Differentiation of schizophrenia using structural MRI with consideration of scanner differences: A real-world multisite study

Kiyotaka Nemoto, Tetsuya Shimokawa, Masaki Fukunaga, Fumio Yamashita, Masashi Tamura, Hidenaga Yamamori, Yuka Yasuda, Hirotsugu Azechi, Noriko Kudo, Yoshiyuki Watanabe, Mikio Kido, Tsutomu Takahashi, Shinsuke Koike, Naohiro Okada, Yoji Hirano, Toshiaki Onitsuka, Hidenori Yamasue, Michio Suzuki, Kiyoto Kasai, Ryota HashimotoTetsuaki Arai

Research output: Contribution to journalArticle

Abstract

Aim: Neuroimaging studies have revealed that patients with schizophrenia exhibit reduced gray matter volume in various regions. With these findings, various studies have indicated that structural MRI can be useful for the diagnosis of schizophrenia. However, multisite studies are limited. Here, we evaluated a simple model that could be used to differentiate schizophrenia from control subjects considering MRI scanner differences employing voxel-based morphometry. Methods: Subjects were 541 patients with schizophrenia and 1252 healthy volunteers. Among them, 95 patients and 95 controls (Dataset A) were used for the generation of regions of interest (ROI), and the rest (Dataset B) were used to evaluate our method. The two datasets were comprised of different subjects. Three-dimensional T1-weighted MRI scans were taken for all subjects and gray-matter images were extracted. To differentiate schizophrenia, we generated ROI for schizophrenia from Dataset A. Then, we determined volume within the ROI for each subject from Dataset B. Using the extracted volume data, we calculated a differentiation feature considering age, sex, and intracranial volume for each MRI scanner. Receiver–operator curve analyses were performed to evaluate the differentiation feature. Results: The area under the curve ranged from 0.74 to 0.84, with accuracy from 69% to 76%. Receiver–operator curve analysis with all samples revealed an area under the curve of 0.76 and an accuracy of 73%. Conclusion: We moderately successfully differentiated schizophrenia from control using structural MRI from differing scanners from multiple sites. This could be useful for applying neuroimaging techniques to clinical settings for the accurate diagnosis of schizophrenia.

Original languageEnglish
Pages (from-to)56-63
Number of pages8
JournalPsychiatry and clinical neurosciences
Volume74
Issue number1
DOIs
Publication statusPublished - Jan 1 2020

Fingerprint

Schizophrenia
Neuroimaging
Area Under Curve
Healthy Volunteers
Magnetic Resonance Imaging
Datasets

All Science Journal Classification (ASJC) codes

  • Neuroscience(all)
  • Neurology
  • Clinical Neurology
  • Psychiatry and Mental health

Cite this

Differentiation of schizophrenia using structural MRI with consideration of scanner differences : A real-world multisite study. / Nemoto, Kiyotaka; Shimokawa, Tetsuya; Fukunaga, Masaki; Yamashita, Fumio; Tamura, Masashi; Yamamori, Hidenaga; Yasuda, Yuka; Azechi, Hirotsugu; Kudo, Noriko; Watanabe, Yoshiyuki; Kido, Mikio; Takahashi, Tsutomu; Koike, Shinsuke; Okada, Naohiro; Hirano, Yoji; Onitsuka, Toshiaki; Yamasue, Hidenori; Suzuki, Michio; Kasai, Kiyoto; Hashimoto, Ryota; Arai, Tetsuaki.

In: Psychiatry and clinical neurosciences, Vol. 74, No. 1, 01.01.2020, p. 56-63.

Research output: Contribution to journalArticle

Nemoto, K, Shimokawa, T, Fukunaga, M, Yamashita, F, Tamura, M, Yamamori, H, Yasuda, Y, Azechi, H, Kudo, N, Watanabe, Y, Kido, M, Takahashi, T, Koike, S, Okada, N, Hirano, Y, Onitsuka, T, Yamasue, H, Suzuki, M, Kasai, K, Hashimoto, R & Arai, T 2020, 'Differentiation of schizophrenia using structural MRI with consideration of scanner differences: A real-world multisite study', Psychiatry and clinical neurosciences, vol. 74, no. 1, pp. 56-63. https://doi.org/10.1111/pcn.12934
Nemoto, Kiyotaka ; Shimokawa, Tetsuya ; Fukunaga, Masaki ; Yamashita, Fumio ; Tamura, Masashi ; Yamamori, Hidenaga ; Yasuda, Yuka ; Azechi, Hirotsugu ; Kudo, Noriko ; Watanabe, Yoshiyuki ; Kido, Mikio ; Takahashi, Tsutomu ; Koike, Shinsuke ; Okada, Naohiro ; Hirano, Yoji ; Onitsuka, Toshiaki ; Yamasue, Hidenori ; Suzuki, Michio ; Kasai, Kiyoto ; Hashimoto, Ryota ; Arai, Tetsuaki. / Differentiation of schizophrenia using structural MRI with consideration of scanner differences : A real-world multisite study. In: Psychiatry and clinical neurosciences. 2020 ; Vol. 74, No. 1. pp. 56-63.
@article{e1d34e83d6674fdc9e1a8c24659e845b,
title = "Differentiation of schizophrenia using structural MRI with consideration of scanner differences: A real-world multisite study",
abstract = "Aim: Neuroimaging studies have revealed that patients with schizophrenia exhibit reduced gray matter volume in various regions. With these findings, various studies have indicated that structural MRI can be useful for the diagnosis of schizophrenia. However, multisite studies are limited. Here, we evaluated a simple model that could be used to differentiate schizophrenia from control subjects considering MRI scanner differences employing voxel-based morphometry. Methods: Subjects were 541 patients with schizophrenia and 1252 healthy volunteers. Among them, 95 patients and 95 controls (Dataset A) were used for the generation of regions of interest (ROI), and the rest (Dataset B) were used to evaluate our method. The two datasets were comprised of different subjects. Three-dimensional T1-weighted MRI scans were taken for all subjects and gray-matter images were extracted. To differentiate schizophrenia, we generated ROI for schizophrenia from Dataset A. Then, we determined volume within the ROI for each subject from Dataset B. Using the extracted volume data, we calculated a differentiation feature considering age, sex, and intracranial volume for each MRI scanner. Receiver–operator curve analyses were performed to evaluate the differentiation feature. Results: The area under the curve ranged from 0.74 to 0.84, with accuracy from 69{\%} to 76{\%}. Receiver–operator curve analysis with all samples revealed an area under the curve of 0.76 and an accuracy of 73{\%}. Conclusion: We moderately successfully differentiated schizophrenia from control using structural MRI from differing scanners from multiple sites. This could be useful for applying neuroimaging techniques to clinical settings for the accurate diagnosis of schizophrenia.",
author = "Kiyotaka Nemoto and Tetsuya Shimokawa and Masaki Fukunaga and Fumio Yamashita and Masashi Tamura and Hidenaga Yamamori and Yuka Yasuda and Hirotsugu Azechi and Noriko Kudo and Yoshiyuki Watanabe and Mikio Kido and Tsutomu Takahashi and Shinsuke Koike and Naohiro Okada and Yoji Hirano and Toshiaki Onitsuka and Hidenori Yamasue and Michio Suzuki and Kiyoto Kasai and Ryota Hashimoto and Tetsuaki Arai",
year = "2020",
month = "1",
day = "1",
doi = "10.1111/pcn.12934",
language = "English",
volume = "74",
pages = "56--63",
journal = "Psychiatry and Clinical Neurosciences",
issn = "1323-1316",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - Differentiation of schizophrenia using structural MRI with consideration of scanner differences

T2 - A real-world multisite study

AU - Nemoto, Kiyotaka

AU - Shimokawa, Tetsuya

AU - Fukunaga, Masaki

AU - Yamashita, Fumio

AU - Tamura, Masashi

AU - Yamamori, Hidenaga

AU - Yasuda, Yuka

AU - Azechi, Hirotsugu

AU - Kudo, Noriko

AU - Watanabe, Yoshiyuki

AU - Kido, Mikio

AU - Takahashi, Tsutomu

AU - Koike, Shinsuke

AU - Okada, Naohiro

AU - Hirano, Yoji

AU - Onitsuka, Toshiaki

AU - Yamasue, Hidenori

AU - Suzuki, Michio

AU - Kasai, Kiyoto

AU - Hashimoto, Ryota

AU - Arai, Tetsuaki

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Aim: Neuroimaging studies have revealed that patients with schizophrenia exhibit reduced gray matter volume in various regions. With these findings, various studies have indicated that structural MRI can be useful for the diagnosis of schizophrenia. However, multisite studies are limited. Here, we evaluated a simple model that could be used to differentiate schizophrenia from control subjects considering MRI scanner differences employing voxel-based morphometry. Methods: Subjects were 541 patients with schizophrenia and 1252 healthy volunteers. Among them, 95 patients and 95 controls (Dataset A) were used for the generation of regions of interest (ROI), and the rest (Dataset B) were used to evaluate our method. The two datasets were comprised of different subjects. Three-dimensional T1-weighted MRI scans were taken for all subjects and gray-matter images were extracted. To differentiate schizophrenia, we generated ROI for schizophrenia from Dataset A. Then, we determined volume within the ROI for each subject from Dataset B. Using the extracted volume data, we calculated a differentiation feature considering age, sex, and intracranial volume for each MRI scanner. Receiver–operator curve analyses were performed to evaluate the differentiation feature. Results: The area under the curve ranged from 0.74 to 0.84, with accuracy from 69% to 76%. Receiver–operator curve analysis with all samples revealed an area under the curve of 0.76 and an accuracy of 73%. Conclusion: We moderately successfully differentiated schizophrenia from control using structural MRI from differing scanners from multiple sites. This could be useful for applying neuroimaging techniques to clinical settings for the accurate diagnosis of schizophrenia.

AB - Aim: Neuroimaging studies have revealed that patients with schizophrenia exhibit reduced gray matter volume in various regions. With these findings, various studies have indicated that structural MRI can be useful for the diagnosis of schizophrenia. However, multisite studies are limited. Here, we evaluated a simple model that could be used to differentiate schizophrenia from control subjects considering MRI scanner differences employing voxel-based morphometry. Methods: Subjects were 541 patients with schizophrenia and 1252 healthy volunteers. Among them, 95 patients and 95 controls (Dataset A) were used for the generation of regions of interest (ROI), and the rest (Dataset B) were used to evaluate our method. The two datasets were comprised of different subjects. Three-dimensional T1-weighted MRI scans were taken for all subjects and gray-matter images were extracted. To differentiate schizophrenia, we generated ROI for schizophrenia from Dataset A. Then, we determined volume within the ROI for each subject from Dataset B. Using the extracted volume data, we calculated a differentiation feature considering age, sex, and intracranial volume for each MRI scanner. Receiver–operator curve analyses were performed to evaluate the differentiation feature. Results: The area under the curve ranged from 0.74 to 0.84, with accuracy from 69% to 76%. Receiver–operator curve analysis with all samples revealed an area under the curve of 0.76 and an accuracy of 73%. Conclusion: We moderately successfully differentiated schizophrenia from control using structural MRI from differing scanners from multiple sites. This could be useful for applying neuroimaging techniques to clinical settings for the accurate diagnosis of schizophrenia.

UR - http://www.scopus.com/inward/record.url?scp=85074783154&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074783154&partnerID=8YFLogxK

U2 - 10.1111/pcn.12934

DO - 10.1111/pcn.12934

M3 - Article

C2 - 31587444

AN - SCOPUS:85074783154

VL - 74

SP - 56

EP - 63

JO - Psychiatry and Clinical Neurosciences

JF - Psychiatry and Clinical Neurosciences

SN - 1323-1316

IS - 1

ER -