Fast multichannel magnetic resonance imaging method based on PCU-Net network

• Main Authors: SHI WEICHENG, WANG CHUNLIN, JIN CHAOYANG
• Format: Patent
• Language: Chinese; English
• Published: 11.06.2021
• Subjects: MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The invention discloses a fast multi-channel magnetic resonance imaging method based on a PCU-Net network. The fast multi-channel magnetic resonance imaging method comprises three steps of data processing and division, construction and training optimization of the PCU-Net network and multi-channel magnetic resonance image reconstruction. According to the method, a plurality of U-shaped convolutional neural networks are expanded to multi-channel data training and prediction, features among a plurality of channels are extracted through a multi-channel complex module, and the network is trained based on a multi-channel complex mean square error so as to be used for magnetic resonance image reconstruction of multi-channel under-sampling data. Network convergence is accelerated through a method of circularly importing network parameters. Experimental results show that the method not only can reconstruct the multi-channel magnetic resonance image with high quality, but also can quickly reconstruct the multi-channel