CT-based single vertebral body segmentation method and system, and medium
A vertebral body, a single technology, applied in the field of segmentation of a single vertebral body, can solve multi-scale problems, vertebral body segmentation and other problems, and achieve the effect of accurate segmentation and recognition
Pending Publication Date: 2021-10-01
上海嘉奥信息科技发展有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In view of the above-mentioned related technologies, the inventor believes that there are problems of vertebral body segmentation and recognition and multi-scale problems. Therefore, it is necessary to propose a technical solution to improve the above technical problems
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.
[0031] The present invention provides a method for segmenting a single vertebral body based on CT, comprising the steps of: referring to figure 1 and figure 2 .
[0032] Step 1: Split the network.
[0033] Segmenting the network is the core part of this method. The segmentation network is to segment voxels from the 3D cone image block, and perform binary classification on all voxels, indicating whether the voxel belongs to the current cone instance. The network is composed of a fully convolutional ...
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
Login to View More Abstract
The invention provides a CT-based single vertebral body segmentation method. The method comprises the following steps of: 1, segmenting voxels from 3D vertebral body image blocks, carrying out dichotomy on the voxels, and judging voxel vertebral body instance types; step 2, segmenting one vertebral body instance in the 3D vertebral body; 3, predicting an anatomical marker of the detected vertebral body by using an identification sub-network; 4, distinguishing a completely visible vertebral body and a partially visible vertebral body through a complete classification self-network; and 5, segmenting the vertebral body according to a specific segmentation sequence. According to the CT-based single vertebral body segmentation method and system and the medium provided by the invention, the problems of vertebral body segmentation and recognition and multi-scale are solved, the method and the system can be used for any imaging mode, any view angle, any number and any type of visible vertebral bodies, and the effects of rapid, flexible and accurate segmentation and recognition are achieved.
Description
technical field [0001] The present invention relates to the technical field of single vertebral body segmentation, in particular, to a CT-based single vertebral body segmentation method, system and medium. Background technique [0002] The spine, also known as the spinal column, is the bony structure that forms the central weight-bearing axis of the upper body. Spine images have a variety of medical imaging modalities, in which various images such as X-ray film, CT, MRI, and PET are used to evaluate spinal anatomy and diagnose spinal pathology. Among them, CT is the most widely used scanning technique in contemporary times and is the most spatially accurate way to assess the three-dimensional morphology of vertebrae. Spine segmentation is a fundamental step in most subsequent spine image analysis and modeling tasks. [0003] Regarding the related technologies mentioned above, the inventor believes that there are problems of vertebral body segmentation and recognition and m...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06N3/08G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/20021G06T2207/30012G06N3/045
Inventor 肖建如孟子尧赵义成盛斌吕天予周振华马科威刘铁龙矫健
Owner 上海嘉奥信息科技发展有限公司