Autism Spectrum Disorder Diagnosis Based on Attentional Feature Fusion Using NasNetMobile and DeiT Networks DOI Open Access

Zainab A. Altomi,

Yasmin M. Alsakar,

M. M. El-Gayar

et al.

Electronics, Journal Year: 2025, Volume and Issue: 14(9), P. 1822 - 1822

Published: April 29, 2025

Autism spectrum disorder (ASD) is a neurodevelopmental condition that affects social interactions, communication, and behavior. Prompt precise diagnosis essential for prompt support intervention. In this study, deep learning-based framework diagnosing ASD using facial images has been proposed. The methodology begins with logarithmic transformation image pre-processing, enhancing contrast making subtle features more distinguishable. Next, feature extraction performed NasNetMobile DeiT networks, where captures high-level abstract patterns, the network focuses on fine-grained characteristics relevant to identification. extracted are then fused attentional fusion, which adaptively assigns importance most discriminative features, ensuring an optimal representation. Finally, classification conducted bagging vector machine (SVM) classifier employing polynomial kernel, generalization robustness. Experimental results validate effectiveness of proposed approach, achieving 95.77% recall, 95.67% precision, 95.66% F1-score, accuracy, demonstrating its strong potential assisting in through analysis.

Language: Английский

An exploration of machine learning approaches for early Autism Spectrum Disorder detection DOI Creative Commons

Nawshin Haque,

Tania Islam, Md. Erfan

et al.

Healthcare Analytics, Journal Year: 2025, Volume and Issue: unknown, P. 100379 - 100379

Published: Jan. 1, 2025

Language: Английский

Citations

0
Explainable AI-Powered Multimodal Fusion Framework for EEG-Based Autism Spectrum Disorder Classification DOI
Nuzhat Noor Islam Prova

Published: Jan. 1, 2025

Language: Английский

Citations

0
Multimodal Morphometric Similarity Network Analysis of Autism Spectrum Disorder DOI Creative Commons
Antonio Del Casale, Darvin Shehu, Maria Camilla Rossi‐Espagnet

et al.

Brain Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 247 - 247

Published: Feb. 26, 2025

Background: Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by persistent difficulties in social interaction, communication, and repetitive behaviors. Neuroimaging studies have revealed structural functional neural changes individuals with ASD compared to healthy subjects. Objectives: This study aimed investigate brain network connectivity using Morphometric Similarity Network (MSN) analysis. Methods: Data from the Brain Imaging Exchange (ABIDE) were analyzed, comprising 597 644 controls. Structural was assessed cortical morphometric features. Global regional indices, including density index, node degree, strength, clustering coefficients, evaluated. Results: Among global when threshold value of 0.4, patients HCs showed lower (p = 0.041) higher negative 0.0051) coefficients. For bilateral superior frontal cortices degree (left hemisphere: p 0.014; right 0.0038) strength (left: 0.017; right: 0.018). Additionally, they coefficients (left, 0.0088; right, 0.0056) pars orbitalis 0.016; 0.0006), as well positive pole 0.03; 0.044). Conclusions: These findings highlight significant alterations both organization ASD, which may contribute disorder’s cognitive behavioral manifestations. Future are needed pathophysiological mechanisms underlying these changes, inform development more targeted individualized therapeutic interventions for ASD.

Language: Английский

Citations

0
Autism Spectrum Disorder Diagnosis Based on Attentional Feature Fusion Using NasNetMobile and DeiT Networks DOI Open Access

Zainab A. Altomi,

Yasmin M. Alsakar,

M. M. El-Gayar

et al.

Electronics, Journal Year: 2025, Volume and Issue: 14(9), P. 1822 - 1822

Published: April 29, 2025

Autism spectrum disorder (ASD) is a neurodevelopmental condition that affects social interactions, communication, and behavior. Prompt precise diagnosis essential for prompt support intervention. In this study, deep learning-based framework diagnosing ASD using facial images has been proposed. The methodology begins with logarithmic transformation image pre-processing, enhancing contrast making subtle features more distinguishable. Next, feature extraction performed NasNetMobile DeiT networks, where captures high-level abstract patterns, the network focuses on fine-grained characteristics relevant to identification. extracted are then fused attentional fusion, which adaptively assigns importance most discriminative features, ensuring an optimal representation. Finally, classification conducted bagging vector machine (SVM) classifier employing polynomial kernel, generalization robustness. Experimental results validate effectiveness of proposed approach, achieving 95.77% recall, 95.67% precision, 95.66% F1-score, accuracy, demonstrating its strong potential assisting in through analysis.

Language: Английский

Citations

0