Compressed sensing nuclear magnetic resonance imaging method based on deep neural network

Abstract

The invention discloses a compressed sensing nuclear magnetic resonance imaging method based on a deep neural network. Through the method, a high-quality nuclear magnetic resonance image can be reconstructed with k-space low sampling data collected by a nuclear magnetic resonance imaging device. The method mainly comprises three steps: constructing an alternating direction multiplier deep neural network, training the parameters of the network, and applying the trained network to compressed sensing nuclear magnetic resonance imaging. A nuclear magnetic resonance image reconstructed with multiple pairs of sampling data at low sampling rate and corresponding full-sampling data is used as a training data set, and the model parameters of the alternating direction multiplier deep neural network are trained so that the output image of the deep neural network when sampling data at low sampling rate is used as input is as close as possible to an image reconstructed with full-sampling data. In application, k-space sampling data at given low sampling rate is input to a trained alternating direction multiplier deep neural network, and the output of the network is a reconstructed nuclear magnetic resonance image.

Description

Technical field: [0001] The invention belongs to the field of medical nuclear magnetic resonance imaging, and in particular relates to a compression sensing nuclear magnetic resonance imaging method based on a deep neural network, which is used to reconstruct high-quality nuclear magnetic resonance images from k-space sampling data collected by nuclear magnetic resonance equipment. Background technique: [0002] Magnetic resonance imaging technology is a non-invasive imaging technology that can provide functional and anatomical auxiliary diagnostic information for medical diagnosis. Slow imaging speed is an important problem of MRI technology. Compressed sensing MRI technology is a fast MRI technology, which samples the sample data in k-space, collects a small number of samples instead of all samples, and then reconstructs a clear MRI image based on a small number of samples. Imaging equipment takes only a small number of samples, thus speeding up MRI imaging. [0003] The...

AI Technical Summary

Problems solved by technology

Although the above methods have good performance in MRI compressed sensing imaging, the construction of the compressed sensing reconstruction model is mainly determined by human experience, and the transformation domain, sparsity constraints, regularization coefficients, etc. are all set manually. Therefore, according to the idea of ​​this traditional method, it is difficult to select the optimal compressed sensing imaging model to achieve higher precision image reconstruction

Images