Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks

The emergence of convolutional neural networks (CNN) in various fields has also paved numerous ways for advancement in the field of medical imaging. This paper focuses on functional magnetic resonance imaging (fMRI) in the field of neuroimaging. It has high temporal resolution and robust to control...

Full description

Bibliographic Details
Main Authors:	Suhaimi, Farahana, Htike@Muhammad Yusof, Zaw Zaw
Format:	Article
Language:	English English
Published:	Science Gate 2018
Subjects:	Q350 Information theory
Online Access:	http://irep.iium.edu.my/69669/ http://irep.iium.edu.my/69669/ http://irep.iium.edu.my/69669/13/69669%20Feature%20map%20size%20selection%20for%20fMRI%20classification%20on%20end-to-end%20deep%20convolutional%20neural%20networks_wos.pdf http://irep.iium.edu.my/69669/19/69669_Feature%20map%20size%20selection%20for%20fMRI%20classification%20on%20end-to-end%20deep%20convolutional%20neural%20networks_ARTICLE.pdf

id	iium-69669
recordtype	eprints
spelling	iium-696692019-01-31T03:36:17Z http://irep.iium.edu.my/69669/ Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks Suhaimi, Farahana Htike@Muhammad Yusof, Zaw Zaw Q350 Information theory The emergence of convolutional neural networks (CNN) in various fields has also paved numerous ways for advancement in the field of medical imaging. This paper focuses on functional magnetic resonance imaging (fMRI) in the field of neuroimaging. It has high temporal resolution and robust to control or non-control subjects. CNN analysis on structural magnetic resonance imaging (MRI) and fMRI datasets is compared to rule out one of the grey areas in building CNNs for medical imaging analysis. This study focuses on the feature map size selection on fMRI datasets with CNNs where the selected sizes are evaluated for their performances. Although few outstanding studies on fMRI have been published, the availability of diverse previous studies on MRI previous works impulses us to study to learn the pattern of feature map sizes for CNN configuration. Six configurations are analyzed with prominent public fMRI dataset, names as Human Connectome Project (HCP). This dataset is widely used for any type of fMRI classification. With three set of data divisions, the accuracy values for validation set of fMRI classification are assessed and discussed. Despite the fact that only one slice of every 118 subjects' temporal brain images is used in the study, the validation of classification for three training-excluded subjects known as validation set, has proven the need for feature map size selection. This paper emphasizes the indispensable step of selecting the feature map sizes when designing CNN for fMRI classification. In addition, we provide proofs that validation set should consist of distinct subjects for definite evaluation of any model performance. Science Gate 2018-12 Article PeerReviewed application/pdf en http://irep.iium.edu.my/69669/13/69669%20Feature%20map%20size%20selection%20for%20fMRI%20classification%20on%20end-to-end%20deep%20convolutional%20neural%20networks_wos.pdf application/pdf en http://irep.iium.edu.my/69669/19/69669_Feature%20map%20size%20selection%20for%20fMRI%20classification%20on%20end-to-end%20deep%20convolutional%20neural%20networks_ARTICLE.pdf Suhaimi, Farahana and Htike@Muhammad Yusof, Zaw Zaw (2018) Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks. International Journal of Advanced and Applied Sciences, 5 (8). pp. 95-103. ISSN 2313-626X E-ISSN 2313-3724 http://www.science-gate.com/IJAAS/2018/V5I8/Suhaimi.html
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English English
topic	Q350 Information theory
spellingShingle	Q350 Information theory Suhaimi, Farahana Htike@Muhammad Yusof, Zaw Zaw Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks
description	The emergence of convolutional neural networks (CNN) in various fields has also paved numerous ways for advancement in the field of medical imaging. This paper focuses on functional magnetic resonance imaging (fMRI) in the field of neuroimaging. It has high temporal resolution and robust to control or non-control subjects. CNN analysis on structural magnetic resonance imaging (MRI) and fMRI datasets is compared to rule out one of the grey areas in building CNNs for medical imaging analysis. This study focuses on the feature map size selection on fMRI datasets with CNNs where the selected sizes are evaluated for their performances. Although few outstanding studies on fMRI have been published, the availability of diverse previous studies on MRI previous works impulses us to study to learn the pattern of feature map sizes for CNN configuration. Six configurations are analyzed with prominent public fMRI dataset, names as Human Connectome Project (HCP). This dataset is widely used for any type of fMRI classification. With three set of data divisions, the accuracy values for validation set of fMRI classification are assessed and discussed. Despite the fact that only one slice of every 118 subjects' temporal brain images is used in the study, the validation of classification for three training-excluded subjects known as validation set, has proven the need for feature map size selection. This paper emphasizes the indispensable step of selecting the feature map sizes when designing CNN for fMRI classification. In addition, we provide proofs that validation set should consist of distinct subjects for definite evaluation of any model performance.
format	Article
author	Suhaimi, Farahana Htike@Muhammad Yusof, Zaw Zaw
author_facet	Suhaimi, Farahana Htike@Muhammad Yusof, Zaw Zaw
author_sort	Suhaimi, Farahana
title	Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks
title_short	Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks
title_full	Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks
title_fullStr	Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks
title_full_unstemmed	Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks
title_sort	feature map size selection for fmri classification on end-to-end deep convolutional neural networks
publisher	Science Gate
publishDate	2018
url	http://irep.iium.edu.my/69669/ http://irep.iium.edu.my/69669/ http://irep.iium.edu.my/69669/13/69669%20Feature%20map%20size%20selection%20for%20fMRI%20classification%20on%20end-to-end%20deep%20convolutional%20neural%20networks_wos.pdf http://irep.iium.edu.my/69669/19/69669_Feature%20map%20size%20selection%20for%20fMRI%20classification%20on%20end-to-end%20deep%20convolutional%20neural%20networks_ARTICLE.pdf
first_indexed	2023-09-18T21:38:53Z
last_indexed	2023-09-18T21:38:53Z
_version_	1777413006305525760

Feature map size selection for fMRI classification on end-to-end deep convolutional neural networks

Similar Items