Comprehensive evaluation of pipelines for classification of psychiatric disorders using multi-site resting-state fMRI datasets.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

Objective classification biomarkers that are developed using resting-state functional magnetic resonance imaging (rs-fMRI) data are expected to contribute to more effective treatment for psychiatric disorders. Unfortunately, no widely accepted biomarkers are available at present, partially because of the large variety of analysis pipelines for their development. In this study, we comprehensively evaluated analysis pipelines using a large-scale, multi-site fMRI dataset for major depressive disorder (MDD). We explored combinations of options in four sub-processes of the analysis pipelines: six types of brain parcellation, four types of functional connectivity (FC) estimations, three types of site-difference harmonization, and five types of machine-learning methods. A total of 360 different MDD classification biomarkers were constructed using the SRPBS dataset acquired with unified protocols (713 participants from four sites) as the discovery dataset, and datasets from other projects acquired with heterogeneous protocols (449 participants from four sites) were used for independent validation. We repeated the procedure after swapping the roles of the two datasets to identify superior pipelines, regardless of the discovery dataset. The classification results of the top 10 biomarkers showed high similarity, and weight similarity was observed between eight of the biomarkers, except for two that used both data-driven parcellation and FC computation. We applied the top 10 pipelines to the datasets of other psychiatric disorders (autism spectrum disorder and schizophrenia), and eight of the biomarkers exhibited sufficient classification performance for both disorders. Our results will be useful for establishing a standardized pipeline for classification biomarkers.

Authors

  • Yuji Takahara
    Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institute International, Kyoto, Japan; Laboratory for Drug Discovery and Disease Research, Shionogi & Co., Ltd., Osaka, Japan. Electronic address: yuji.takahara@shionogi.co.jp.
  • Yuto Kashiwagi
    Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institute International, Kyoto, Japan; Laboratory for Drug Discovery and Development, Shionogi & Co., Ltd., Osaka, Japan.
  • Tomoki Tokuda
    Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institute International, Kyoto, Japan.
  • Junichiro Yoshimoto
    Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institute International, Kyoto, Japan; Department of Biomedical Data Science, School of Medicine, Fujita Health University, Aichi, Japan; International Center for Brain Science, Fujita Health University, Aichi, Japan.
  • Yuki Sakai
    Division of Radiology, Department of Medical Technology, Kyushu University Hospital, Fukuoka, Japan.
  • Ayumu Yamashita
    Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institute International, Kyoto, Japan; Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan.
  • Toshinori Yoshioka
    Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institute International, Kyoto, Japan; XNef, Inc., Kyoto, Japan.
  • Hidehiko Takahashi
    Department of Psychiatry and Behavioral Sciences, Tokyo Medical and Dental University Graduate School, Tokyo, Japan.
  • Hiroto Mizuta
    Department of Psychiatry, Graduate School of Medicine, Kyoto University, Japan.
  • Kiyoto Kasai
    Department of Neuropsychiatry, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
  • Akira Kunimitsu
    Department of Radiology, International University of Health and Welfare, Mita Hospital, Tokyo, Japan.
  • Naohiro Okada
    Department of Neuropsychiatry, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan; The International Research Center for Neurointelligence (WPI-IRCN) at The University of Tokyo Institutes for Advanced Study (UTIAS), The University of Tokyo, Tokyo, Japan.
  • Eri Itai
    Department of Psychiatry and Neurosciences, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan.
  • Hotaka Shinzato
    Department of Psychiatry and Neurosciences. Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima, Japan.
  • Satoshi Yokoyama
    Department of Psychiatry and Neurosciences, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan.
  • Yoshikazu Masuda
    Department of Psychiatry and Neurosciences, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan.
  • Yuki Mitsuyama
    Department of Psychiatry and Neurosciences, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan.
  • Go Okada
    Department of Psychiatry and Neurosciences. Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima, Japan.
  • Yasumasa Okamoto
    Department of Psychiatry and Neurosciences. Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima, Japan.
  • Takashi Itahashi
    Medical Institute of Developmental Disabilities Research, Showa University, 6-11-11 Kitakarasuyama, Tokyo, 157-8577, Japan.
  • Haruhisa Ohta
    Medical Institute of Developmental Disabilities Research, Showa University, 6-11-11 Kitakarasuyama, Tokyo, 157-8577, Japan.
  • Ryu-Ichiro Hashimoto
    Medical Institute of Developmental Disabilities Research, Showa University, 6-11-11 Kitakarasuyama, Tokyo, 157-8577, Japan.
  • Kenichiro Harada
    Division of Neuropsychiatry, Department of Neuroscience, Yamaguchi University Graduate School of Medicine, Yamaguchi, Japan.
  • Hirotaka Yamagata
    Division of Neuropsychiatry, Department of Neuroscience, Yamaguchi University Graduate School of Medicine, Yamaguchi, Japan.
  • Toshio Matsubara
    Division of Neuropsychiatry, Department of Neuroscience, Yamaguchi University Graduate School of Medicine, Yamaguchi, Japan.
  • Koji Matsuo
    Division of Gynecologic Oncology, Department of Obstetrics and Gynecology, University of Southern California, Los Angeles, CA; Norris Comprehensive Cancer Center, University of Southern California, Los Angeles, CA. Electronic address: koji.matsuo@med.usc.edu.
  • Saori C Tanaka
    Computational Neuroscience Labs, ATR Institute International, 619-0288, Kyoto, Japan.
  • Hiroshi Imamizu
    Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institute International, Kyoto, Japan; Department of Psychology, Graduate School of Humanities and Sociology, The University of Tokyo, Tokyo, Japan.
  • Koichi Ogawa
    Faculty of Science and Engineering, Hosei University, Tokyo, Japan.
  • Sotaro Momosaki
    Laboratory for Drug Discovery and Disease Research, Shionogi & Co., Ltd., Osaka, Japan.
  • Mitsuo Kawato
    ATR Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institute International, Hikaridai, Kyoto, Japan. Electronic address: kawato@atr.jp.
  • Okito Yamashita
    From the Institute for Advanced Co-Creation Studies (T.Y.), Osaka University; Departments of Neurosurgery (T.Y., R.F., M.T., K.H., H.K., Y.S.) and Neuromodulation and Neurosurgery (K.H., Y.S.), Osaka University Graduate School of Medicine; Department of Neuroinformatics (T.Y., R.F., Y.K.), ATR Computational Neuroscience Laboratories, Kyoto, Japan; Computational and Biological Learning Laboratory, Department of Engineering (B.S.), University of Cambridge, UK; Center for Information and Neural Networks (B.S.), National Institute for Information and Communications Technology, Osaka; RIKEN Center for Advanced Intelligence Project (O.Y.), Tokyo; Department of Computational Brain Imaging (O.Y.), ATR Neural Information Analysis Laboratories, Kyoto; and Graduate School of Informatics (Y.K.), Kyoto University, Japan.