Deep transformation method for discriminant analysis of multi-channel resting state fMRI

Analysis of resting state - functional Magnetic Resonance Imaging (rs-fMRI) data has been a challenging problem due to a high homogeneity, large intra-class variability, limited samples and difference in acquisition technologies/techniques. These issues are predominant in the case of Attention Defic...

Full description

Saved in:
Bibliographic Details
Main Authors: Aradhya, Abhay M S, Joglekar, Aditya, Suresh, Sundaram, Pratama, Mahardhika
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/138475
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-138475
record_format dspace
spelling sg-ntu-dr.10356-1384752020-05-06T08:53:51Z Deep transformation method for discriminant analysis of multi-channel resting state fMRI Aradhya, Abhay M S Joglekar, Aditya Suresh, Sundaram Pratama, Mahardhika School of Computer Science and Engineering Engineering::Computer science and engineering Resting State-fMRI Deep Transformation Method Analysis of resting state - functional Magnetic Resonance Imaging (rs-fMRI) data has been a challenging problem due to a high homogeneity, large intra-class variability, limited samples and difference in acquisition technologies/techniques. These issues are predominant in the case of Attention Deficit Hyperactivity Disorder (ADHD). In this paper, we propose a new Deep Transformation Method (DTM) that extracts the discriminant latent feature space from rsfMRI and projects it in the subsequent layer for classification of rs-fMRI data. The hidden transformation layer in DTM projects the original rs-fMRI data into a new space using the learning policy and extracts the spatio-temporal correlations of the functional activities as a latent feature space. The subsequent convolution and decision layers transform the latent feature space into high-level features and provide accurate classification. The performance of DTM has been evaluated using the ADHD200 rs-fMRI benchmark data with crossvalidation. The results show that the proposed DTM achieves a mean classification accuracy of 70.36% and an improvement of 8.25% on the state of the art methodologies was observed. The improvement is due to concurrent analysis of the spatio-temporal correlations between the different regions of the brain and can be easily extended to study other cognitive disorders using rs-fMRI. Further, brain network analysis has been studied to identify the difference in functional activities and the corresponding regions behind cognitive symptoms in ADHD. Accepted version 2020-05-06T08:53:51Z 2020-05-06T08:53:51Z 2019 Journal Article Aradhya, A. M. S., Joglekar, A., Suresh, S., & Pratama, M. (2019). Deep transformation method for discriminant analysis of multi-channel resting state fMRI. Proceedings of the AAAI Conference on Artificial Intelligence, 33(1), 2556–2563. doi:10.1609/aaai.v33i01.33012556 2159-5399 https://hdl.handle.net/10356/138475 10.1609/aaai.v33i01.33012556 1 33 2556 2563 en Proceedings of the AAAI Conference on Artificial Intelligence © 2019 Association for the Advancement of Artificial Intelligence. All rights reserved. This paper was published in Proceedings of the AAAI Conference on Artificial Intelligence and is made available with permission of Association for the Advancement of Artificial Intelligence. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Resting State-fMRI
Deep Transformation Method
spellingShingle Engineering::Computer science and engineering
Resting State-fMRI
Deep Transformation Method
Aradhya, Abhay M S
Joglekar, Aditya
Suresh, Sundaram
Pratama, Mahardhika
Deep transformation method for discriminant analysis of multi-channel resting state fMRI
description Analysis of resting state - functional Magnetic Resonance Imaging (rs-fMRI) data has been a challenging problem due to a high homogeneity, large intra-class variability, limited samples and difference in acquisition technologies/techniques. These issues are predominant in the case of Attention Deficit Hyperactivity Disorder (ADHD). In this paper, we propose a new Deep Transformation Method (DTM) that extracts the discriminant latent feature space from rsfMRI and projects it in the subsequent layer for classification of rs-fMRI data. The hidden transformation layer in DTM projects the original rs-fMRI data into a new space using the learning policy and extracts the spatio-temporal correlations of the functional activities as a latent feature space. The subsequent convolution and decision layers transform the latent feature space into high-level features and provide accurate classification. The performance of DTM has been evaluated using the ADHD200 rs-fMRI benchmark data with crossvalidation. The results show that the proposed DTM achieves a mean classification accuracy of 70.36% and an improvement of 8.25% on the state of the art methodologies was observed. The improvement is due to concurrent analysis of the spatio-temporal correlations between the different regions of the brain and can be easily extended to study other cognitive disorders using rs-fMRI. Further, brain network analysis has been studied to identify the difference in functional activities and the corresponding regions behind cognitive symptoms in ADHD.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Aradhya, Abhay M S
Joglekar, Aditya
Suresh, Sundaram
Pratama, Mahardhika
format Article
author Aradhya, Abhay M S
Joglekar, Aditya
Suresh, Sundaram
Pratama, Mahardhika
author_sort Aradhya, Abhay M S
title Deep transformation method for discriminant analysis of multi-channel resting state fMRI
title_short Deep transformation method for discriminant analysis of multi-channel resting state fMRI
title_full Deep transformation method for discriminant analysis of multi-channel resting state fMRI
title_fullStr Deep transformation method for discriminant analysis of multi-channel resting state fMRI
title_full_unstemmed Deep transformation method for discriminant analysis of multi-channel resting state fMRI
title_sort deep transformation method for discriminant analysis of multi-channel resting state fmri
publishDate 2020
url https://hdl.handle.net/10356/138475
_version_ 1681058595218653184