GBM multimodal magnetic resonance image segmentation method based on deep neural network

Abstract

The invention provides a GBM multimodal magnetic resonance image segmentation method based on a deep neural network. The method comprises the following steps that firstly each slice image of the collected GBM multimodal magnetic resonance image is preprocessed and then all the slice images are divided into training samples and test samples, and the slice images of the training samples are marked;then the training sample image blocks are extracted and the mean and the variance are standardized, and a training data asset is formed after data amplification; then one deep neural network is constructed and the deep neural network is trained by using the training data set so as to obtain a deep neural network segmentation model; and finally the slice image to be segmented is preprocessed and the image blocks are extracted, and the voxels are classified and post-processed by using the deep neural network segmentation model so that GBM multimodal magnetic resonance image segmentation can be realized. The high requirements of automatic diagnosis, surgical planning and prognosis for the detection and locating accuracy of the abnormal brain tissues and the surrounding normal structures can be met.

Description

technical field [0001] The invention relates to the fields of digital medical image processing and analysis and computer-aided diagnosis, in particular to a GBM multimodal magnetic resonance image segmentation method based on a deep neural network. Background technique [0002] Glioma is the most common primary brain tumor, which mainly occurs in adults, especially the elderly, and has three characteristics: high recurrence rate, high mortality rate and low cure rate. Relevant statistics show that more than half of the glioma patients are the most malignant GBM (Glioblastoma Multiforme, glioblastoma multiforme). Even with the most aggressive treatment, the median survival time of GBM patients is still less than 15 months, and the survival rate over 5 years is less than 5%. GBM presents a patch of heterogeneous tumor areas on multimodal magnetic resonance images. This area usually includes 4 parts: necrotic area, edema area, non-enhancing tumor area and enhancing tumor area...

AI Technical Summary

Problems solved by technology

[0010] The above invention still cannot speed up the segmentation speed and solve the problem of network weight explosion during training

Images