A magnetic resonance image segmentation method combining global and local information

Abstract

The invention discloses a brain magnetic resonance image segmentation method combining global and local information, which comprises the following steps: segmenting the brain magnetic resonance imageby using an end-to-end convolution neural network constructed to obtain various prediction probability distributions; The supervoxels are generated by linear iterative clustering supervoxel algorithmfor brain MRI images. A magnetic resonance image of that brain in which a segmentation result is obtain by fusing the segmentation result prediction probability distribution and the generate supervoxels comprises the following step of: finding out the corresponding regions of the supervoxels in the prediction probability distribution of each category; Background, cerebrospinal fluid (CSF), gray matter (GM) and white matter (WM) were counted and the specific gravity of each category was calculated. The supervoxel class proportion method is used to re-assign the prediction probability distribution of each class. The class with the highest probability of classification and the class label of the pixel are obtained to obtain the segmentation result of the brain magnetic resonance image. The invention can improve the segmentation precision and obtain a better segmentation result of the magnetic resonance image of the brain.

Description

technical field [0001] The invention relates to a brain magnetic resonance image segmentation method combining global and local information, belonging to the technical field of digital images. Background technique [0002] The brain is the highest regulating organ of all physiological activities of the human body and the central organ of psychological thinking activities. It is the most special and important organ of the human body. Its health is extremely important, so it is necessary to pay attention to the health of the brain. However, with the rapid development of society, accelerated pace of life, aging body, environmental factors, traffic and accidents and other factors, brain diseases such as epilepsy, cerebrovascular disease, cerebral palsy and intracranial tumors are more common now. Brain diseases have become an important factor threatening people's health. Effective diagnosis and treatment of brain diseases is extremely beneficial for improving human life expecta...

AI Technical Summary

Problems solved by technology

[0011] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, provide a brain magnetic resonance image segmentation method that combines global and local information, and solve the problems of MRI images subject to noise, partial volume effects and other factors in the existing methods The influence of the influence leads to the problem of low segmentation accuracy

Images