Prediction of subsequent recognition performance using brain activity in the medial temporal lobe

Takamitsu Watanabe, Satoshi Hirose, Hiroyuki Wada, Masaki Katsura, Junichi Chikazoe, Koji Jimura, Yoshio Imai, Toru Machida, Ichiro Shirouzu, Yasushi Miyashita, Seiki Konishi

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Application of multivoxel pattern analysis (MVPA) to functional magnetic resonance imaging (fMRI) data enables reconstruction and classification of cognitive status from brain activity. However, previous studies using MVPA have extracted information about cognitive status that is experienced simultaneously with fMRI scanning, but not one that will be observed after the scanning. In this study, by focusing on activity in the medial temporal lobe (MTL), we demonstrate that MVPA on fMRI data is capable of predicting subsequent recognition performance. In this experiment, six runs of fMRI signals were acquired during encoding of phonogram stimuli. In the analysis, using data acquired in runs 1-3, we first conducted MVPA-based voxel-wise search for the clusters in the MTL whose signals contained the most information about subsequent recognition performance. Next, using the fMRI signals acquired in runs 1-3 from the selected clusters, we trained a classifier function in MVPA. Finally, the trained classifier function was applied to fMRI signals acquired in runs 4-6. Consequently, we succeeded in predicting the subsequent recognition performance for stimuli studied in runs 4-6 with significant accuracy. This accurate prediction suggests that MVPA can extract information that is associated not only with concurrent cognitive status, but also with behavior in the near future.

Original languageEnglish
Pages (from-to)3085-3092
Number of pages8
JournalNeuroImage
Volume54
Issue number4
DOIs
Publication statusPublished - 2011 Feb 14
Externally publishedYes

Fingerprint

Temporal Lobe
Magnetic Resonance Imaging
Brain

Keywords

  • FMRI
  • Human
  • Machine learning
  • Multivariate pattern analysis
  • Subsequent memory effect

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Prediction of subsequent recognition performance using brain activity in the medial temporal lobe. / Watanabe, Takamitsu; Hirose, Satoshi; Wada, Hiroyuki; Katsura, Masaki; Chikazoe, Junichi; Jimura, Koji; Imai, Yoshio; Machida, Toru; Shirouzu, Ichiro; Miyashita, Yasushi; Konishi, Seiki.

In: NeuroImage, Vol. 54, No. 4, 14.02.2011, p. 3085-3092.

Research output: Contribution to journalArticle

Watanabe, T, Hirose, S, Wada, H, Katsura, M, Chikazoe, J, Jimura, K, Imai, Y, Machida, T, Shirouzu, I, Miyashita, Y & Konishi, S 2011, 'Prediction of subsequent recognition performance using brain activity in the medial temporal lobe', NeuroImage, vol. 54, no. 4, pp. 3085-3092. https://doi.org/10.1016/j.neuroimage.2010.10.066
Watanabe, Takamitsu ; Hirose, Satoshi ; Wada, Hiroyuki ; Katsura, Masaki ; Chikazoe, Junichi ; Jimura, Koji ; Imai, Yoshio ; Machida, Toru ; Shirouzu, Ichiro ; Miyashita, Yasushi ; Konishi, Seiki. / Prediction of subsequent recognition performance using brain activity in the medial temporal lobe. In: NeuroImage. 2011 ; Vol. 54, No. 4. pp. 3085-3092.
@article{88dd1da19a1c45978f66d51161d9b4e1,
title = "Prediction of subsequent recognition performance using brain activity in the medial temporal lobe",
abstract = "Application of multivoxel pattern analysis (MVPA) to functional magnetic resonance imaging (fMRI) data enables reconstruction and classification of cognitive status from brain activity. However, previous studies using MVPA have extracted information about cognitive status that is experienced simultaneously with fMRI scanning, but not one that will be observed after the scanning. In this study, by focusing on activity in the medial temporal lobe (MTL), we demonstrate that MVPA on fMRI data is capable of predicting subsequent recognition performance. In this experiment, six runs of fMRI signals were acquired during encoding of phonogram stimuli. In the analysis, using data acquired in runs 1-3, we first conducted MVPA-based voxel-wise search for the clusters in the MTL whose signals contained the most information about subsequent recognition performance. Next, using the fMRI signals acquired in runs 1-3 from the selected clusters, we trained a classifier function in MVPA. Finally, the trained classifier function was applied to fMRI signals acquired in runs 4-6. Consequently, we succeeded in predicting the subsequent recognition performance for stimuli studied in runs 4-6 with significant accuracy. This accurate prediction suggests that MVPA can extract information that is associated not only with concurrent cognitive status, but also with behavior in the near future.",
keywords = "FMRI, Human, Machine learning, Multivariate pattern analysis, Subsequent memory effect",
author = "Takamitsu Watanabe and Satoshi Hirose and Hiroyuki Wada and Masaki Katsura and Junichi Chikazoe and Koji Jimura and Yoshio Imai and Toru Machida and Ichiro Shirouzu and Yasushi Miyashita and Seiki Konishi",
year = "2011",
month = "2",
day = "14",
doi = "10.1016/j.neuroimage.2010.10.066",
language = "English",
volume = "54",
pages = "3085--3092",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "4",

}

TY - JOUR

T1 - Prediction of subsequent recognition performance using brain activity in the medial temporal lobe

AU - Watanabe, Takamitsu

AU - Hirose, Satoshi

AU - Wada, Hiroyuki

AU - Katsura, Masaki

AU - Chikazoe, Junichi

AU - Jimura, Koji

AU - Imai, Yoshio

AU - Machida, Toru

AU - Shirouzu, Ichiro

AU - Miyashita, Yasushi

AU - Konishi, Seiki

PY - 2011/2/14

Y1 - 2011/2/14

N2 - Application of multivoxel pattern analysis (MVPA) to functional magnetic resonance imaging (fMRI) data enables reconstruction and classification of cognitive status from brain activity. However, previous studies using MVPA have extracted information about cognitive status that is experienced simultaneously with fMRI scanning, but not one that will be observed after the scanning. In this study, by focusing on activity in the medial temporal lobe (MTL), we demonstrate that MVPA on fMRI data is capable of predicting subsequent recognition performance. In this experiment, six runs of fMRI signals were acquired during encoding of phonogram stimuli. In the analysis, using data acquired in runs 1-3, we first conducted MVPA-based voxel-wise search for the clusters in the MTL whose signals contained the most information about subsequent recognition performance. Next, using the fMRI signals acquired in runs 1-3 from the selected clusters, we trained a classifier function in MVPA. Finally, the trained classifier function was applied to fMRI signals acquired in runs 4-6. Consequently, we succeeded in predicting the subsequent recognition performance for stimuli studied in runs 4-6 with significant accuracy. This accurate prediction suggests that MVPA can extract information that is associated not only with concurrent cognitive status, but also with behavior in the near future.

AB - Application of multivoxel pattern analysis (MVPA) to functional magnetic resonance imaging (fMRI) data enables reconstruction and classification of cognitive status from brain activity. However, previous studies using MVPA have extracted information about cognitive status that is experienced simultaneously with fMRI scanning, but not one that will be observed after the scanning. In this study, by focusing on activity in the medial temporal lobe (MTL), we demonstrate that MVPA on fMRI data is capable of predicting subsequent recognition performance. In this experiment, six runs of fMRI signals were acquired during encoding of phonogram stimuli. In the analysis, using data acquired in runs 1-3, we first conducted MVPA-based voxel-wise search for the clusters in the MTL whose signals contained the most information about subsequent recognition performance. Next, using the fMRI signals acquired in runs 1-3 from the selected clusters, we trained a classifier function in MVPA. Finally, the trained classifier function was applied to fMRI signals acquired in runs 4-6. Consequently, we succeeded in predicting the subsequent recognition performance for stimuli studied in runs 4-6 with significant accuracy. This accurate prediction suggests that MVPA can extract information that is associated not only with concurrent cognitive status, but also with behavior in the near future.

KW - FMRI

KW - Human

KW - Machine learning

KW - Multivariate pattern analysis

KW - Subsequent memory effect

UR - http://www.scopus.com/inward/record.url?scp=78650932712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650932712&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2010.10.066

DO - 10.1016/j.neuroimage.2010.10.066

M3 - Article

C2 - 21035553

AN - SCOPUS:78650932712

VL - 54

SP - 3085

EP - 3092

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 4

ER -