MRI brain tumor automatic segmentation method of double-flow decoding convolutional neural network based on edge feature optimization

Abstract

The invention discloses an MRI brain tumor automatic segmentation method based on a double-flow decoding convolutional neural network of edge feature optimization. According to the invention, two optimization strategies based on edges are mainly used to improve the performance of brain tumor segmentation. Firstly, on a network structure, an independent decoding network branch is designed to process edge stream information, and the edge stream information is fused into semantic stream information through feature fusion. Secondly, punishing unmatched pixels of the prediction segmentation mask and the label near the edge by using a regularization loss function to encourage the prediction segmentation mask to be aligned with the label value around the edge; in training, a new edge extraction algorithm is introduced to provide edge tags with higher quality. In addition, an adaptive balance class weight coefficient is added into a cross entropy loss function, so that the problem of serious class imbalance in back propagation of edge extraction is solved. Experiments show that the tumor segmentation precision is effectively improved.

Description

technical field [0001] The invention belongs to the field of machine vision, and in particular relates to an MRI brain tumor automatic segmentation method based on an edge feature optimized dual-stream decoding convolutional neural network. Background technique [0002] With the rapid development and popularization of medical imaging equipment, imaging technologies include magnetic resonance imaging (MR), computed tomography (CT), ultrasound, positron emission tomography (PET), etc., and a large number of medical images are produced every day all over the world. According to reports, the amount of medical imaging information in the world accounts for more than 1 / 5 of the total information in the world. Medical image segmentation is an important step in the analysis of medical image processing, which helps to make the image more intuitive and clear, and improve the efficiency of diagnosis. Therefore, medical image segmentation technology is attached great importance at home a...

AI Technical Summary

Problems solved by technology

Although the encoding and decoding structure of the original U-net network is relatively ingenious, there are still several problems to be improved: (1) The original U-net network structure design is simple, and the feature processing layer only uses two stacked convolutional layers, so that The network layer of the network layer does not give full play to the advantages of deep learning, whether in the encoding network of feature extraction or in the decoding network structure of feature processing; (2) The network does not focus on the features and segmentation effects of the edge part during training , and this part happens to be the key part that affects the accuracy of tumor segmentation

Images