International Journal of Intelligent Systems and Applications (IJISA)
IJISA Vol. 18, No. 5, 8 Oct. 2026
Cover page and Table of Contents: PDF (size: 1878KB)
NeuroASD-Net: A Deep Learning-Based Approach for Autism Detection from Structural MRI
PDF (1878KB), PP.191-212
Views: 0 Downloads: 0
Author(s)
Harendra Sharma
1
Oshin Sharma
1,*
Index Terms
Autism Spectrum Disorder, NeuroASD-Net, k-Means Clustering, Self-Adaptive Black-Winged Kite Algorithm, EffiDSR-Net
Abstract
Autism spectrum disorder (ASD), a complex neurodevelopmental disorder, is typified by social interaction challenges, communication difficulties, and repetitive activities. Effective intervention requires an early and precise diagnosis. This paper introduces NeuroASD-Net, a novel framework for ASD detection from structural Magnetic Resonance Imaging (MRI). The approach integrates advanced preprocessing techniques such as histogram matching and Contrast Limited Adaptive Histogram Equalization (CLAHE) to standardize input data. The next stage is the segmentation of key brain regions, like cerebrospinal fluid, white matter, and gray matter, using k-Means clustering. This segmentation step isolates critical regions for subsequent analysis. Following segmentation, a Two-Level Feature Extraction (TLFE) model is applied. In the first level, spatial and textural patterns are extracted using Local Binary Patterns (LBP), Gabor filters, and the Gray Level Co-occurrence Matrix (GLCM), capturing essential morphological characteristics of the brain. Feature selection is then optimized using the Self-Adaptive Black-Winged Kite Algorithm (SA-BKA). In the second level, high-level features are extracted using EffiDSR-Net, in which the EfficientNet model is enhanced with Dual Scale Residual (DSR) Blocks and a Convolutional Block Attention Module (CBAM). The features from both levels are fused to form a comprehensive feature set. Finally, classification is performed using a Softmax layer, achieving precise ASD detection. The proposed framework demonstrates enhanced diagnostic accuracy, achieving an Accuracy of 99.28%, Sensitivity of 99.31%, Specificity of 99.24%, F1-score of 99.31%, and an Area Under the ROC Curve (AUC) of 0.995, indicating its effectiveness for clinical ASD detection.
Cite This Paper
Harendra Sharma, Oshin Sharma, "NeuroASD-Net: A Deep Learning-Based Approach for Autism Detection from Structural MRI", International Journal of Intelligent Systems and Applications (IJISA), Vol.18, No.5, pp.191-212, 2026. DOI:10.5815/ijisa.2026.05.10
Reference
[1]Bahathiq, R.A., Banjar, H., Bamaga, A.K. and Jarraya, S.K., 2022. Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging. Frontiers in Neuroinformatics, 16, p.949926.
[2]Ali, M.T., ElNakieb, Y., Elnakib, A., Shalaby, A., Mahmoud, A., Ghazal, M., Yousaf, J., Abu Khalifeh, H., Casanova, M., Barnes, G. and El-Baz, A., 2022. The role of structure MRI in diagnosing autism. Diagnostics, 12(1), p.165.
[3]Saputra, D.C.E., Maulana, Y., Win, T.A., Phann, R. and Caesarendra, W., 2023. Implementation of machine learning and deep learning models based on structural MRI for identification autism spectrum disorder. Journal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI), 9(2), pp.307-318.
[4]Duan, Y., Zhao, W., Luo, C., Liu, X., Jiang, H., Tang, Y., Liu, C. and Yao, D., 2022. Identifying and predicting autism spectrum disorder based on multi-site structural MRI with machine learning. Frontiers in human neuroscience, 15, p.765517.
[5]Elshoky, B.R.G., Younis, E.M., Ali, A.A. and Ibrahim, O.A.S., 2022. Comparing automated and non-automated machine learning for autism spectrum disorders classification using facial images. Etri Journal, 44(4), pp.613-623.
[6]Moridian, P., Ghassemi, N., Jafari, M., Salloum-Asfar, S., Sadeghi, D., Khodatars, M., Shoeibi, A., Khosravi, A., Ling, S.H., Subasi, A. and Alizadehsani, R., 2022. Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review. Frontiers in Molecular Neuroscience, 15, p.999605.
[7]Kadi, I., Abbas, M. and Eddine, M.M.C., 2024. Intelligent models for early Autism detection from MRI images. Studies in Engineering and Exact Sciences, 5(2), pp.e8464-e8464.
[8]Han, J., Jiang, G., Ouyang, G. and Li, X., 2022. A multimodal approach for identifying autism spectrum disorders in children. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30, pp.2003-2011.
[9]Talaat, F.M., Ali, Z.H., Mostafa, R.R. and El-Rashidy, N., 2024. Real-time facial emotion recognition model based on kernel autoencoder and convolutional neural network for autism children. Soft Computing, pp.1-14.
[10]Alcañiz, M., Chicchi‐Giglioli, I.A., Carrasco Ribelles, L.A., MarínMorales, J., Minissi, M.E., Teruel García, G., Sirera, M. and Abad, L., 2022. Eye gaze as a biomarker in the recognition of autism spectrum disorder using virtual reality and machine learning: A proof of concept for diagnosis. Autism Research, 15(1), pp.131-145.
[11]Feng, M. and Xu, J., 2023. Detection of ASD children through deep-learning application of fMRI. Children, 10(10), p.1654.
[12]Kuttala, D., Mahapatra, D., Subramanian, R. and Oruganti, V.R.M., 2022. Dense attentive GAN-based one-class model for detection of autism and ADHD. Journal of King Saud University-Computer and Information Sciences, 34(10), pp.10444-10458.
[13]Durkut, M., Blok, E., Suleri, A. and White, T., 2022. The longitudinal bidirectional relationship between autistic traits and brain morphology from childhood to adolescence: a population-based cohort study. Molecular Autism, 13(1), p.31.
[14]Ashraf, A., Qingjie, Z., Bangyal, W.H.K. and Iqbal, M., 2023. 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, 70(1), pp.4478-4489.
[15]Nagesh, N., Patil, P., Patil, S. and Kokatanur, M., 2022. An architectural framework for automatic detection of autism using deep convolution networks and genetic algorithm. International Journal of Electrical and Computer Engineering (IJECE), 12(2), pp.1768-1775.
[16]Jain, S., Tripathy, H.K., Mallik, S., Qin, H., Shaalan, Y. and Shaalan, K., 2023. Autism Detection of MRI Brain Images Using Hybrid Deep CNN With DM-Resnet Classifier. IEEE Access.
[17]Devika, K., Mahapatra, D., Subramanian, R. and Oruganti, V.R.M., 2022. Outlier-based autism detection using longitudinal structural MRI. IEEE Access, 10, pp.27794-27808.
[18]Nogay, H.S. and Adeli, H., 2023. Diagnostic of autism spectrum disorder based on structural brain MRI images using grid search optimization and convolutional neural networks. Biomedical Signal Processing and Control, 79, p.104234.
[19]Yakolli, N., Anusha, V., Khan, A.A., Shubhashree, A. and Chatterjee, S., 2023. Enhancing the diagnosis of autism spectrum disorder using phenotypic, structural, and functional MRI data. Innovations in Systems and Software Engineering, pp.1-12.
[20]Belhaouari, S.B., Talbi, A., Hassan, S., Al-Thani, D. and Qaraqe, M., 2023. PFT: A novel time-frequency decomposition of bold fMRI signals for autism spectrum disorder detection. Sustainability, 15(5), p.4094.
[21]Koc, E., Kalkan, H. and Bilgen, S., 2023. Autism Spectrum Disorder Detection by Hybrid Convolutional Recurrent Neural Networks from Structural and Resting State Functional MRI Images. Autism Research and Treatment, 2023(1), p.4136087.
[22]Oruganti, V.R.M., Mahapatra, D. and Subramanian, R., 2022. Outlier-based autism detection using longitudinal structural mri. arXiv preprint arXiv:2202.09988.
[23]Wang, N., Yao, D., Ma, L. and Liu, M., 2022. Multi-site clustering and nested feature extraction for identifying autism spectrum disorder with resting-state fMRI. Medical image analysis, 75, p.102279.
[24]Sharif, H. and Khan, R.A., 2022. A novel machine learning based framework for detection of autism spectrum disorder (ASD). Applied Artificial Intelligence, 36(1), p.2004655.
[25]Alkahtani, H., Aldhyani, T.H. and Alzahrani, M.Y., 2023. Deep learning algorithms to identify autism spectrum disorder in children-based facial landmarks. Applied Sciences, 13(8), p.4855.