Brain tumor segmentation method and device in combination with convolutional neural network and fuzzy inference

Abstract

The invention relates to medical instrument, applies a computer image processing technology to segmentation of a brain tumor magnetic resonance image, avoids the defects of low efficiency and instability existing in manual segmentation, provides a rapid and reliable brain tumor segmentation result by use of a computer algorithm and provides an accurate basis for diagnosis, treatment and surgical guidance of a brain tumor. According to the technical scheme, a brain tumor segmentation method in combination with a convolutional neural network and fuzzy inference comprises the following steps of (1) selecting an image; (2) constructing a CNN (Convolutional Neural Network) model; (3) carrying out nonlinear mapping; and (4) establishing a fuzzy inference system. The brain tumor segmentation method in combination with the convolutional neural network and fuzzy inference is mainly applied to processing of medical images.

Description

technical field [0001] The invention relates to a medical device, which combines medical images and computer algorithms to complete the segmentation of nuclear magnetic resonance images of brain tumors. Specifically, it involves a brain tumor segmentation method and device that combines convolutional neural networks and fuzzy reasoning. Background technique [0002] Brain tumors are divided into benign tumors and malignant tumors. Benign tumors can generally recover after surgical treatment. Malignant tumors are also called brain cancer because they are stubborn and difficult to cure. According to the survey, 23,000 new brain tumors were diagnosed in the United States in 2015 alone. Brain tumors have seriously endangered human life and health, and how to better diagnose and treat them is very important. At present, the main means of checking the impact of brain tumors are magnetic resonance imaging (magnetic resonance imaging, MRI) and computed tomography (computed tomogra...

AI Technical Summary

Problems solved by technology

[0018] In order to overcome the deficiencies of the prior art, the present invention aims to apply computer image processing technology to the segmentation of brain tumor MRI images, avoid the defects of low efficiency and instability in manual segmentation, and use computer algorithms to provide fast and reliable brain tumor segmentation. Tumor segmentation results provide accurate basis for the diagnosis, treatment and surgical guidance of brain tumors

Images