Method for segmenting sulus regions on surface of pallium of a three-dimensional cerebral magnetic resonance image

Abstract

The invention relates to a method for segmenting a sulus region on the surface of a pallium of a three-dimensional cerebral magnetic resonance image. The technical characteristics lie in that firstly, the 3D cerebral nuclear magnetic resonance image is pretreated and the surface of the pallium is reconstructed, including removing a braincase and non-cerebral tissues; carrying out cerebral tissue segmenting on a cerebral image and reconstructing the surface of the pallium of geometrical accuracy and correct topological structure in the segmented cerebral image; the surface of the pallium is shown by a series of vertexes and triangles; secondly, the maximum principle curvature and the minimum principle curvature of each vertex on the surface of the pallium are estimated; and finally, sulus and gyrus regions are segmented on the surface of the pallium according to the maximum principle curvature and Hidden Markov Random Field expectation maximization framework and each sulus region is marked by connectivity analysis. Compared with other methods, the method has the advantages of simple and effective algorithm and high segmentation accuracy.

Description

technical field [0001] The invention relates to a method for segmenting brain sulcus regions on the surface of the cerebral cortex of a three-dimensional brain magnetic resonance image, and belongs to the fields of medical image processing, computational neuroanatomy, and the like. It is suitable for the segmentation of brain sulcus regions on the triangulated cerebral cortex surface reconstructed from human three-dimensional brain magnetic resonance images. Background technique [0002] The human cerebral cortex is an extremely complex and curly anatomical structure, mainly composed of sulci and gyri, which correspond to the valleys and ridges on the cerebral cortex, respectively. Although the precise geometric patterns of sulci and gyri vary widely between individuals, the most dominant sulci and gyri are shared anatomical landmarks in the cerebral cortex. Therefore, the main sulci and gyri have been widely used to assist in the registration of non-linear brain MRI images...

AI Technical Summary

Problems solved by technology

Its disadvantage is that the depth of the brain sulcus cannot distinguish the brain sulcus area and the deep-buried brain gyrus area in the brain sulcus well, because the depths of the brain sulcus area and the deep-buried brain gyrus area in the brain sulcus are very large, and the watershed method is very difficult. It is easy to produce over-segmentation phenomenon, dividing a brain sulcus region into multiple brain sulcus regions, and it is difficult to control the heuristic rules to merge the over-segmented brain sulcus regions; method 2: based on the average curvature of the surface of the cerebral cortex. Methods The surface of the cerebral cortex is regarded as a connected graph structure, and the surface of the cerebral cortex is divided into sulcus and gyrus regions by using the graph cutting method according to the average curvature information

The feature is that the image clipping method is very efficient, but the average curvature cannot distinguish the brain sulci and gyrus regions very well; method 3: Bayesian method based on the average curvature and brain sulcus depth, this method first uses the Bayesian method to The surface of the cerebral cortex is segmented into sulci and gyri regions, then a single sulcus region is extracted using the watershed region growing method, and finally the over-segmented sulcus regions are merged using a heuristic rule

The disadvantage is that the Euclidean sulcus depth defined by this method is not the real sulcus depth, and the average curvature cannot distinguish the sulci and gyrus regions very well.

[0004] The existing methods for segmenting brain sulci on the surface of the cerebral cortex have the following three main defects: First, the average principal curvature is used to distinguish brain sulci and gyrus regions, but the average principal curvature is the maximum principal curvature and the minimum principal curvature. The average value, while the minimum principal curvature of the sulci and gyrus regions is very small, so the average curvature cannot distinguish the sulci and gyrus regions very well

Second, the depth of the brain sulcus is used to distinguish the brain sulcus and the brain gyrus, but the depth of the brain sulcus and the deep gyrus in the brain sulcus are both very large, so the depth of the brain sulcus cannot distinguish the brain sulci and the brain gyrus. back area

Third, use the watershed method and heuristic merging rules to extract a single brain sulcus region, but the watershed method can easily divide a brain sulcus region into multiple brain sulcus regions, and the heuristic merging rules are difficult to control

Images