Autism Spectrum Disorder Detection using Enhanced 3D-ResNet50 Algorithm
| International Journal of Electronics and Communication Engineering |
| © 2026 by SSRG - IJECE Journal |
| Volume 13 Issue 1 |
| Year of Publication : 2026 |
| Authors : P. Yugander, M. Jagannath |
10.14445/23488549/IJECE-V13I1P116
How to Cite?
P. Yugander, M. Jagannath, "Autism Spectrum Disorder Detection using Enhanced 3D-ResNet50 Algorithm," SSRG International Journal of Electronics and Communication Engineering, vol. 13, no. 1, pp. 193-206, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I1P116
Abstract:
Autism Spectrum Disorder (ASD) is a neuro-developmental disease that affects behavioural retardation in verbal communications and social interactions. Clinicians employ various ASD detection techniques to identify the condition. However, these traditional methods are time-consuming and suffer from a lack of accuracy. Over the last two decades, Machine Learning (ML) and Deep Learning (DL) algorithms have played a crucial role in the field of biomedical signal and image processing. In this paper, we propose a Machine Learning Framework. This contains two stages. In the first stage, an enhanced 3D-ResNet50 algorithm is proposed. The proposed algorithm is used to extract features from Magnetic Resonance (MR) Images. In the second stage, the extracted features are used to classify the ASD controls using Machine Learning Algorithms. To improve the accuracy of ASD classification, an enhanced 3D-ResNet50 algorithm is integrated with the ML algorithms. The proposed algorithm is used along with the machine learning algorithms like Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Random Forest (RF), and Logistic Regression (LR). The proposed machine learning framework is tested on 1112 Functional Magnetic Resonance Images (fMRI). These images are collected from the Autism Brain Imaging Data Exchange (ABIDE-I) website. The ABIDE-I website provides a collection of 17 datasets from various international biomedical laboratories. The proposed algorithm is tested on the total ABIDE-I website and 17 individual datasets. Our proposed approach achieved 90% overall accuracy and 97% accuracy for the individual NYU dataset alone.
Keywords:
Autism, 3D-ResNet50, Support Vector Machine, MR images, Random Forest.
References:
[1] I. Kamp-Becker et al., “Diagnostic Accuracy of the ADOS and ADOS-2 in Clinical Practice,” European Child & Adolescent Psychiatry, vol. 27, pp. 1193-1207, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Jared A. Nielsen et al., “Multisite Functional Connectivity MRI Classification of Autism: ABIDE Results,” Frontiers in Human Neuroscience, vol. 7, pp. 1-12, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Lizhen Shao et al., “Classification of ASD Based on fMRI Data with Deep Learning,” Cognitive Neurodynamics, vol. 15, pp. 961-974, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Anibal Sólon Heinsfeld et al., “Identification of Autism Spectrum Disorder using Deep Learning and the ABIDE Dataset,” Neuroimage: Clinical, vol. 17, pp. 16-23, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Meijie Liu, Baojuan Li, and Dewen Hu, “Autism Spectrum Disorder Studies Using fMRI Data and Machine Learning: A Review,” Frontiers in Neuroscience, vol. 15, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Nurul Amirah Mashudi, Norulhusna Ahmad, and Norliza Mohd Noor, “Classification of Adult Autistic Spectrum Disorder using Machine Learning Approach,” IAES International Journal of Artificial Intelligence, vol. 10, no. 3, pp. 743-751, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] R. Abhinav Chaitanya et al., “Autism Spectrum Disorder Detection using Attention-Based CNN and ML Classifiers,” Procedia Computer Science, vol. 258, pp. 4216-4227, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Alexandre Abraham et al, “Deriving Reproducible Biomarkers from Multi-site Resting-state Data: An Autism-based Example,” NeuroImage, vol. 147, pp. 736-745, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[9] S.M. Mahedy Hasan et al., “A Machine Learning Framework for Early-Stage Detection of Autism Spectrum Disorders,” IEEE Access, vol. 11, pp. 15038-15057, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Zhiyong Wang et al., “Diagnosis and Intervention for Children with Autism Spectrum Disorder: A Survey,” IEEE Transactions on Cognitive and Developmental Systems, vo. 14, no. 3, pp. 819-832, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Yin Liang, Baolin Liu, and Hesheng Zhang, “A Convolutional Neural Network Combined with Prototype Learning Framework for Brain Functional Network Classification of Autism Spectrum Disorder,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 29, pp. 2193-2202, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Manu Kohli, Arpan Kumar Kar, and Shuchi Sinha, “The Role of Intelligent Technologies in Early Detection of Autism Spectrum Disorder (ASD): A Scoping Review,” IEEE Access, vol. 10, pp. 104887-104913, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Rui Yang et al., “Exploring sMRI Biomarkers for Diagnosis of Autism Spectrum Disorders Based on Multi Class Activation Mapping Models,” IEEE Access, vol. 9, pp. 124122-124131, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Adnan Ashraf et al., “Analysis of Brain Imaging Data for the Detection of Early Age Autism Spectrum Disorder Using Transfer Learning Approaches for Internet of Things,” IEEE Transactions on Consumer Electronics, vol. 70, no. 1, pp. 4478-4489, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Sara Karim et al., “A Review on Predicting Autism Spectrum Disorder(ASD) meltdown using Machine Learning Algorithms,” 2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), Dhaka, Bangladesh, pp. 1-6, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Alishba Sadiq et al., “Non-Oscillatory Connectivity Approach for Classification of Autism Spectrum Disorder Subtypes Using Resting-State fMRI,” IEEE Access, vol. 10, pp. 14049-14061, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Ali Jahani et al., “Twinned Neuroimaging Analysis Contributes to Improving the Classification of Young People with Autism Spectrum Disorder,” Scientific Reports, vol. 14, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Rajat Mani Thomas et al., “Classifying Autism Spectrum Disorder Using the Temporal Statistics of Resting-State Functional MRI Data With 3D Convolutional Neural Networks,” Frontiers in Psychiatry, vol. 11, pp. 1-12, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Yilan Dong, Dafnis Batalle, and Maria Deprez, “A Framework for Comparison and Interpretation of Machine Learning Classifiers to Predict Autism on the ABIDE Dataset,” Human Brain Mapping, vol. 46, no. 5, pp. 1-20, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Mohamed T. Ali et al., “The Role of Structure MRI in Diagnosing Autism,” Diagnostics, vol. 12, no. 1, pp. 1-28, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Qiang Zheng et al., “ConnectomeAE: Multimodal Brain Connectome-based Dual-branch Autoencoder and its Application in the Diagnosis of Brain Diseases,” Computer Methods and Programs in Biomedicine, vol. 267, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Fahad Almuqhim, and Fahad Saeed, “ASD-SAENet: A Sparse Autoencoder, and Deep-Neural Network Model for Detecting Autism Spectrum Disorder (ASD) Using fMRI Data,” Frontiers in Computational Neuroscience, vol. 15, pp. 1-10, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Wonsik Jung et al., “EAG-RS: A Novel Explainability-Guided ROI-Selection Framework for ASD Diagnosis via Inter-Regional Relation Learning,” IEEE Transactions on Medical Imaging, vol. 43, no. 4, pp. 1400-1411, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Canhua Wang, Zhiyong Xiao, and Jianhua Wu, “Functional Connectivity-based Classification of Aautism and Control using SVM-RFECV on rs-fMRI Data,” Physica Medica, vol. 65, pp. 99-105, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Junxia Han et al., “A Multimodal Approach for Identifying Autism Spectrum Disorders in Children,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 30, pp. 2003-2021, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Shuaibing Liang et al., “Autism Spectrum Self-Stimulatory Behaviors Classification Using Explainable Temporal Coherency Deep Features and SVM Classifier,” IEEE Access, vol. 9, pp. 34264-34275, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Mohammed I. Al-Hiyali et al., “Classification of BOLD FMRI Signals Using Wavelet Transform and Transfer Learning for Detection of Autism Spectrum Disorder,” 2020 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), Langkawi Island, Malaysia, pp. 94-98, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Sejuti Rahman et al., “Automated Detection Approaches to Autism Spectrum Disorder Based on Human Activity Analysis: A Review,” Cognitive Computation, vol. 14, pp. 1773-1800, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Yangsong Zhang et al., “Predicting the Symptom Severity in Autism Spectrum Disorder Based on EEG Metrics,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 30, pp. 1898-1907, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[30] A Di Martino et al., “The Autism Brain Imaging Data Exchange: Towards a Large-Scale Evaluation of the Intrinsic Brain Architecture in Autism,” Molecular Psychiatry, vol. 19, no. 6, pp. 659-667, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Michelle Tang et al., “Deep Multimodal Learning for the Diagnosis of Autism Spectrum Disorder,” Journal of Imaging, vol. 6, no. 6, pp. 1-11, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Zeinab Sherkatghanad et al., “Automated Detection of Autism Spectrum Disorder Using a Convolutional Neural Network,” Frontiers in Neuroscience, vol. 13, pp. 1-13, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Lebo Wang, Kaiming Li, and Xiaoping P. Hu, “Graph Convolutional Network for fMRI Analysis based on Connectivity Neighborhood,” Network Neuroscience, vol. 5, no. 1, pp. 83-95, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Jingsheng Deng et al., “Diagnosing Autism Spectrum Disorder Using Ensemble 3D-CNN: A Preliminary Study,” 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France, pp. 3480-3484, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Amin Majidzadeh Sabegh et al., “Automatic Detection of Autism Spectrum Disorder based on fMRI Images using a Novel Convolutional Neural Network,” Research on Biomedical Engineering, vol. 39, pp. 407-413, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Xuehan Liu et al., “MADE-for-ASD: A Multi-Atlas Deep Ensemble Network for Diagnosing Autism Spectrum Disorder,” Computers in Biology and Medicine, vol. 182, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]