A 3D reconstruction method of cardiac soft tissue based on sparse principal component analysis

Abstract

The invention discloses a three-dimensional reconstruction method of cardiac soft tissue based on sparse principal component analysis. Firstly, the traditional high-complexity thin-plate spline model is used to extract the three-dimensional historical shape data of the region of interest in the historical image data; The three-dimensional morphological data of the region are processed with relative coordinates and averaged; the processed data is subjected to sparse principal component analysis to extract sparse principal components; finally, a new morphological model is established with the obtained sparse principal In the stereo image, the model parameters are obtained through stereo matching, and then the three-dimensional shape of the current target area on the heart surface is reconstructed.

Description

technical field [0001] The invention belongs to the technical field of cardiac modeling, and more specifically relates to a three-dimensional reconstruction method of cardiac soft tissue based on sparse principal component analysis. Background technique [0002] Heart disease has always been the disease with the highest death rate, and the number of heart surgeries has been on the rise in recent years. In response to this situation, developing a minimally invasive heart surgery robot and providing medical equipment assistance for doctors has become a very meaningful and challenging task. Compared with traditional open-cavity heart surgery, robot-assisted minimally invasive surgery is favored by patients for its smaller wounds and faster recovery. [0003] When the current minimally invasive medical surgical robot performs heart surgery, in order to reduce the damage to the human body caused by cardiac arrest, the use of extracorporeal blood circulation is abandoned. The he...

AI Technical Summary

Problems solved by technology

However, none of the above models can effectively use these cardiac motion characteristics and statistical laws to reduce the complexity of the model.

In addition, Bebek O et al. in the document "Whisker-like position sensor for measuring physiological motion" proposed the use of whisker sensors to estimate cardiac motion; Ott L et al. proposed a A motion estimation method based on a micro-mechanical structure; these methods require the device to touch the heart, which will cause some damage to the heart, and are limited in practical application

Yang Bo and others disclosed a low-complexity model in the patent "A Low-Complexity Online Modeling System and Method for Three-dimensional Heart Surface Morphology". However, this low-complexity model based on principal component analysis is a linear model of the original variables. combination, and the elements of its loading vector are all non-zero, which makes it impossible to explain the meaning represented by each principal component

Images