基于深度学习技术的磁共振成像研究进展  

Advances in magnetic resonance imaging based on deep learning technology

作　　者：罗伶俐 王远军[1] LUO Lingli;WANG Yuanjun(Institute of Medical Imaging Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学医学影像工程研究所,上海200093

出　　处：《中国医学物理学杂志》2020年第7期873-877,共5页Chinese Journal of Medical Physics

基　　金：国家自然科学基金(61201067);上海市自然科学基金(18ZR1426900)。

摘　　要：磁共振(MR)成像是当前应用于临床医学诊断的重要医学成像手段之一。如何缩短扫描时间进行快速成像一直以来都是MR成像领域中的热门研究问题。近年来,随着深度学习的兴起和快速发展,深度学习被广泛应用于医学图像处理领域中。目前基于深度学习的MR成像方法作为MR成像的新兴方向,相应的研究已取得了一系列进展。本文对几种常见的基于深度学习的MR成像方法进行归纳和简要分析,并对其研究前景进行了展望。Magnetic resonance(MR)imaging is one of the most important medical imaging methods currently used in clinical medical diagnosis.How to shorten the scanning time for accelerated MR imaging has always been a hot research issue in the field of MR imaging.In recent years,with the rise and rapid development of deep learning,deep learning has been widely used in medical image processing.At present,deep learning-based MR imaging has emerged as an emerging direction of MR imaging,and lots of progress has been made in the related researches.Herein several common deep learning-based MR imaging are summarized and analyzed briefly,and their research prospects are discussed.

关 键 词：磁共振成像 深度学习 图像重建 综述 

分 类 号：R318[医药卫生—生物医学工程]