Frontiers in Neuroinformatics (Nov 2021)

Magnetic Resonance Imaging Sequence Identification Using a Metadata Learning Approach

  • Shuai Liang,
  • Shuai Liang,
  • Derek Beaton,
  • Stephen R. Arnott,
  • Tom Gee,
  • Mojdeh Zamyadi,
  • Robert Bartha,
  • Sean Symons,
  • Glenda M. MacQueen,
  • Stefanie Hassel,
  • Jason P. Lerch,
  • Jason P. Lerch,
  • Evdokia Anagnostou,
  • Evdokia Anagnostou,
  • Raymond W. Lam,
  • Benicio N. Frey,
  • Benicio N. Frey,
  • Roumen Milev,
  • Daniel J. Müller,
  • Daniel J. Müller,
  • Sidney H. Kennedy,
  • Sidney H. Kennedy,
  • Sidney H. Kennedy,
  • Sidney H. Kennedy,
  • Christopher J. M. Scott,
  • Christopher J. M. Scott,
  • Christopher J. M. Scott,
  • The ONDRI Investigators,
  • Stephen C. Strother,
  • Stephen C. Strother,
  • Angela Troyer,
  • Anthony E. Lang,
  • Barry Greenberg,
  • Chris Hudson,
  • Dale Corbett,
  • David A. Grimes,
  • David G. Munoz,
  • Douglas P. Munoz,
  • Elizabeth Finger,
  • J. B. Orange,
  • Lorne Zinman,
  • Manuel Montero-Odasso,
  • Maria Carmela Tartaglia,
  • Mario Masellis,
  • Michael Borrie,
  • Michael J. Strong,
  • Morris Freedman,
  • Paula M. McLaughlin,
  • Richard H. Swartz,
  • Robert A. Hegele,
  • Robert Bartha,
  • Sandra E. Black,
  • Sean Symons,
  • Stephen C. Strother,
  • William E. McIlroy

DOI
https://doi.org/10.3389/fninf.2021.622951
Journal volume & issue
Vol. 15

Abstract

Read online

Despite the wide application of the magnetic resonance imaging (MRI) technique, there are no widely used standards on naming and describing MRI sequences. The absence of consistent naming conventions presents a major challenge in automating image processing since most MRI software require a priori knowledge of the type of the MRI sequences to be processed. This issue becomes increasingly critical with the current efforts toward open-sharing of MRI data in the neuroscience community. This manuscript reports an MRI sequence detection method using imaging metadata and a supervised machine learning technique. Three datasets from the Brain Center for Ontario Data Exploration (Brain-CODE) data platform, each involving MRI data from multiple research institutes, are used to build and test our model. The preliminary results show that a random forest model can be trained to accurately identify MRI sequence types, and to recognize MRI scans that do not belong to any of the known sequence types. Therefore the proposed approach can be used to automate processing of MRI data that involves a large number of variations in sequence names, and to help standardize sequence naming in ongoing data collections. This study highlights the potential of the machine learning approaches in helping manage health data.

Keywords