Unlock instant, AI-driven research and patent intelligence for your innovation.

Pelvic femur medical image modeling method based on RFR-SSMs

A modeling method and medical image technology, applied in the field of medical image processing, can solve the problems of relying on a priori shape initialization, complex calculation, unable to meet clinical medicine and other problems

Active Publication Date: 2019-10-15
LANZHOU UNIVERSITY OF TECHNOLOGY
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing modeling methods mainly include Active Shape Models (ASMs), Active Appearance Models (AAMs) and Constrained Local Models (CLMs). The initialization of the prior shape does not meet the needs of clinical medicine

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
  • Pelvic femur medical image modeling method based on RFR-SSMs
  • Pelvic femur medical image modeling method based on RFR-SSMs
  • Pelvic femur medical image modeling method based on RFR-SSMs

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The method of the present invention will be further described below through specific embodiments.

[0054] A pelvis-femoral medical image modeling method based on RFR-SSMs, including three processes of RFR-SSMs training, statistical shape model establishment and RFR-SSMs matching, wherein:

[0055] (1) the training of described RFR-SSMs, comprises the steps:

[0056] (1) Input the CT scan image of the pelvis, adjust the window width and window level so that the gray scale range of the pelvis image is between 0-255; use the existing image segmentation algorithm to segment the femur in the CT scan image of the pelvis to obtain the input Data set S n =(x 1 ,y 1 , x 2 ,y 2 …x n ,y n ) T , where x i ,y i is the pixel of the femur image;

[0057] (2) The data set S n Input into the RFR-SSMs framework for training, starting from the root node to the data set S n The data in is split at each node, and each node applies its own split function to the new input, thus ...

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 provides a pelvic femur medical image modeling method based on RFR-SSMs, and the method comprises three processes: training of RFR-SSMs, building of a statistical shape model, and matching of RFR-SSMs, and specifically comprises the steps: inputting a thighbone part in a pelvis CT scanning image to obtain an input data set Sn, and preprocessing the input data set by using random forest regression to eliminate the influence of factors such as scale, rotation, blurring and the like on an original image; secondly, selecting an average shape from the preprocessed image data set as areference image, aligning other images with the reference image, performing statistical shape modeling by using PCA, and converting a coordinate system from a reference coordinate system to an image coordinate system; and finally, optimizing the model through a parameter w = {b, theta, r} to enable the model to achieve an expected effect. Compared with traditional ASMs, AAMs and SSMs modeling methods, the result shows that the algorithm has obvious superiority in performance, and the thighbone contour can be accurately and stably detected.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and relates to a pelvis-femoral medical image modeling method based on RFR-SSMs. Background technique [0002] At present, pelvic disease is a disease with a relatively high incidence rate clinically, which poses a serious threat to people's life and health. Therefore, accurate modeling of pelvic diseased femur has important medical significance. The traditional femur modeling of pelvic lesions often relies on magnetic resonance imaging (MRI) and computed tomography (CT) to model and analyze the femur of pelvic lesions by obtaining the location, characteristics, and size of these lesions. Pelvic disease and the process of developing a reasonable surgical plan play an important role. Therefore, there is an urgent need for a fast and effective method to model and analyze the femoral part of pelvic lesions in clinical practice. Existing modeling methods mainly include Active Shap...

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): G06T17/00G06T7/10G06T7/00
CPCG06T17/00G06T7/10G06T7/0012G06T2210/41G06T2207/10081G06T2207/30008G06T2207/20081
Inventor 徐铸业赵小强惠永永宋昭漾
Owner LANZHOU UNIVERSITY OF TECHNOLOGY