Three-dimension cardiac muscle straining computing method

Abstract

The invention discloses a three-dimensional myocardial deformation strain calculation method. The invention divides the myocardium into a plurality of local (sub) regions according to the time and space coordinates on the basis of completing the segmentation processing of the marked cardiac magnetic resonance image sequence, a feed forward neural network (BPNN) and a polynomial or support vector machine (SVM) are used for fitting a local displacement field, the calculation of the established local continuous displacement field is done by the Newton iterative method, the motion parameters of the myocardial particle are calculated and the non-linear interpolation technology is used for calculating the myocardial strain parameters. The invention has clear physical significance and simple and effective algorithm, a model is applicable to parallel calculation, which can calculate the forward and backward motion of arbitrary myocardial particle; and the strain calculation results can be used as the judgment criteria of the three-dimensional cardiac ultrasound strain measurement results.

Description

technical field [0001] The invention belongs to tagged heart nuclear magnetic resonance imaging (tagged MRI) myocardial deformation and strain analysis technology, in particular to a 3D (three-dimensional) myocardial strain calculation method based on local interpolation. Background technique [0002] Cardiac motion is a non-rigid complex 3D motion that deforms (including displacement, shear, rotation, contraction or expansion, etc.) during periodic beating. By calculating the 3D motion of the myocardial particle, the 3D strain of each point of the myocardium can be obtained. 3D myocardial strain data is an important parameter for the clinical diagnosis of cardiac diseases and the study of cardiac motion. Therefore, analyzing the spatiotemporal distribution of strain in the 3D heart has important research value, and is one of the hotspots in the field of biomedicine at home and abroad. [0003] At present, the main methods of non-invasive cardiac medical imaging include ca...

AI Technical Summary

Problems solved by technology

[0005] However, the above-mentioned methods all have problems such as complex algorithms, long time-consuming, low calculation accuracy, and controversial premise assumptions (myocardial continuity and isocapacity).

The myocardial particle displacement method based on local fitting proposed a method of fitting myocardial displacement using a feedforward neural network, but it did not solve the problem of calculating myocardial strain (Zhu Jin, Wang Pingan, Xia Deshen: Myocardial deformation calculation based on BPNN method, computer research and development 2005 Vol.42 No.12 pp: 2143-2149)

Images