Research Review of MRI Image Reconstruction Based on Deep Learning
Magnetic Resonance Imaging technology has been widely used in clinical diagnosis and treatments,due to its advantages of high resolution,non-radiation,and the ability to acquire multi-parameter information.However,the main drawback of MRI is the slow imaging speed,which limits its further development.This paper studies the traditional MRI reconstruction methods,summarizes and categorizes supervised and unsupervised MRI reconstruction methods based on Deep Learning,and analyzes and displays the visualization of the network results.Finally it discusses the future research difficulties to achieve MRI image reconstruction.
国家科技期刊平台
NSTL
万方数据
