Rapid magnetic resonance imaging method based on AR2 U-Net neural network

Abstract

The invention discloses a rapid magnetic resonance imaging method based on an AR2 U-Net neural network. According to the method, an existing R2U-Net convolutional neural network is improved; the method is based on an R2U-Net convolutional neural network. An attention gate module is added, an AG training model is used for implicitly learning and suppressing an unrelated region in an input image, and meanwhile, obvious features useful for a specific task are highlighted, so that the AR2 U-Net convolutional neural network only needs a small amount of training data under the condition of reconstructing an image with the same quality. The problem that the swing amplitude of an optimization loss function is too large in the updating process is solved. According to the method, an Adam optimization algorithm is adopted to replace a conventional SGD optimization algorithm, the convergence rate of the convolutional network can be further increased, the problem that training is ended too early can be effectively prevented, and for learning rate processing, a polynomial attenuation strategy is adopted, so that learning can be stably reduced, and the reduction speed is higher along with increase of the number of turns.

Description

technical field [0001] The invention belongs to the field of magnetic resonance imaging, and relates to a fast magnetic resonance imaging method based on an AR2 U-Net convolutional neural network. Background technique [0002] In 1946, the principle of Magnetic Resonance Imaging (MRI) was discovered by two American scientists, Bloch and Purcell. MRI, because of its high soft tissue resolution and no ionizing radiation damage to the human body, is widely used and has become a routine medical examination method. However, due to the disadvantages of slow scanning speed in the application of MRI, motion artifacts are prone to occur, and it is difficult to meet the requirements of real-time imaging, so how to speed up the imaging speed of MRI is one of the hot spots in the field of MRI. [0003] In the past, researchers usually accelerated the imaging time of MRI from three aspects. One is to improve the performance of MRI hardware, but the physiological effects of the human bod...

AI Technical Summary

Problems solved by technology

The above-mentioned articles on fast MRI imaging based on convolutional neural network deep learning or applied for invention patents are mainly based on the general U-Net convolutional neural network deep learning method for MRI fast imaging or based on residual or MRI rapid imaging based on recursive residual convolutional neural network (R2U-Net); the above-mentioned attention-based invention patents or articles are mainly used for image classification and segmentation, and there is no convolution between attention and U-Net Patents or articles on combining neural networks and applying them to MRI image reconstruction

Images