EUVIMEDEUVIMED entdecken
Open Access

DHCA‐Net: A Novel Dual‐Stream Hierarchical Channel Attention Network for Explainable Autism Spectrum Disorder Detection From Facial Images

Davinder Paul Singh iD, Tathagat Banerjee, Anand Deva Durai C iD, Shivam Mahendra Shukla iD, Prakash Gadipelli iD, Piyush Charan, Dheeraj Malhotra iD, Dharamvir iD, Ram Murat Singh iD, Yogendra Narayan iD, Vraj Patel, Ronak Panchal

International Journal of Developmental Neuroscience · 2026-08 · 86 (5)

DOI: 10.1002/jdn.70158 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Developmental Neuroscience, online erschienen am 20.07.2026. Verfasst von Davinder Paul Singh und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of CSE, School of Technology, Pandit Deendayal Energy University, Gandhinagar, Gujarat, India. Hauptthemen laut MEDLINE: Autism Spectrum Disorder, Face, Deep Learning, Attention. Die Arbeit nennt 85 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: King Khalid University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autism spectrum disorder (ASD) consists of a spectrum of neurodevelopmental conditions characterized by complex behavioural traits and subtle, atypical facial morphologies. Analysing these facial biomarkers provides a promising, non‐invasive avenue for objective clinical screening, addressing the subjectivity of traditional diagnostic processes. Therefore, the present study aims to introduce DHCA‐Net, a deep learning framework designed for automated ASD detection through the analysis of facial images. The proposed architecture uses different levels of attention and different adaptive tuning to advance discriminative learning. Specifically, DHCA‐Net introduces three novel attention mechanisms to advance discriminative learning: a hierarchical channel module for spatial‐semantic processing, a temporal‐depth convolutional module for local contextual control and an inverted residual multi‐core module for dynamic feature learning. An adaptive refinement step is also introduced to denoise clinical features. To bolster and diversify the classifier, the model exploits deep spatial and contextual resources via a multi‐head feature fusion (MHFF) mechanism. We conducted extensive testing on a benchmark dataset comprising 2936 diverse, preprocessed facial images (86.4% train, 10.2% test, 3.4% validation splits). A comparative analysis evaluated DHCA‐Net against architectures such as DenseNet, Xception, EfficientNet and Swin‐Transformer. The proposed model achieved 93.7% classification accuracy, a 0.9365 F1 score and a 0.9887 AUC, demonstrating superior performance. Furthermore, the model maintains an efficient average inference latency of 70.14 ms despite its mid‐to‐high computational complexity. This explainable framework offers significant clinical applicability for scalable screening, though future work must address generalization across broader demographic populations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Autism Spectrum DisorderFaceDeep LearningAttentionImage Processing, Computer-AssistedHumansConvolutional Neural Networks

Stichwörter der Autor:innen

attention mechanismsautism spectrum disorder (ASD)computer visiondeep learningfacial image analysisfeature fusioninterpretabilitytransfer learning

Autor:innen und Institutionen

  • Department of CSE, School of Technology, Pandit Deendayal Energy University, Gandhinagar, Gujarat, India.
  • Department of CSE, IIT Patna, Patna, Bihar, India.
  • Department of Computer Science, College of Computer Science, King Khalid University, Abha, Saudi Arabia.
  • Department of Engineering Sciences and Humanities, Thakur Shree DPS College of Engineering & Management, Vasai-Virar, Maharashtra, India.
  • Department of Chemistry, Aditya University, Surampalem, Kakinada, India.
  • Department of Interdisciplinary Engineering - Robotics & AI, Centre for AI and Advanced Computing (CAAC), Manav Rachna University, Faridabad, India.

ORCID-Profile: Davinder Paul Singh, Anand Deva Durai C, Shivam Mahendra Shukla, Prakash Gadipelli, Dheeraj Malhotra, Dharamvir, Ram Murat Singh, Yogendra Narayan

Förderung

  • King Khalid University

Zitieren

APA

Singh, D. P., Banerjee, T., C, A. D. D., Shukla, S. M., Gadipelli, P., Charan, P., Malhotra, D., Dharamvir, Singh, R. M., Narayan, Y., Patel, V., & Panchal, R. (2026). DHCA‐Net: A Novel Dual‐Stream Hierarchical Channel Attention Network for Explainable Autism Spectrum Disorder Detection From Facial Images. International Journal of Developmental Neuroscience, 86(5). https://doi.org/10.1002/jdn.70158

Vancouver

Singh DP, Banerjee T, C ADD, Shukla SM, Gadipelli P, Charan P, et al. DHCA‐Net: A Novel Dual‐Stream Hierarchical Channel Attention Network for Explainable Autism Spectrum Disorder Detection From Facial Images. International Journal of Developmental Neuroscience. 2026;86(5). doi:10.1002/jdn.70158

BibTeX
@article{Singh2026,
  author = {Singh, Davinder Paul and Banerjee, Tathagat and C, Anand Deva Durai and Shukla, Shivam Mahendra and Gadipelli, Prakash and Charan, Piyush and Malhotra, Dheeraj and Dharamvir and Singh, Ram Murat and Narayan, Yogendra and Patel, Vraj and Panchal, Ronak},
  title = {DHCA‐Net: A Novel Dual‐Stream Hierarchical Channel Attention Network for Explainable Autism Spectrum Disorder Detection From Facial Images},
  journal = {International Journal of Developmental Neuroscience},
  year = {2026},
  volume = {86},
  number = {5},
  doi = {10.1002/jdn.70158}
}
Kostenlos starten →