Attention Deficit Hyperactivity Disorder identification: FMRI data analyzed with CNN and seed-based approach

Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent mental disorder affecting both adults and children, frequently leading to academic difficulties. This study aims to improve the diagnosis of ADHD in children by using resting-state Functional Magnetic Resonance Imaging (fMRI) data. The m...

Full description

Saved in:
Bibliographic Details
Main Authors: Anika Siamin Oyshi, Mohammad Hasan, Md. Khabir Uddin Ahamed, Md. Sydur Rahman, Md. Mahfuzul Haque, Mahmudul Alam
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Brain Disorders
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666459325000186
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344674099101696
author Anika Siamin Oyshi
Mohammad Hasan
Md. Khabir Uddin Ahamed
Md. Sydur Rahman
Md. Mahfuzul Haque
Mahmudul Alam
author_facet Anika Siamin Oyshi
Mohammad Hasan
Md. Khabir Uddin Ahamed
Md. Sydur Rahman
Md. Mahfuzul Haque
Mahmudul Alam
author_sort Anika Siamin Oyshi
collection DOAJ
description Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent mental disorder affecting both adults and children, frequently leading to academic difficulties. This study aims to improve the diagnosis of ADHD in children by using resting-state Functional Magnetic Resonance Imaging (fMRI) data. The method use seed coherence to identify functional connections between specific seed areas and all brain voxels, focusing on Default Mode Network (DMN) regions pertinent to the diagnosis of ADHD. Convolutional Neural Networks (CNNs) are utilized in classification tasks because of their capacity to learn intricate spatial hierarchies. The research utilizes fMRI scans from the ADHD 200 - Global Competitive dataset, comprising 776 subjects from three prominent data centers. The methodology entails data preparation, feature extraction via seed-based correlation, and classification with Convolutional Neural Networks (CNNs). Three classifiers were assessed: a Neural Network (Keras Sequential Model), a Support Vector Machine (SVM), and a Random Forest Classifier. The optimal outcome was achieved by the neural network, which harmonized precision, recall, and F1 scores, attaining an accuracy of 97 %. The SVM demonstrated considerable accuracy at 83 %, however the Random Forest Classifier exhibited a mere 50 % accuracy, underscoring the necessity for enhancement. These results underscore the merits and shortcomings of each classifier and offer suggestions for enhancement. The paper highlights the significance of Neural Networks for attaining precise and equitable forecasts, proposes enhancements for the Support Vector Machine, and stresses the imperative of optimizing the Random Forest Classifier. This study enhances ADHD diagnosis by methodically employing neuroimaging techniques and assessing several classifiers, leading to a reliable diagnostic system.
format Article
id doaj-art-aa8151c1edcd4861903980086f5077de
institution Kabale University
issn 2666-4593
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Brain Disorders
spelling doaj-art-aa8151c1edcd4861903980086f5077de2025-08-20T03:42:37ZengElsevierBrain Disorders2666-45932025-03-011710019810.1016/j.dscb.2025.100198Attention Deficit Hyperactivity Disorder identification: FMRI data analyzed with CNN and seed-based approachAnika Siamin Oyshi0Mohammad Hasan1Md. Khabir Uddin Ahamed2Md. Sydur Rahman3Md. Mahfuzul Haque4Mahmudul Alam5Department of Computer Science and Engineering, Jamalpur Science and Technology University, Jamalpur-2012, BangladeshDepartment of Computer Science and Engineering, Jamalpur Science and Technology University, Jamalpur-2012, BangladeshDepartment of Computer Science and Engineering, Jamalpur Science and Technology University, Jamalpur-2012, BangladeshDepartment of Computer Science and Engineering, Jamalpur Science and Technology University, Jamalpur-2012, BangladeshDepartment of Electrical and Electronic Engineering, Jamalpur Science and Technology University, Jamalpur-2012, BangladeshDepartment of Computer Science and Engineering, Jamalpur Science and Technology University, Jamalpur-2012, Bangladesh; Corresponding author.Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent mental disorder affecting both adults and children, frequently leading to academic difficulties. This study aims to improve the diagnosis of ADHD in children by using resting-state Functional Magnetic Resonance Imaging (fMRI) data. The method use seed coherence to identify functional connections between specific seed areas and all brain voxels, focusing on Default Mode Network (DMN) regions pertinent to the diagnosis of ADHD. Convolutional Neural Networks (CNNs) are utilized in classification tasks because of their capacity to learn intricate spatial hierarchies. The research utilizes fMRI scans from the ADHD 200 - Global Competitive dataset, comprising 776 subjects from three prominent data centers. The methodology entails data preparation, feature extraction via seed-based correlation, and classification with Convolutional Neural Networks (CNNs). Three classifiers were assessed: a Neural Network (Keras Sequential Model), a Support Vector Machine (SVM), and a Random Forest Classifier. The optimal outcome was achieved by the neural network, which harmonized precision, recall, and F1 scores, attaining an accuracy of 97 %. The SVM demonstrated considerable accuracy at 83 %, however the Random Forest Classifier exhibited a mere 50 % accuracy, underscoring the necessity for enhancement. These results underscore the merits and shortcomings of each classifier and offer suggestions for enhancement. The paper highlights the significance of Neural Networks for attaining precise and equitable forecasts, proposes enhancements for the Support Vector Machine, and stresses the imperative of optimizing the Random Forest Classifier. This study enhances ADHD diagnosis by methodically employing neuroimaging techniques and assessing several classifiers, leading to a reliable diagnostic system.http://www.sciencedirect.com/science/article/pii/S2666459325000186Attention Deficit Hyperactivity Disorder (ADHD)Functional Magnetic Resonance Imaging (fMRI)Default Mode Network (DMN)Seed-based correlation techniqueConvolutional Neural Network (CNN)Independent Component Analysis (ICA)
spellingShingle Anika Siamin Oyshi
Mohammad Hasan
Md. Khabir Uddin Ahamed
Md. Sydur Rahman
Md. Mahfuzul Haque
Mahmudul Alam
Attention Deficit Hyperactivity Disorder identification: FMRI data analyzed with CNN and seed-based approach
Brain Disorders
Attention Deficit Hyperactivity Disorder (ADHD)
Functional Magnetic Resonance Imaging (fMRI)
Default Mode Network (DMN)
Seed-based correlation technique
Convolutional Neural Network (CNN)
Independent Component Analysis (ICA)
title Attention Deficit Hyperactivity Disorder identification: FMRI data analyzed with CNN and seed-based approach
title_full Attention Deficit Hyperactivity Disorder identification: FMRI data analyzed with CNN and seed-based approach
title_fullStr Attention Deficit Hyperactivity Disorder identification: FMRI data analyzed with CNN and seed-based approach
title_full_unstemmed Attention Deficit Hyperactivity Disorder identification: FMRI data analyzed with CNN and seed-based approach
title_short Attention Deficit Hyperactivity Disorder identification: FMRI data analyzed with CNN and seed-based approach
title_sort attention deficit hyperactivity disorder identification fmri data analyzed with cnn and seed based approach
topic Attention Deficit Hyperactivity Disorder (ADHD)
Functional Magnetic Resonance Imaging (fMRI)
Default Mode Network (DMN)
Seed-based correlation technique
Convolutional Neural Network (CNN)
Independent Component Analysis (ICA)
url http://www.sciencedirect.com/science/article/pii/S2666459325000186
work_keys_str_mv AT anikasiaminoyshi attentiondeficithyperactivitydisorderidentificationfmridataanalyzedwithcnnandseedbasedapproach
AT mohammadhasan attentiondeficithyperactivitydisorderidentificationfmridataanalyzedwithcnnandseedbasedapproach
AT mdkhabiruddinahamed attentiondeficithyperactivitydisorderidentificationfmridataanalyzedwithcnnandseedbasedapproach
AT mdsydurrahman attentiondeficithyperactivitydisorderidentificationfmridataanalyzedwithcnnandseedbasedapproach
AT mdmahfuzulhaque attentiondeficithyperactivitydisorderidentificationfmridataanalyzedwithcnnandseedbasedapproach
AT mahmudulalam attentiondeficithyperactivitydisorderidentificationfmridataanalyzedwithcnnandseedbasedapproach