Mean deviation based identification of activated voxels from time-series fMRI data of schizophrenia patients

Indranath Chatterjee

doi:10.12688/f1000research.16405.1

Home Browse Mean deviation based identification of activated voxels from time-series...

ALL Metrics

Views

Downloads

Get PDF

Get XML

Export

▬

✚

Research Article

Mean deviation based identification of activated voxels from time-series fMRI data of schizophrenia patients

[version 1; peer review: 1 approved, 1 approved with reservations]

Indranath Chatterjee

PUBLISHED 08 Oct 2018

Author details Author details

Department of Computer Science, University of Delhi, Delhi, 110007, India

Indranath Chatterjee
Roles: Conceptualization, Formal Analysis, Investigation, Methodology, Project Administration, Resources, Validation, Visualization, Writing – Original Draft Preparation, Writing – Review & Editing

OPEN PEER REVIEW

REVIEWER STATUS

This article is included in the Brainhack Global collection.

Abstract

Background: Schizophrenia is a serious mental illness affecting different regions of the brain, which causes symptoms such as hallucinations and delusions. Functional magnetic resonance imaging (fMRI) is the most popular technique to study the functional activation patterns of the brain. The fMRI data is four-dimensional, composed of 3D brain images over time. Each voxel of the 3D brain volume is associated with a time series of signal intensity values. This study aimed to identify the distinct voxels from time-series fMRI data that show high functional activation during a task.
Methods: In this study, a novel mean-deviation based approach was applied to time-series fMRI data of 34 schizophrenia patients and 34 healthy subjects. The statistical measures such as mean and median were used to find the functional changes in each voxel over time. The voxels that show significant changes for each subject were selected and thus used as the feature set during the classification of schizophrenia patients and healthy controls.
Results: The proposed approach identifies a set of relevant voxels that are used to distinguish between healthy and schizophrenia subjects with high classification accuracy. The study shows functional changes in brain regions such as superior frontal gyrus, cuneus, medial frontal gyrus, middle occipital gyrus, and superior temporal gyrus.
Conclusions: This work describes a simple yet novel feature selection algorithm for time-series fMRI data to identify the activated brain voxels that are generally affected in schizophrenia. The brain regions identified in this study may further help clinicians to understand the illness for better medical intervention. It may be possible to explore the approach to fMRI data of other psychological disorders.

Keywords

fMRI, Schizophrenia, Time-series, Classification

Corresponding author: Indranath Chatterjee

Competing interests: No competing interests were disclosed.

Grant information: The author(s) declared that no grants were involved in supporting this work.

Copyright: © 2018 Chatterjee I. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

How to cite: Chatterjee I. Mean deviation based identification of activated voxels from time-series fMRI data of schizophrenia patients [version 1; peer review: 1 approved, 1 approved with reservations]. F1000Research 2018, 7:1615 (https://doi.org/10.12688/f1000research.16405.1) First published: 08 Oct 2018, 7:1615 (https://doi.org/10.12688/f1000research.16405.1) Latest published: 20 Dec 2018, 7:1615 (https://doi.org/10.12688/f1000research.16405.2)

Introduction

Schizophrenia is a severe mental disorder that affects different regions of the brain, often involving hallucinations and delusions. Functional magnetic resonance imaging (fMRI) data comprising 3D brain scans acquired over time (thus resulting in a 4D set) is often used to study brain regions affected by schizophrenia. Each voxel of the 3D brain volume is associated with a time series of signal intensity values. General linear model (GLM)¹ and independent component analysis (ICA)² are often employed to study the voxel activity by transforming the 4D time-series data to a 3D spatial map.

The present work involves a novel application of mean deviation on time-series fMRI data to identify the distinct voxels that show high functional activation during a task. The work aims to identify the relevant brain regions that are affected in schizophrenia. Further, the identified voxels (features) are used to distinguish between schizophrenia patients and healthy subjects.

Methods

fMRI data

The time-series fMRI data having 1.5T strength was taken from the FBIRN phase – II data repository³ available at site 0009 and site 0010. From the dataset, four different runs of auditory oddball task data of 34 schizophrenic patients (group G1) and 34 healthy controls (group G2) were extracted. Every run of each subject’s data contains 140 brain volumes acquired in 280 seconds time (TR = 2 seconds). Table 1 shows the dataset details.

Table 1. Dataset details.

Subject	Sample size	Age (Mean & Std Dev)	Male/Female
Healthy	34	37.76 (±12.25) years	24/10
Schizophrenia	34	39.76 (±10.8) years	27/7

Pre-processing of the fMRI data was done using SPM8 toolbox in Matlab2014b. The temporal variation was corrected using slice timing correction, followed by the motion correction using realignment. Each of the fMRI scans was spatially normalized into standard Montreal Neurological Institute (MNI) space using an EPI template yielding voxel dimension of 3×3×3 mm³. Finally smoothing was done using a 9×9×9 mm³ full width at half maximum (FWHM) Gaussian kernel, resulting in a 3D brain volume containing 53×63×46, i.e., 1,53,594 voxels.

Data analysis

The activation pattern of the voxels was analysed in two phases.

Phase I. In the first phase, identification of voxels exhibiting high activation pattern (anytime during its time-course) is carried out for each subject. As the study focused on the variation in the signal intensity of the voxels (V) over time, absolute mean deviation ( $\bar{V_{d}}$ ) for each of the 140 time points was computed for each voxel, and the median (M) of the 140 values of $\bar{V}$ was found. Mean deviation ( $\bar{V}$ ) values were compared with α times M (α was chosen to be 3, based on experimentation) to identify whether a voxel exhibited high level of activation at any time during the 140 units of time. This voxel-wise analysis was performed for all the voxels of a given subject. Thus, a set of relevant voxels showing high degree of activation was obtained for each subject.

Phase II. In the second phase, a common subset of voxels exhibiting high degree of activation across all the subjects within a group was obtained. Finally, both the subsets belonging to groups G1 (schizophrenia patients) and G2 (healthy controls) were merged to get the set S. The voxels in set S were backtracked to MNI brain space and finally mapped into Talairach’s space⁴ to identify the brain regions. This procedure has been described in Algorithm 1.

Classification. The set S was used to distinguish between schizophrenia patients and healthy subjects using two classifiers, viz., support vector machine (SVM) with sigmoid kernel⁵ and extreme learning machine (ELM) classifier⁶.

Experimental settings. All the implementations were done in MATLAB2014b. Parameter α was varied in the range^1,7 in steps of 1 to identify the number of voxels that exhibited a high level of activations during the task. When the value of α was taken as 1 and 2, a large number of voxels showed activation level higher than α times M, resulting in set S having voxels that represents almost the entire brain. However, for α = 3, it was found that set S contained only 1580 distinct voxels that mapped to the brain regions which are generally affected in schizophrenia. When α was taken as more than 3, the number of voxels in the set S were close to zero rendering it too small for any meaningful analysis. Thus, α = 3 was found to be the most suitable value.

Further, the set S of voxels obtained α = 3 was used to fine-tune the classifiers. The SVM classifier gave the best results for the regularization parameter C = 1.09, and sigmoid kernel based ELM classifier gave best the results with 503 hidden neurons.

To evaluate the distinguishing capability of the voxels/features in set S, a comparison was done between the classification accuracy obtained using S and the accuracy obtained using the voxels set given by the GLM based approach. In this case, GLM was applied using SPM8 toolbox to convert the 4D time-series fMRI data to 3D contrast map for each subject. The GLM yielded an activation map comprising around 60000 voxels out of 153594 which were activated during the task.

Algorithm 1. The proposed approach

Notations:

m (=34): the number of subjects in each group
n (=140): the number of observations in a run
V_i : time-series of i^th voxel
i.e. V_i = [v_i,1 v_i,2 v_i,3 ⋯ v_i,n];
$μ_{i} : mean of V_{i} i.e. μ_{i} = \frac{{\sum_{j = 1}^{j = n} v}_{i, j}}{n}$

Steps:

1. Calculate absolute mean deviation for each voxel using ${\bar{V}}_{d_{i}} = | V_{i} - μ_{ι} | .$
2. Find median M_i of ${\bar{V}}_{d_{i}} .$
3. For each subject k ∈{1,2,...,m}, select the set V_{s_k} of voxels that show deviation higher than αM_i.
4. Find the group wise intersection of the voxels selected in step 3 for groups G1 and G2
- i.e. $V_{s_{G 1}} = \cap_{k = 1}^{m} V_{s_{k}} (G 1)$
- $V_{s_{G 2}} = \cap_{k = 1}^{m} V_{s_{k}} (G 2)$
5. Merge the two sets, obtained in step 4 to obtain set S
- i.e. S = V_{S_G1} ∪ V_{S_G2}
6. Map S into the brain space to identify affected regions.

Results

A comparison of the results of the classification accuracies obtained using feature sets given by the GLM and the proposed approach is shown in Table 2. The features selected by the proposed approach when backtracked to Talairach’s space revealed the brain regions that are generally affected in schizophrenia^8–10, which validates the efficacy of the approach. The distribution of the selected voxels that distinguish the schizophrenia patients from the healthy subjects is shown in Figure 1 (a–d). Figure 2 (a–c) show the activated voxels when plotted on a sample fMRI image for an axial, coronal and sagittal view of the brain.

Table 2. Comparison showing classification accuracy with feature set obtained after GLM and the proposed approach using SVM and ELM classifiers.

	GLM	Proposed approach
Number of voxels	~ 60,000	~ 1580
SVM with Sigmoid kernel	32.45%	76.47%
ELM with Sigmoid kernel	57.35%	61.46%

Figure 1.

Identified brain regions at different levels of hierarchy, namely, hemisphere level (a), lobes level (b), gyrus level (c), and Brodmann's area level (d).

Figure 2.

Voxels identified by the proposed approach plotted over a functional brain image in different views of the brain, i.e., axial (a), coronal (b) and sagittal (c) plane.

Discussion

Unlike other conventional methods such as GLM to select the voxels showing a statistically significant response to the experimental conditions⁷, the proposed approach identifies the neural activity in a particular voxel over time, irrespective of any experimental condition. The proposed approach does not require any details for the task and conditions. It works on the temporal values of each voxel for each subject's data one by one. Like other multi-voxel pattern analysis (MVPA) methods^7,11,12, this approach also tries to find the participation of multiple voxels when selecting the final set of relevant voxels across a particular group of the subjects.

The classification accuracies, as shown in Table 2, demonstrate the efficacy of the proposed methodology. The reduced set of 1580 voxels achieved a much higher accuracy when compared to the GLM approach. Figures 1a–d show the distribution of the selected voxels for each level of brain regions. These regions show distinct changes in functional activation in schizophrenia patients when compared to healthy controls, and thereby distinguish between schizophrenia and healthy subjects with high classification accuracy. Most of the regions identified in the study comply with the existing literature^13–16. The regions such as superior frontal gyrus, cuneus, lingual gyrus, medial frontal, middle occipital gyrus, superior temporal gyrus, anterior cingulate, and declive show the changes in functional activation. Studies showed functional changes in superior frontal gyrus¹³, superior temporal gyrus¹⁵, lingual gyrus¹⁵, and cuneus¹⁵. Even functional abnormality in anterior cingulate was found in several studies^16,17. The literature also suggests functional changes in middle occipital gyrus¹⁸. When observed at the cell level of brain regions in Talairach’s space, this study shows distinguishable functional changes in Brodmann’s area (BA) 18, 10, 9, 17, 19, 32, 21, 37, 11, and BA 6. Previous studies^14,19 also showed changes in functional activation in these areas of the brain.

Conclusions

This work describes a simple and fast feature selection algorithm based on mean deviation for time-series fMRI data to identify the activated brain voxels that are generally affected in schizophrenia. The proposed approach was found to be efficient in selecting a minimal set of relevant voxels directly from time-series 4D fMRI data. The obtained voxel set was capable of distinguishing between healthy and schizophrenic subjects. One may explore the possibility of applying this approach to fMRI data of other psychological disorders.

Data availability

The Matlab source codes, a text file containing dataset details including subject ID and their age, and the instructions for the study can be found at: https://github.com/IndraChatterjee/AnomalyDetection_TimeSeries_fMRI_Schizophrenia.

The complete source codes are archived in a publicly accessible record at: https://doi.org/10.5281/zenodo.1438539²⁰

License: CC0

The four runs of auditory oddball task fMRI data from the FBIRN phase II repository can be downloaded from http://schizconnect.org/ querying 1.5T fMRI data for healthy and schizophrenia subjects available at site 0009 and 0010. The list of subjects chosen for this study is mentioned in the ‘DataDetails_FBIRN15T.txt’ file available at the GitHub repository. Users are required to sign-up to SchizConnect to download data and conditions of use are as written in the data use agreement of the FBIRN project.

Author endorsement

Cameron Craddock confirms that the author has an appropriate level of expertise to conduct this research, and confirms that the submission is of an acceptable scientific standard. Cameron Craddock declares the following competing interests: I am the Chair of Brainhack, and this organisation awarded this paper this year's Brainhack poster prize. Affiliation: Associate Professor of Diagnostic Medicine, Dell Medical School, The University of Texas at Austin, Austin, TX, USA.

Grant information

The author(s) declared that no grants were involved in supporting this work.

The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Acknowledgments

The author would like to thank the organizers and all the attendees of 2018 OHBM Brainhack Singapore.

Data used for this study were hosted in the Function BIRN Data Repository (http://fbirnbdr.birncommunity.org:8080/BDR/) using Project Accession Number 2007-BDR-6UHZ1, supported by grants to the Function BIRN (U24-RR021992) Testbed funded by the National Center for Research Resources at the National Institutes of Health, U.S.A.

Faculty Opinions recommended

References

1. Friston KJ, Holmes AP, Worsley KJ, et al.: Statistical parametric maps in functional imaging: a general linear approach. Hum Brain Mapp. 1994; 2(4): 189–210. Publisher Full Text
2. Kim DI, Mathalon D, Ford JM, et al.: Auditory oddball deficits in schizophrenia: an independent component analysis of the fMRI multisite function BIRN study. Schizophren Bull. 2009; 35(1): 67–81. PubMed Abstract | Publisher Full Text | Free Full Text
3. Keator DB, van Erp TG, Turner JA, et al.: The Function Biomedical Informatics Research Network Data Repository. NeuroImage. 2016; 124(Pt B): 1074–1079. PubMed Abstract | Publisher Full Text | Free Full Text
4. Lancaster JL, Woldorff MG, Parsons LM, et al.: Automated Talairach atlas labels for functional brain mapping. Hum Brain Mapp. 2000; 10(3): 120–131. PubMed Abstract | Publisher Full Text
5. Cortes C, Vapnik V: Support-vector networks. Mach Learn. 1995; 20(3): 273–297. Publisher Full Text
6. Huang GB, Zhu QY, Siew CK: Extreme learning machine: theory and applications. Neurocomputing. 2006; 70(1–3): 489–501. Publisher Full Text
7. Norman KA, Polyn SM, Detre GJ, et al.: Beyond mind-reading: multi-voxel pattern analysis of fMRI data. Trends Cogn Sci. 2006; 10(9): 424–430. PubMed Abstract | Publisher Full Text
8. Castro E, Gómez-Verdejo V, Martínez-Ramón M, et al.: A multiple kernel learning approach to perform classification of groups from complex-valued fMRI data analysis: application to schizophrenia. NeuroImage. 2014; 87: 1–17. PubMed Abstract | Publisher Full Text | Free Full Text
9. Garrity AG, Pearlson GD, McKiernan K, et al.: Aberrant “default mode” functional connectivity in schizophrenia. Am J Psychiatry. 2007; 164(3): 450–457. PubMed Abstract | Publisher Full Text
10. Gur RE, Gur RC: Functional magnetic resonance imaging in schizophrenia. Dialogues Clin Neurosci. 2010; 12(3): 333–343. PubMed Abstract | Free Full Text
11. Formisano E, De Martino F, Valente G: Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning. Magn Reson Imaging. 2008; 26(7): 921–934. PubMed Abstract | Publisher Full Text
12. De Martino F, Valente G, Staeren N, et al.: Combining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns. NeuroImage. 2008; 43(1): 44–58. PubMed Abstract | Publisher Full Text
13. Hof PR, Haroutunian V, Friedrich VL Jr, et al.: Loss and altered spatial distribution of oligodendrocytes in the superior frontal gyrus in schizophrenia. Biol Psychiatry. 2003; 53(12): 1075–1085. PubMed Abstract | Publisher Full Text
14. Chatterjee I, Agarwal M, Rana B, et al.: Bi-objective approach for computer-aided diagnosis of schizophrenia patients using fMRI data. Multimed Tools Appl. 2018; 77(20): 26991–27015. Publisher Full Text
15. Hoptman MJ, Zuo XN, Butler PD, et al.: Amplitude of low-frequency oscillations in schizophrenia: a resting state fMRI study. Schizophr Res. 2010; 117(1): 13–20. PubMed Abstract | Publisher Full Text | Free Full Text
16. Vercammen A, Knegtering H, den Boer JA, et al.: Auditory hallucinations in schizophrenia are associated with reduced functional connectivity of the temporo-parietal area. Biol Psychiatry. 2010; 67(10): 912–918. PubMed Abstract | Publisher Full Text
17. Carter CS, Mintun M, Nichols T, et al.: Anterior cingulate gyrus dysfunction and selective attention deficits in schizophrenia: [¹⁵O]H₂O PET study during single-trial Stroop task performance. Am J Psychiatry. 1997; 154(12): 1670–1675. PubMed Abstract | Publisher Full Text
18. Brunet E, Sarfati Y, Hardy-Baylé MC, et al.: Abnormalities of brain function during a nonverbal theory of mind task in schizophrenia. Neuropsychologia. 2003; 41(12): 1574–1582. PubMed Abstract | Publisher Full Text
19. Camchong J, Dyckman KA, Austin BP, et al.: Common neural circuitry supporting volitional saccades and its disruption in schizophrenia patients and relatives. Biol Psychiatry. 2008; 64(12): 1042–1050. PubMed Abstract | Publisher Full Text | Free Full Text
20. Chatterjee I: Feature selection technique for time-series fMRI data of schizophrenia patients [Source Code]. Zenodo. 2018. http://www.doi.org/10.5281/zenodo.1438539

Comments on this article Comments (0)

Version 2

VERSION 2 PUBLISHED 08 Oct 2018

Author details Author details

Department of Computer Science, University of Delhi, Delhi, 110007, India

Competing interests

No competing interests were disclosed.

Grant information

The author(s) declared that no grants were involved in supporting this work.

Article Versions (2)

version 2

Revised

Published: 20 Dec 2018, 7:1615

https://doi.org/10.12688/f1000research.16405.2

version 1

Published: 08 Oct 2018, 7:1615

https://doi.org/10.12688/f1000research.16405.1

© 2018 Chatterjee I. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Download

Export To

metrics

	Views	Downloads
F1000Research	-	-
PubMed Central Data from PMC are received and updated monthly.	-	-

Citations

SEE MORE DETAILS

CITE

how to cite this article

Chatterjee I. Mean deviation based identification of activated voxels from time-series fMRI data of schizophrenia patients [version 1; peer review: 1 approved, 1 approved with reservations] F1000Research 2018, 7:1615 (https://doi.org/10.12688/f1000research.16405.1)

NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.

track

receive updates on this article

Track an article to receive email alerts on any updates to this article.

Open Peer Review

Current Reviewer Status: ?

Key to Reviewer Statuses VIEW HIDE

ApprovedThe paper is scientifically sound in its current form and only minor, if any, improvements are suggested

Approved with reservations A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.

Not approvedFundamental flaws in the paper seriously undermine the findings and conclusions

Version 1

VERSION 1

PUBLISHED 08 Oct 2018

Views

Reviewer Report 22 Nov 2018

Sagarika Bhattacharjee, Department of Psychology, Nanyang Technological University, Singapore, Singapore

Approved with Reservations

https://doi.org/10.5256/f1000research.17921.r39217

The present study describes an methodology that classifies schizophrenia patients from healthy controls.
The study claims to demonstrate high classification accuracy.
The study has significant relevance to the neuroscience community however I have following concerns:

The functional significance of the brain regions involved needs to be elaborated so that their activation could be validated. The description of the role of obtained brain regions in schizophrenia patients and healthy individuals will indicate that the obtained regions are actually involved in schizophrenic patients and not a result of Type II error.
It will be good to provide some details about the demographics, level of education, duration of disease, medication history of the participants in order to evaluate the role of these confounding factors in the obtained results. These factors might cause some variation in the fMRI signals and just wondering if any of these parameters were taken as covariate in the analysis.
The fMRI signals obtained are task state and not resting state. These signals were obtained while doing oddball paradigm. So, I was wondering whether such classification would apply to schizophrenia patients only when they are doing this particular task, or it would apply to all schizophrenic patients irrespective of their state.

Is the work clearly and accurately presented and does it cite the current literature?

Yes
Is the study design appropriate and is the work technically sound?

Yes
Are sufficient details of methods and analysis provided to allow replication by others?

Yes
If applicable, is the statistical analysis and its interpretation appropriate?

I cannot comment. A qualified statistician is required.
Are all the source data underlying the results available to ensure full reproducibility?

Yes
Are the conclusions drawn adequately supported by the results?

Partly

Competing Interests: I know the author personally from a conference

I confirm that I have read this submission and believe that I have an appropriate level of expertise to confirm that it is of an acceptable scientific standard, however I have significant reservations, as outlined above.

CITE

Report a concern

Author Response 20 Dec 2018

Indranath Chatterjee, Department of Computer Science, University of Delhi, Delhi, 110007, India

20 Dec 2018

Author Response

I am thankful to the respected referee for her insightful comments and valuable suggestions.

I have updated the manuscript in accordance with the suggestions and queries. The suggested changes ... Continue reading I am thankful to the respected referee for her insightful comments and valuable suggestions.

I have updated the manuscript in accordance with the suggestions and queries. The suggested changes are made in the discussion section of the revised manuscript. I have also included some demographic details of the subjects in the dataset table. As I have not incorporated any covariates in this study, the limitation and the scope of future works are added in the discussion section.
I am thankful to the respected referee for her insightful comments and valuable suggestions.

I have updated the manuscript in accordance with the suggestions and queries. The suggested changes are made in the discussion section of the revised manuscript. I have also included some demographic details of the subjects in the dataset table. As I have not incorporated any covariates in this study, the limitation and the scope of future works are added in the discussion section.
Competing Interests: No competing interests were disclosed. Close
Report a concern
Respond or Comment

COMMENTS ON THIS REPORT

Author Response 20 Dec 2018

Indranath Chatterjee, Department of Computer Science, University of Delhi, Delhi, 110007, India

20 Dec 2018

Author Response

I am thankful to the respected referee for her insightful comments and valuable suggestions.

I have updated the manuscript in accordance with the suggestions and queries. The suggested changes ... Continue reading I am thankful to the respected referee for her insightful comments and valuable suggestions.

I have updated the manuscript in accordance with the suggestions and queries. The suggested changes are made in the discussion section of the revised manuscript. I have also included some demographic details of the subjects in the dataset table. As I have not incorporated any covariates in this study, the limitation and the scope of future works are added in the discussion section.
I am thankful to the respected referee for her insightful comments and valuable suggestions.

I have updated the manuscript in accordance with the suggestions and queries. The suggested changes are made in the discussion section of the revised manuscript. I have also included some demographic details of the subjects in the dataset table. As I have not incorporated any covariates in this study, the limitation and the scope of future works are added in the discussion section.
Competing Interests: No competing interests were disclosed. Close
Report a concern

Views

Reviewer Report 01 Nov 2018

Sahil Bajaj, Social, Cognitive and Affective Neuroscience Laboratory (SCAN Lab), Department of Psychiatry, College of Medicine, University of Arizona, Tucson, AZ, USA

Approved

https://doi.org/10.5256/f1000research.17921.r39310

Here author describes an interesting algorithm to identify the activated brain voxels affected in schizophrenia from time-series fMRI data.

I think this is an interesting paper and a nice example which can be implemented in more severe cases of mental ... Continue reading

How did the author remove the effect of gender, I noticed that there are way more males in the data than females.
I can see some voxels outside the brain and which are at the skull. I am not sure why did the author get those voxels and if the author made any effort to exclude those voxels?

Is the work clearly and accurately presented and does it cite the current literature?

Yes
Is the study design appropriate and is the work technically sound?

Yes
Are sufficient details of methods and analysis provided to allow replication by others?

Yes
If applicable, is the statistical analysis and its interpretation appropriate?

Yes
Are all the source data underlying the results available to ensure full reproducibility?

Yes
Are the conclusions drawn adequately supported by the results?

Yes

Competing Interests: No competing interests were disclosed.

I confirm that I have read this submission and believe that I have an appropriate level of expertise to confirm that it is of an acceptable scientific standard.

CITE

Report a concern

Respond or Comment

Comments on this article Comments (0)

Version 2

VERSION 2 PUBLISHED 08 Oct 2018

Open Peer Review

Reviewer Status

Reviewer Reports

	Invited Reviewers
	1	2
Version 2 (revision) 20 Dec 18		read
Version 1 08 Oct 18	read	read

Sahil Bajaj, University of Arizona, Tucson, USA
Sagarika Bhattacharjee, Nanyang Technological University, Singapore, Singapore

Comments on this article

All Comments(0)

Add a comment

Browse by related subjects

Back to all reports

Reviewer Report

13 Views

16 Jan 2019 | for Version 2

Sagarika Bhattacharjee, Department of Psychology, Nanyang Technological University, Singapore, Singapore

13 Views Cite this report Responses(0)

Approved

I thank the author for making the revision.

Competing Interests

I know the author personally from a conference.

I confirm that I have read this submission and believe that I have an appropriate level of expertise to confirm that it is of an acceptable scientific standard.

Respond to this report

Responses (0)

Back to all reports

Reviewer Report

25 Views

22 Nov 2018 | for Version 1

Sagarika Bhattacharjee, Department of Psychology, Nanyang Technological University, Singapore, Singapore

25 Views Cite this report Responses(1)

Approved With Reservations

The functional significance of the brain regions involved needs to be elaborated so that their activation could be validated. The description of the role of obtained brain regions in schizophrenia patients and healthy individuals will indicate that the obtained regions are actually involved in schizophrenic patients and not a result of Type II error.
It will be good to provide some details about the demographics, level of education, duration of disease, medication history of the participants in order to evaluate the role of these confounding factors in the obtained results. These factors might cause some variation in the fMRI signals and just wondering if any of these parameters were taken as covariate in the analysis.
The fMRI signals obtained are task state and not resting state. These signals were obtained while doing oddball paradigm. So, I was wondering whether such classification would apply to schizophrenia patients only when they are doing this particular task, or it would apply to all schizophrenic patients irrespective of their state.

Is the work clearly and accurately presented and does it cite the current literature?

Yes
Is the study design appropriate and is the work technically sound?

Yes
Are sufficient details of methods and analysis provided to allow replication by others?

Yes
If applicable, is the statistical analysis and its interpretation appropriate?

I cannot comment. A qualified statistician is required.
Are all the source data underlying the results available to ensure full reproducibility?

Yes
Are the conclusions drawn adequately supported by the results?

Partly

Competing Interests

I know the author personally from a conference

Respond to this report

Responses (1)

Author Response

20 Dec 2018

Indranath Chatterjee, Department of Computer Science, University of Delhi, Delhi, 110007, India

I am thankful to the respected referee for her insightful comments and valuable suggestions.

I have updated the manuscript in accordance with the suggestions and queries. The suggested changes are made in the discussion section of the revised manuscript. I have also included some demographic details of the subjects in the dataset table. As I have not incorporated any covariates in this study, the limitation and the scope of future works are added in the discussion section.

View more View less

Competing Interests

No competing interests were disclosed.

Back to all reports

Reviewer Report

21 Views

01 Nov 2018 | for Version 1

Sahil Bajaj, Social, Cognitive and Affective Neuroscience Laboratory (SCAN Lab), Department of Psychiatry, College of Medicine, University of Arizona, Tucson, AZ, USA

21 Views Cite this report Responses(0)

Approved

How did the author remove the effect of gender, I noticed that there are way more males in the data than females.
I can see some voxels outside the brain and which are at the skull. I am not sure why did the author get those voxels and if the author made any effort to exclude those voxels?

Is the work clearly and accurately presented and does it cite the current literature?

Yes
Is the study design appropriate and is the work technically sound?

Yes
Are sufficient details of methods and analysis provided to allow replication by others?

Yes
If applicable, is the statistical analysis and its interpretation appropriate?

Yes
Are all the source data underlying the results available to ensure full reproducibility?

Yes
Are the conclusions drawn adequately supported by the results?

Yes

Competing Interests

No competing interests were disclosed.

I confirm that I have read this submission and believe that I have an appropriate level of expertise to confirm that it is of an acceptable scientific standard.

Respond to this report

Responses (0)

Alongside their report, reviewers assign a status to the article:

Approved - the paper is scientifically sound in its current form and only minor, if any, improvements are suggested

Approved with reservations - A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.

Not approved - fundamental flaws in the paper seriously undermine the findings and conclusions

[1] 1. Friston KJ, Holmes AP, Worsley KJ, et al.: Statistical parametric maps in functional imaging: a general linear approach. Hum Brain Mapp. 1994; 2(4): 189–210. Publisher Full Text

[2] 2. Kim DI, Mathalon D, Ford JM, et al.: Auditory oddball deficits in schizophrenia: an independent component analysis of the fMRI multisite function BIRN study. Schizophren Bull. 2009; 35(1): 67–81. PubMed Abstract | Publisher Full Text | Free Full Text

[3] 3. Keator DB, van Erp TG, Turner JA, et al.: The Function Biomedical Informatics Research Network Data Repository. NeuroImage. 2016; 124(Pt B): 1074–1079. PubMed Abstract | Publisher Full Text | Free Full Text

[4] 4. Lancaster JL, Woldorff MG, Parsons LM, et al.: Automated Talairach atlas labels for functional brain mapping. Hum Brain Mapp. 2000; 10(3): 120–131. PubMed Abstract | Publisher Full Text

[5] 5. Cortes C, Vapnik V: Support-vector networks. Mach Learn. 1995; 20(3): 273–297. Publisher Full Text

[6] 6. Huang GB, Zhu QY, Siew CK: Extreme learning machine: theory and applications. Neurocomputing. 2006; 70(1–3): 489–501. Publisher Full Text

[7] 7. Norman KA, Polyn SM, Detre GJ, et al.: Beyond mind-reading: multi-voxel pattern analysis of fMRI data. Trends Cogn Sci. 2006; 10(9): 424–430. PubMed Abstract | Publisher Full Text

[8] 8. Castro E, Gómez-Verdejo V, Martínez-Ramón M, et al.: A multiple kernel learning approach to perform classification of groups from complex-valued fMRI data analysis: application to schizophrenia. NeuroImage. 2014; 87: 1–17. PubMed Abstract | Publisher Full Text | Free Full Text

[9] 9. Garrity AG, Pearlson GD, McKiernan K, et al.: Aberrant “default mode” functional connectivity in schizophrenia. Am J Psychiatry. 2007; 164(3): 450–457. PubMed Abstract | Publisher Full Text

[10] 10. Gur RE, Gur RC: Functional magnetic resonance imaging in schizophrenia. Dialogues Clin Neurosci. 2010; 12(3): 333–343. PubMed Abstract | Free Full Text

[11] 11. Formisano E, De Martino F, Valente G: Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning. Magn Reson Imaging. 2008; 26(7): 921–934. PubMed Abstract | Publisher Full Text

[12] 12. De Martino F, Valente G, Staeren N, et al.: Combining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns. NeuroImage. 2008; 43(1): 44–58. PubMed Abstract | Publisher Full Text

[13] 13. Hof PR, Haroutunian V, Friedrich VL Jr, et al.: Loss and altered spatial distribution of oligodendrocytes in the superior frontal gyrus in schizophrenia. Biol Psychiatry. 2003; 53(12): 1075–1085. PubMed Abstract | Publisher Full Text

[14] 14. Chatterjee I, Agarwal M, Rana B, et al.: Bi-objective approach for computer-aided diagnosis of schizophrenia patients using fMRI data. Multimed Tools Appl. 2018; 77(20): 26991–27015. Publisher Full Text

[15] 15. Hoptman MJ, Zuo XN, Butler PD, et al.: Amplitude of low-frequency oscillations in schizophrenia: a resting state fMRI study. Schizophr Res. 2010; 117(1): 13–20. PubMed Abstract | Publisher Full Text | Free Full Text

[16] 16. Vercammen A, Knegtering H, den Boer JA, et al.: Auditory hallucinations in schizophrenia are associated with reduced functional connectivity of the temporo-parietal area. Biol Psychiatry. 2010; 67(10): 912–918. PubMed Abstract | Publisher Full Text

[17] 17. Carter CS, Mintun M, Nichols T, et al.: Anterior cingulate gyrus dysfunction and selective attention deficits in schizophrenia: [¹⁵O]H₂O PET study during single-trial Stroop task performance. Am J Psychiatry. 1997; 154(12): 1670–1675. PubMed Abstract | Publisher Full Text

[18] 18. Brunet E, Sarfati Y, Hardy-Baylé MC, et al.: Abnormalities of brain function during a nonverbal theory of mind task in schizophrenia. Neuropsychologia. 2003; 41(12): 1574–1582. PubMed Abstract | Publisher Full Text

[19] 19. Camchong J, Dyckman KA, Austin BP, et al.: Common neural circuitry supporting volitional saccades and its disruption in schizophrenia patients and relatives. Biol Psychiatry. 2008; 64(12): 1042–1050. PubMed Abstract | Publisher Full Text | Free Full Text

[20] 20. Chatterjee I: Feature selection technique for time-series fMRI data of schizophrenia patients [Source Code]. Zenodo. 2018. http://www.doi.org/10.5281/zenodo.1438539

Mean deviation based identification of activated voxels from time-series fMRI data of schizophrenia patients

Abstract

Keywords

Introduction

Methods

fMRI data

Table 1. Dataset details.

Data analysis

Algorithm 1. The proposed approach

Results

Table 2. Comparison showing classification accuracy with feature set obtained after GLM and the proposed approach using SVM and ELM classifiers.

Figure 1.

Figure 2.

Discussion

Conclusions

Data availability

Author endorsement

Grant information

Acknowledgments

References

Comments on this article Comments (0)

Open Peer Review

Comments on this article Comments (0)

Open Peer Review

Reviewer Status

Reviewer Reports

Comments on this article

Browse by related subjects

Competing Interests Policy

Stay Updated