Three-dimensional brain tumor image segmentation method based on improved U-Net neural network

Abstract

The invention relates to a three-dimensional brain tumor image segmentation method based on an improved U-Net neural network. The method comprises the following steps: firstly, performing bias field effect removal processing of an N4ITK algorithm on three-dimensional brain tumor MRI image data, and secondly, respectively performing gray normalization preprocessing on each modal image in an original MRI image; building and training an improved U-Net convolutional neural network model; in a training process, inputting the four types of modal data of the patient as four channels of a neural network into an improved U-Net convolutional neural network model for training; the convolutional neural network U-Net being used as a basis, establishing an improved U-Net convolutional neural network model, and the improved U-Net convolutional neural network model comprising an analysis path used for extracting features and a synthesis path used for recovering a target object.

Description

technical field [0001] The invention is an important field in the field of medical imaging, and combines medical images with deep learning algorithms to complete precise segmentation of three-dimensional brain tumor nuclear magnetic resonance images. Background technique [0002] Intracranial tumors, also known as "brain tumors", are one of the most common diseases in neurosurgery. In terms of the incidence of systemic tumors, brain tumors rank fifth, only lower than stomach, uterus, breast and esophageal tumors. Magnetic Resonance Imaging (MRI) has unique advantages such as no radiation damage, no bony artifacts, multi-faceted multi-parameter imaging, and a high degree of soft tissue resolution. conditions for making a diagnosis and formulating a treatment plan. Due to the imaging principle and imaging conditions of medical instruments, as well as some other influencing factors, the obtained pictures will not be conducive to the observation of human eyes, so that doctors ...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the deficiencies of the existing technology, and aiming at the problems of small brain tumor image data sets, serious category imbalance, and low segmentation accuracy of existing algorithms, the present invention aims to propose an improved U-Net convolutional neural network to realize three-dimensional brain tumor Automatic Segmentation of MRI Images

Images