Discriminating brain activated area and predicting the stimuli performed using artificial neural network

In this work, a Multilayer Perceptron implementation MLP using functional Magnetic Resonance Imaging (fMRI) is used to infer stimuli performed. Sets of images of brain activation were generated by visual, auditory and finger tapping paradigms in 54 healthy volunteers. These images were used for...

Full description

Bibliographic Details
Main Authors: Rafael do Espírito Santo, João Ricardo Sato, Maria G. Moraes Martin
Format: Article
Language:Portuguese
Published: Universidade Nove de Julho 2007-01-01
Series:Exacta
Online Access:http://www.redalyc.org/articulo.oa?id=81050213
id doaj-40128401d27140a7aefb731a32bc5014
record_format Article
spelling doaj-40128401d27140a7aefb731a32bc50142020-11-25T01:40:12ZporUniversidade Nove de JulhoExacta1678-54281983-93082007-01-0152311320Discriminating brain activated area and predicting the stimuli performed using artificial neural networkRafael do Espírito SantoJoão Ricardo SatoMaria G. Moraes MartinIn this work, a Multilayer Perceptron implementation MLP using functional Magnetic Resonance Imaging (fMRI) is used to infer stimuli performed. Sets of images of brain activation were generated by visual, auditory and finger tapping paradigms in 54 healthy volunteers. These images were used for training the MLP network in a leave-one-out manner in order to predict the paradigm that a subject performed by using other images, so far unseen by the MLP network. The aim in this paper is the exploring of the influence of the number of the Principal Component (PC) on the performance of the MLP in classifying fMRI paradigms. The classifier´s performance was evaluated in terms of the Sensitivity and Specificity, Prediction Accuracy and the area Az under the receiver operating characteristics (ROC) curve. From the ROC analysis, values of Az up to 1 were obtained with 60 PCs in discriminating the visual paradigm from the auditory paradigm.http://www.redalyc.org/articulo.oa?id=81050213
collection DOAJ
language Portuguese
format Article
sources DOAJ
author Rafael do Espírito Santo
João Ricardo Sato
Maria G. Moraes Martin
spellingShingle Rafael do Espírito Santo
João Ricardo Sato
Maria G. Moraes Martin
Discriminating brain activated area and predicting the stimuli performed using artificial neural network
Exacta
author_facet Rafael do Espírito Santo
João Ricardo Sato
Maria G. Moraes Martin
author_sort Rafael do Espírito Santo
title Discriminating brain activated area and predicting the stimuli performed using artificial neural network
title_short Discriminating brain activated area and predicting the stimuli performed using artificial neural network
title_full Discriminating brain activated area and predicting the stimuli performed using artificial neural network
title_fullStr Discriminating brain activated area and predicting the stimuli performed using artificial neural network
title_full_unstemmed Discriminating brain activated area and predicting the stimuli performed using artificial neural network
title_sort discriminating brain activated area and predicting the stimuli performed using artificial neural network
publisher Universidade Nove de Julho
series Exacta
issn 1678-5428
1983-9308
publishDate 2007-01-01
description In this work, a Multilayer Perceptron implementation MLP using functional Magnetic Resonance Imaging (fMRI) is used to infer stimuli performed. Sets of images of brain activation were generated by visual, auditory and finger tapping paradigms in 54 healthy volunteers. These images were used for training the MLP network in a leave-one-out manner in order to predict the paradigm that a subject performed by using other images, so far unseen by the MLP network. The aim in this paper is the exploring of the influence of the number of the Principal Component (PC) on the performance of the MLP in classifying fMRI paradigms. The classifier´s performance was evaluated in terms of the Sensitivity and Specificity, Prediction Accuracy and the area Az under the receiver operating characteristics (ROC) curve. From the ROC analysis, values of Az up to 1 were obtained with 60 PCs in discriminating the visual paradigm from the auditory paradigm.
url http://www.redalyc.org/articulo.oa?id=81050213
work_keys_str_mv AT rafaeldoespiritosanto discriminatingbrainactivatedareaandpredictingthestimuliperformedusingartificialneuralnetwork
AT joaoricardosato discriminatingbrainactivatedareaandpredictingthestimuliperformedusingartificialneuralnetwork
AT mariagmoraesmartin discriminatingbrainactivatedareaandpredictingthestimuliperformedusingartificialneuralnetwork
_version_ 1725046459211972608