MRI (Magnetic Resonance Imaging) brain tumor localization and intratumoral segmentation method based on deep cascaded convolution network

Abstract

The invention provides an MRI (Magnetic Resonance Imaging) brain tumor localization and intratumoral segmentation method based on a deep cascaded convolution network, which comprises the steps of building a deep cascaded convolution network segmentation model; performing model training and parameter optimization; and carrying out fast localization and intratumoral segmentation on a multi-modal MRIbrain tumor. According to the MRI brain tumor localization and intratumoral segmentation method provided by the invention based on the deep cascaded convolution network, a deep cascaded hybrid neuralnetwork formed by a full convolution neural network and a classified convolution neural network is constructed, the segmentation process is divided into a complete tumor region localization phase andan intratumoral sub-region localization phase, and hierarchical MRI brain tumor fast and accurate localization and intratumoral sub-region segmentation are realized. Firstly, the complete tumor region is localized from an MRI image by adopting a full convolution network method, and then the complete tumor is further divided into an edema region, a non-enhanced tumor region, an enhanced tumor region and a necrosis region by adopting an image classification method, and accurate localization for the multi-modal MRI brain tumor and fast and accurate segmentation for the intratumoral sub-regions are realized.

Description

technical field [0001] The invention relates to the technical field of medical image analysis, in particular to an MRI brain tumor localization and intratumoral segmentation method based on a deep cascaded convolutional network. Background technique [0002] Brain tumor is a major disease that seriously endangers human health. Among them, glioma is the main type of malignant brain tumor. Although it is uncommon, it has a very high fatality rate. According to literature statistics, the average survival time of high-grade glioma is 14 months. Magnetic Resonance Imaging (MRI) is the most commonly used method for the examination and diagnosis of brain tumors in clinical practice. Accurately segmenting brain tumors and intratumoral structures from MRI images is of great value for neuropathological analysis and accurate diagnosis. Provide important support for surgical planning, radiotherapy and chemotherapy plan formulation and prognosis assessment. [0003] The segmentation o...

AI Technical Summary

Problems solved by technology

[0006] In the existing MRI brain tumor segmentation, the image block classification method does not use global context features and the segmentation speed is slow, while the training samples of the fully convolutional network pixel-level classification method are seriously unbalanced, resulting in inaccurate segmentation boundaries of small regions. The present invention provides a An MRI brain tumor localization and intratumoral segmentation method based on a deep cascaded convolutional network. This method divides the segmentation process into two stages: complete tumor area localization and intratumoral sub-area segmentation, by building a deep cascaded hybrid convolutional neural network. Fast and accurate localization and intratumoral subregion segmentation of multimodal MRI brain tumors

Images