Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity Disorder
<b>Background:</b> According to the World Health Organization (WHO), approximately 5% of children and 2.5% of adults suffer from attention deficit hyperactivity disorder (ADHD). This disorder can have significant negative consequences on people’s lives, particularly children. In recent y...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Tomography |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2379-139X/11/5/56 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849718911429246976 |
|---|---|
| author | Elahe Hosseini Seyyed Ali Hosseini Stijn Servaes Brandon Hall Pedro Rosa-Neto Ali-Reza Moradi Ajay Kumar Mir Mohsen Pedram Sanjeev Chawla |
| author_facet | Elahe Hosseini Seyyed Ali Hosseini Stijn Servaes Brandon Hall Pedro Rosa-Neto Ali-Reza Moradi Ajay Kumar Mir Mohsen Pedram Sanjeev Chawla |
| author_sort | Elahe Hosseini |
| collection | DOAJ |
| description | <b>Background:</b> According to the World Health Organization (WHO), approximately 5% of children and 2.5% of adults suffer from attention deficit hyperactivity disorder (ADHD). This disorder can have significant negative consequences on people’s lives, particularly children. In recent years, methods based on artificial intelligence and neuroimaging techniques, such as MRI, have made significant progress, paving the way for development of more reliable diagnostic tools. In this proof of concept study, our aim was to investigate the potential utility of neuroimaging data and clinical information in combination with a deep learning-based analytical approach, more precisely, a novel feature extraction technique for the diagnosis of ADHD with high accuracy. <b>Methods:</b> Leveraging the ADHD200 dataset, which encompasses demographic information and anatomical MRI scans collected from a diverse ADHD population, our study focused on developing modern deep learning-based diagnostic models. The data preprocessing employed a pre-trained Visual Geometry Group16 (VGG16) network to extract two-dimensional (2D) feature maps from three-dimensional (3D) anatomical MRI data to reduce computational complexity and enhance diagnostic power. The inclusion of personal attributes, such as age, gender, intelligence quotient, and handedness, strengthens the diagnostic models. Four deep-learning architectures—convolutional neural network 2D (CNN2D), CNN1D, long short-term memory (LSTM), and gated recurrent units (GRU)—were employed for analysis of the MRI data, with and without the inclusion of clinical characteristics. <b>Results:</b> A 10-fold cross-validation test revealed that the LSTM model, which incorporated both MRI data and personal attributes, had the best diagnostic performance among all tested models in the diagnosis of ADHD with an accuracy of 0.86 and area under the receiver operating characteristic (ROC) curve (AUC) score of 0.90. <b>Conclusions:</b> Our findings demonstrate that the proposed approach of extracting 2D features from 3D MRI images and integrating these features with clinical characteristics may be useful in the diagnosis of ADHD with high accuracy. |
| format | Article |
| id | doaj-art-caa4a2f0a1304f33877bb97b74c03e01 |
| institution | DOAJ |
| issn | 2379-1381 2379-139X |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tomography |
| spelling | doaj-art-caa4a2f0a1304f33877bb97b74c03e012025-08-20T03:12:15ZengMDPI AGTomography2379-13812379-139X2025-05-011155610.3390/tomography11050056Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity DisorderElahe Hosseini0Seyyed Ali Hosseini1Stijn Servaes2Brandon Hall3Pedro Rosa-Neto4Ali-Reza Moradi5Ajay Kumar6Mir Mohsen Pedram7Sanjeev Chawla8Department of Electrical and Computer Engineering, Kharazmi University, Tehran 15719-14911, IranTranslational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montréal, QC H4H 1R3, CanadaTranslational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montréal, QC H4H 1R3, CanadaTranslational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montréal, QC H4H 1R3, CanadaTranslational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montréal, QC H4H 1R3, CanadaDepartment of Clinical Psychology, Kharazmi University, Tehran 15719-14911, IranDepartment of Radiology, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA 19104, USADepartment of Electrical and Computer Engineering, Kharazmi University, Tehran 15719-14911, IranDepartment of Radiology, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA 19104, USA<b>Background:</b> According to the World Health Organization (WHO), approximately 5% of children and 2.5% of adults suffer from attention deficit hyperactivity disorder (ADHD). This disorder can have significant negative consequences on people’s lives, particularly children. In recent years, methods based on artificial intelligence and neuroimaging techniques, such as MRI, have made significant progress, paving the way for development of more reliable diagnostic tools. In this proof of concept study, our aim was to investigate the potential utility of neuroimaging data and clinical information in combination with a deep learning-based analytical approach, more precisely, a novel feature extraction technique for the diagnosis of ADHD with high accuracy. <b>Methods:</b> Leveraging the ADHD200 dataset, which encompasses demographic information and anatomical MRI scans collected from a diverse ADHD population, our study focused on developing modern deep learning-based diagnostic models. The data preprocessing employed a pre-trained Visual Geometry Group16 (VGG16) network to extract two-dimensional (2D) feature maps from three-dimensional (3D) anatomical MRI data to reduce computational complexity and enhance diagnostic power. The inclusion of personal attributes, such as age, gender, intelligence quotient, and handedness, strengthens the diagnostic models. Four deep-learning architectures—convolutional neural network 2D (CNN2D), CNN1D, long short-term memory (LSTM), and gated recurrent units (GRU)—were employed for analysis of the MRI data, with and without the inclusion of clinical characteristics. <b>Results:</b> A 10-fold cross-validation test revealed that the LSTM model, which incorporated both MRI data and personal attributes, had the best diagnostic performance among all tested models in the diagnosis of ADHD with an accuracy of 0.86 and area under the receiver operating characteristic (ROC) curve (AUC) score of 0.90. <b>Conclusions:</b> Our findings demonstrate that the proposed approach of extracting 2D features from 3D MRI images and integrating these features with clinical characteristics may be useful in the diagnosis of ADHD with high accuracy.https://www.mdpi.com/2379-139X/11/5/56ADHD diagnosis3D MRI to 2D feature mapsdeep learningVGG16 modelneuroimagingconvolutional neural networks |
| spellingShingle | Elahe Hosseini Seyyed Ali Hosseini Stijn Servaes Brandon Hall Pedro Rosa-Neto Ali-Reza Moradi Ajay Kumar Mir Mohsen Pedram Sanjeev Chawla Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity Disorder Tomography ADHD diagnosis 3D MRI to 2D feature maps deep learning VGG16 model neuroimaging convolutional neural networks |
| title | Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity Disorder |
| title_full | Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity Disorder |
| title_fullStr | Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity Disorder |
| title_full_unstemmed | Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity Disorder |
| title_short | Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity Disorder |
| title_sort | transforming 3d mri to 2d feature maps using pre trained models for diagnosis of attention deficit hyperactivity disorder |
| topic | ADHD diagnosis 3D MRI to 2D feature maps deep learning VGG16 model neuroimaging convolutional neural networks |
| url | https://www.mdpi.com/2379-139X/11/5/56 |
| work_keys_str_mv | AT elahehosseini transforming3dmrito2dfeaturemapsusingpretrainedmodelsfordiagnosisofattentiondeficithyperactivitydisorder AT seyyedalihosseini transforming3dmrito2dfeaturemapsusingpretrainedmodelsfordiagnosisofattentiondeficithyperactivitydisorder AT stijnservaes transforming3dmrito2dfeaturemapsusingpretrainedmodelsfordiagnosisofattentiondeficithyperactivitydisorder AT brandonhall transforming3dmrito2dfeaturemapsusingpretrainedmodelsfordiagnosisofattentiondeficithyperactivitydisorder AT pedrorosaneto transforming3dmrito2dfeaturemapsusingpretrainedmodelsfordiagnosisofattentiondeficithyperactivitydisorder AT alirezamoradi transforming3dmrito2dfeaturemapsusingpretrainedmodelsfordiagnosisofattentiondeficithyperactivitydisorder AT ajaykumar transforming3dmrito2dfeaturemapsusingpretrainedmodelsfordiagnosisofattentiondeficithyperactivitydisorder AT mirmohsenpedram transforming3dmrito2dfeaturemapsusingpretrainedmodelsfordiagnosisofattentiondeficithyperactivitydisorder AT sanjeevchawla transforming3dmrito2dfeaturemapsusingpretrainedmodelsfordiagnosisofattentiondeficithyperactivitydisorder |