Deep neural network magnetic resonance signal denoising method based on discrete cosine transform

Abstract

The invention belongs to the field of nuclear magnetic resonance data processing, and particularly relates to a deep neural network magnetic resonance signal denoising method based on discrete cosinetransform. The method includes the following steps of: firstly, adopting the discrete cosine transform to transform a noisy signal and a simulated signal as the input and ideal output of a deep neuralnetwork; and then, performing layer-wise greedy pre-training on the deep neural network by adopting an unsupervised learning mode to realize network weight initialization; finely adjusting global parameters by using an error back propagation method; and finally, inputting a test set to the trained deep neural network, performing inverse normalization on the network output, and then performing inverse discrete cosine transform to obtain the denoised nuclear magnetic resonance signal. According to the method, the nonlinear mapping from the noisy signal to a clean signal can be realized, and one-time elimination of all types of noise in the nuclear magnetic resonance signal can be realized; various complex and variable detection environments and noise interference can be adapted, the signal-to-noise ratio can be significantly improved, and the accuracy of the subsequent inversion and interpretation extraction parameters can be improved; and moreover, the introduction of discrete cosine transform and restricted Boltzmann machine pre-training greatly shortens the training time of the deep neural network, improves the training efficiency of the deep neural network, and makes a method for eliminating nuclear magnetic resonance noise in the deep neural network be practical.

Description

technical field [0001] The invention belongs to the field of nuclear magnetic resonance data processing, and in particular relates to a method for denoising magnetic resonance signals with a deep neural network based on discrete cosine transform. Background technique [0002] As a geophysical method capable of qualitatively and quantitatively detecting groundwater, Magnetic Resonance Sounding (MRS) has developed rapidly from theoretical research to instrument development in recent years. However, due to the extremely weak MRS signal, the high-sensitivity instrument is severely disturbed by the noise in the surrounding environment, and cannot accurately extract the MRS signal, which restricts the wide application of the MRS method. There are three types of noise that affect the quality of MRS signals: peak noise, power frequency noise, and random noise. At present, the MRS signal denoising method mainly used in the world is to eliminate different types of noise respectively,...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a deep neural network magnetic resonance signal denoising method based on discrete cosine transform, which solves the problem of complex process in the existing denoising method, and realizes "once Sexual elimination

Images