalization; t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an MRI spine image intervertebral disc scanning positioning and vertebra identification method based on deep learning. The method comprises the following steps of s1, performing semantic segmentation on a MRI spine image prepared in advance by using a convolutional neural network model; s2, fitting foreground pixels on the image obtained by semantic segmentation in the step s1 to obtain a plurality of polygons; s3, polygon screening is carried out; s4, polygon sorting is carried out, labels are added, and vertebra identification is completed; s5, polygon edge approximation is carried out, and the number of vertexes is reduced, so that the polygon is closer to a quadrangle; s6, calculating and finding out a lower left corner vertex, an upper left corner vertex, an upper right corner vertex and a lower right corner vertex of the polygon; and s7, calculating an intervertebral disc scanning positioning line to complete intervertebral disc scanning positioning. According to the invention, the efficiency of MRI spine examination can be improved, the manual workload is reduced, and the scanning positions of multiple examinations of a patient have very high repeatability.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a deep learning-based MRI spine image intervertebral disc scanning positioning and vertebral identification method. Background technique [0002] With the improvement of the economic level and the development of technology, people have put forward higher requirements for medical and health care. Magnetic resonance imaging (Magnet Resonance Image, MRI) as an advanced imaging diagnostic technology is more and more widely used in the examination of patients. Compared with other imaging techniques, the use of MRI for the diagnosis of spine-related diseases has obvious advantages, such as more obvious tissue contrast, imaging in any direction, etc. [0003] In the process of MRI examination of the spine, there are two key operations, disc positioning and vertebral identification: [0004] Intervertebral disc localization refers to that after the MRI scanning positio...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/66G06T7/62G06T7/194G06T7/00G06N3/08G06N3/04G06V10/26
CPCG06T7/0012G06T7/62G06T7/66G06T7/194G06N3/08G06T2207/10088G06T2207/30012G06N3/045
Inventor 盛靖友杨明卞威卢章丁强
Owner ALLTECH MEDICAL SYST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products