波谱学杂志 ›› 2023, Vol. 40 ›› Issue (2): 207-219.doi: 10.11938/cjmr20223034

• 综述评论 • 上一篇    下一篇

磁共振指纹成像技术及临床应用的进展

黄敏1,2,*(),李思怡1,陈军波1,2,周到1,2   

  1. 1.中南民族大学 生物医学工程学院,湖北 武汉 430074
    2.医学信息分析及肿瘤诊疗湖北省重点实验室,湖北 武汉 430074
  • 收稿日期:2022-11-14 出版日期:2023-06-05 在线发表日期:2023-02-16
  • 通讯作者: 黄敏 E-mail:minhuang@mail.scuec.edu.cn
  • 基金资助:
    湖北省自然科学基金资助项目(2020CFB837);中央高校基本科研业务费专项资金资助项目(CZZ21006)

Progress of Magnetic Resonance Fingerprinting Technology and Its Clinical Application

HUANG Min1,2,*(),LI Siyi1,CHEN Junbo1,2,ZHOU Dao1,2   

  1. 1. School of Biomedical Engineering, South-Central Minzu University, Wuhan 430074, China
    2. Hubei Key Laboratory of Medical Information Analysis and Tumor Diagnosis & Treatment, Wuhan 430074, China
  • Received:2022-11-14 Published:2023-06-05 Online:2023-02-16
  • Contact: HUANG Min E-mail:minhuang@mail.scuec.edu.cn

摘要:

磁共振指纹(magnetic resonance fingerprinting,MRF)是一种革新性的快速定量磁共振新技术,本文在成像技术和临床应用两个层面对MRF进行了综述. 在成像技术方面,主要从数据采集、字典建立,以及传统量化框架到深度学习量化框架的模式识别这3个步骤进行论述,分析存在的技术难点. 然后对MRF在人体重要部位的临床应用进行了总结,介绍了MRF技术在重复性和再现性方面的验证现状. 最后,本文分析了MRF走向临床存在的各种技术挑战及障碍,对MRF技术未来的发展方向进行了展望.

关键词: 磁共振指纹, 数据采集, 字典建立, 模式识别, 深度学习网络, 临床应用, 可重复性

Abstract:

Magnetic resonance fingerprinting (MRF) is a revolutionary new technique for rapid quantitative magnetic resonance imaging. We reviewed the imaging technology and clinical application of MRF in an all-round way. We focus on three technical aspects: data collection, dictionary generation, and pattern recognition from traditional quantitative framework to deep learning quantitative framework. We also analyzed the technical challenges and limitations of MRF. The clinical applications of MRF in various human body regions were summarized, and the current status of MRF technology verification in terms of repeatability and reproducibility was introduced. Finally, we discussed the potential barriers and opportunities for MRF to enter clinical application and envision the future development direction of MRF technology.

Key words: magnetic resonance fingerprinting, data acquisition, dictionary generation, pattern recognition, deep learning net, clinical application, repeatability

中图分类号: