Right ventricle multi-map partitioning method based on cardiac magnetic resonance movie minor-axis image

Abstract

The invention provides a right ventricle multi-map partitioning method based on a cardiac magnetic resonance movie minor-axis image. A magnetic resonance imaging system is used for collecting a certain number of heart original magnetic resonance images of a tested person, and a region of interest is extracted. A fixed number of map images of right ventricle are selected from the original magneticresonance images to be added into a map set, and an expert manual partitioning result is obtained by an expert manually partitioning the map image. The map images and target images obtain a right ventricle coarse partitioning result by adopting B sample conversion based on normalized mutual information, COLLATE fusion is adopted for the coarse partitioning result, firstly log likelihood estimationis carried out on complete data, and then iterative solution is carried out by using a maximum expectation algorithm until convergence, so that the right ventricle final partitioning result is obtained through amending treatment. The method has higher robustness, the accuracy and precision of fusion can be improved, and the method is used for accurately partitioning the heart right ventricle minor-axis image.

Description

technical field [0001] The invention belongs to the field of magnetic resonance image processing, and in particular relates to a right ventricle multi-atlas segmentation method based on cardiac magnetic resonance film short-axis images. Background technique [0002] In addition to the advantages of no ionizing radiation damage, multi-directional imaging, and high soft tissue contrast, short-axis cardiac magnetic resonance cine imaging can also provide dynamic cine images with high temporal and spatial resolution. Cardiac short-axis cine images can accurately display the structure of the heart on the one hand, and can be used to segment the heart and quantify cardiac function parameters on the other hand. [0003] The right ventricle has become a major difficulty in cardiac segmentation due to its thin myocardial wall, unclear border, large changes in myocardial structure, and low contrast with surrounding tissues. Accurate segmentation of the right ventricle is a major chall...

AI Technical Summary

Problems solved by technology

[0004] Traditional medical image segmentation algorithms have shortcomings in the segmentation of the right ventricle of the heart: the convergence condition of the active contour model is difficult to determine, and the initial contour of the level set algorithm is very sensitive

The traditional multi-atlas algorithm fusion stage usually uses weighted fusion strategy or STAPLE fusion strategy for processing, which can obtain better results for brain hippocampus or liver segmentation, but cannot achieve good results for right ventricle segmentation

Images