WEAKLY SUPERVISED FAST MAGNETIC RESONANCE IMAGING METHOD AND APPARATUS

摘要

A weakly supervised fast magnetic resonance imaging method based on a deep neural network model. Under-sampled data of different rates is reconstructed by means of different imaging methods to obtain reconstructed images of different rates as sample labels, the reconstructed images and under-sampled data are used as training samples to train a deep neural network model to obtain a reconstruction model that can be used for all under-sampling rates, and the reconstruction model can be used for directly reconstructing magnetic resonance under-sampled data to obtain a reconstructed image.