A Brain Tissue Extraction Method Based on Fully Convolutional Neural Network

Abstract

The invention discloses a method for extracting brain tissue based on a fully convolutional neural network, comprising the following steps: firstly, using a fully convolutional segmentation network to perform preliminary segmentation on a two-dimensional original nuclear magnetic resonance image to obtain a preliminary segmentation result; secondly, according to The preliminary segmentation results separate the internal and boundary information of the brain tissue; again, select these pixels that cannot be determined to be brain tissue as boundary candidate pixels, and send these candidate pixels and their neighborhoods to the convolutional neural network for secondary segmentation. Realize the classification judgment; finally, integrate the internal segmentation results obtained from the primary segmentation and the boundary segmentation results obtained from the secondary segmentation, and then obtain the final segmentation results of brain tissue extraction. The present invention performs two thick and thin segmentations, which not only ensures the calculation efficiency of the method, but also realizes the refined segmentation target, and can be better applied to brain magnetic resonance images to achieve more accurate brain tissue and skull, eyeballs, skin, The removal of non-brain tissue such as fat.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and relates to a brain tissue extraction method based on a fully convolutional neural network. Background technique [0002] The brain is one of the vital organs of the human body and an important part of our body. Human beings have never stopped studying the brain. Scientists hope to explore the unknown functions of the human brain by studying the complex structure inside the brain. Magnetic Resonance Imaging (MRI) technology is non-invasive, contains a large amount of information, and has the characteristics of multi-directional imaging. In MRI images, soft tissues with relatively low gray scale can be clearly distinguished. Therefore, important information such as the location and size of brain tissue anatomy in MRI images can be identified with the naked eye. In addition, MRI images have been widely used clinically because of their high signal-to-noise ratio, high resoluti...

AI Technical Summary

Problems solved by technology

At present, the existing traditional brain tissue extraction methods are difficult to achieve accurate segmentation of brain tissue

Images