MS-ViT: multi-scale vision transformer; AUC: area under the curve; ROC: receiver operating characteristic; ms: milliseconds; FP: false positive; PTQ: post-training quantization; ROI: regions of interest.
Declarations
Author contributions
KR: Conceptualization, Methodology, Resources, Writing—review & editing, Supervision, Project administration. TSJ: Software, Validation, Investigation, Data curation, Writing—review & editing. AMH: Methodology, Software, Validation, Formal analysis, Visualization, Writing—original draft, Writing—review & editing. All authors confirm their authorship of this manuscript, affirm that they have contributed to its development, including its conceptual design, implementation, and analysis. They have also read and approved the submitted version.
Conflicts of interest
The authors declare that there are no conflicts of interest, financial or personal, that could have influenced the outcomes or interpretation of this research.
Ethical approval
This study used publicly available, de-identified facial images from a Kaggle dataset; no new data were collected. For deployment, we advocate on-device processing, minimal data retention, and optional de-identification (e.g., landmark-only or blur-based strategies) to mitigate re-identification risks.
Consent to participate
Not applicable.
Consent to publication
Not applicable.
Availability of data and materials
The facial images used in this study were obtained from a publicly available Kaggle dataset, Autistic Children Facial Data Set (https://www.kaggle.com/datasets/imrankhan77/autistic-children-facial-data-set). The data were used under the dataset’s stated terms of use; no additional images were collected by the authors. The processed splits and training scripts are available from the authors upon reasonable request (Accessed: 2025 Jan 12).
Funding
This research did not receive any specific grant from public, commercial, or not-for-profit funding agencies.
Open Exploration maintains a neutral stance on jurisdictional claims in published institutional affiliations and maps. All opinions expressed in this article are the personal views of the author(s) and do not represent the stance of the editorial team or the publisher.
References
Sato A, Kotajima-Murakami H, Tanaka M, Katoh Y, Ikeda K. Influence of Prenatal Drug Exposure, Maternal Inflammation, and Parental Aging on the Development of Autism Spectrum Disorder.Front Psychiatry. 2022;13:821455. [DOI] [PubMed] [PMC]
Aizaki K, Walton C, Lewis C. Understanding the Impact of Restricted Interests on the Social Interactions of Adults with Autism Spectrum Disorder. In: Tsuchiya K, Coffey F, Nakamura K, editors. Multimodal Approaches to Healthcare Communication Research: Visualising Interactions for Resilient Healthcare in the UK and Japan. London: Bloomsbury Academic; 2023. pp. 83. [DOI]
Rezaee K. Machine learning in automated diagnosis of autism spectrum disorder: A comprehensive review.Comput Sci Rev. 2025;56:100730. [DOI]
Hammond P, Forster-Gibson C, Chudley AE, Allanson JE, Hutton TJ, Farrell SA, et al. Face-brain asymmetry in autism spectrum disorders.Mol Psychiatry. 2008;13:614–23. [DOI] [PubMed]
Zhang F, Roeyers H. Exploring brain functions in autism spectrum disorder: A systematic review on functional near-infrared spectroscopy (fNIRS) studies.Int J Psychophysiol. 2019;137:41–53. [DOI] [PubMed]
Hughes HK, Moreno RJ, Ashwood P. Innate immune dysfunction and neuroinflammation in autism spectrum disorder (ASD).Brain Behav Immun. 2023;108:245–54. [DOI] [PubMed]
Albahri AS, Duhaim AM, Fadhel MA, Alnoor A, Baqeret NS, Alzubaidi L, et al. A systematic review of trustworthy and explainable artificial intelligence in healthcare: Assessment of quality, bias risk, and data fusion.Inf Fusion. 2023;96:156–91. [DOI]
Kuhn E, Blanchard EB, Fuse T, Hickling EJ, Broderick J. Heart rate of motor vehicle accident survivors in the emergency department, peritraumatic psychological reactions, ASD, and PTSD severity: a 6-month prospective study.J Trauma Stress. 2006;19:735–40. [DOI] [PubMed]
Welch KC. Physiological signals of autistic children can be useful.IEEE Instrum Meas Mag. 2012;15:28–32. [DOI]
Yadav KB, Vishwas S, Anand N, Kashyap BSR, Bangalore R. Automated identification and classification of autism spectrum disorder using behavioural and visual patterns in children. In: 2023 4th International Conference for Emerging Technology (INCET). Belgaum: IEEE; 2023. pp. 1–5. [DOI]
Singhi P, Malhi P. Early Diagnosis of Autism Spectrum Disorder: What the Pediatricians Should Know.Indian J Pediatr. 2023;90:364–8. [DOI] [PubMed]
Shaw KA, Williams S, Patrick ME, Valencia-Prado M, Durkin MS, Howerton EM, et al. Prevalence and Early Identification of Autism Spectrum Disorder Among Children Aged 4 and 8 Years—Autism and Developmental Disabilities Monitoring Network, 16 Sites, United States, 2022.MMWR Surveill Summ. 2025;74:1–22. [DOI] [PubMed] [PMC]
Aishworiya R, Valica T, Hagerman R, Restrepo B. An Update on Psychopharmacological Treatment of Autism Spectrum Disorder.Neurotherapeutics. 2022;19:248–62. [DOI] [PubMed] [PMC]
Schwichtenberg AJ, Janis A, Lindsay A, Desai H, Sahu A, Kellerman A, et al. Sleep in Children with Autism Spectrum Disorder: A Narrative Review and Systematic Update.Curr Sleep Med Rep. 2022;8:51–61. [DOI] [PubMed] [PMC]
Hyman SL, Levy SE, Myers SM; COUNCIL ON CHILDREN WITH DISABILITIES, SECTION ON DEVELOPMENTAL AND BEHAVIORAL PEDIATRICS. Executive Summary: Identification, Evaluation, and Management of Children With Autism Spectrum Disorder.Pediatrics. 2020;145:e20193448. [DOI] [PubMed]
Sandbank M, Bottema-Beutel K, Woynaroski T. Intervention Recommendations for Children With Autism in Light of a Changing Evidence Base.JAMA Pediatr. 2021;175:341–2. [DOI] [PubMed]
Zwaigenbaum L, Bauman ML, Choueiri R, Kasari C, Carter A, Granpeesheh D, et al. Early Intervention for Children With Autism Spectrum Disorder Under 3 Years of Age: Recommendations for Practice and Research.Pediatrics. 2015;136:S60–81. [DOI] [PubMed] [PMC]
Lecciso F, Levante A, Fabio RA, Caprì T, Leo M, Carcagnì P, et al. Emotional Expression in Children With ASD: A Pre-Study on a Two-Group Pre-Post-Test Design Comparing Robot-Based and Computer-Based Training.Front Psychol. 2021;12:678052. [DOI] [PubMed] [PMC]
Akter T, Ali MH, Khan MI, Satu MS, Uddin MJ, Alyami SA, et al. Improved Transfer-Learning-Based Facial Recognition Framework to Detect Autistic Children at an Early Stage.Brain Sci. 2021;11:734. [DOI] [PubMed] [PMC]
Elshoky BRG, Younis EMG, Ali AA, Ibrahim OAS. Comparing automated and non-automated machine learning for autism spectrum disorders classification using facial images.ETRI J. 2022;44:613–23. [DOI]
Banire B, Al Thani D, Qaraqe M, Mansoor B. Face-Based Attention Recognition Model for Children with Autism Spectrum Disorder.J Healthc Inform Res. 2021;5:420–45. [DOI] [PubMed] [PMC]
Pan Y, Foroughi A. Evaluation of AI tools for healthcare networks at the cloud-edge interaction to diagnose autism in educational environments.J Cloud Comput. 2024;13:39. [DOI]
Atlam ES, Aljuhani KO, Gad I, Abdelrahim EM, Atwa AEM, Ahmed A. Automated identification of autism spectrum disorder from facial images using explainable deep learning models.Sci Rep. 2025;15:26682. [DOI] [PubMed] [PMC]
Shahzad I, Khan SUR, Waseem A, Abideen ZUI, Liu J. Enhancing ASD classification through hybrid attention-based learning of facial features.Signal Image Video P. 2024;18:475–88. [DOI]
Mahmood MA, Jamel L, Alturki N, Tawfeek MA. Leveraging artificial intelligence for diagnosis of children autism through facial expressions.Sci Rep. 2025;15:11945. [DOI] [PubMed] [PMC]
Attar N, Paygude S. Early Autism Diagnosis in Children through Facial Image Recognition Using Refined Gravitational Search Optimized MobileNetv2 model. In: 2025 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS). Bhopal: IEEE; 2025. pp. 1–8. [DOI]
Rahman MA, Hossain MM, Singh SP, Sharmin N. Predicting early ASD traits of adults and toddlers using machine learning and deep learning with explainable AI and optimization.Neural Comput Appl. 2025;37:22287–314. [DOI]
Ibadi H, Lakizadeh A. ASDvit: Enhancing autism spectrum disorder classification using vision transformer models based on static features of facial images.Intell-Based Med. 2025;11:100226. [DOI]
Attar N, Paygude S. Autism detection in children based on facial image data using RPY axial facial features and Dual Phase Net model.Multimed Tools Appl. 2025;84:17517–46. [DOI]
Mujeeb Rahman KK, Subashini MM. Identification of Autism in Children Using Static Facial Features and Deep Neural Networks.Brain Sci. 2022;12:94. [DOI] [PubMed] [PMC]
Li Y, Huang WC, Song PH. A face image classification method of autistic children based on the two-phase transfer learning.Front Psychol. 2023;14:1226470. [DOI] [PubMed] [PMC]
Alkahtani H, Aldhyani THH, Alzahrani MY. Deep Learning Algorithms to Identify Autism Spectrum Disorder in Children-Based Facial Landmarks.Appl Sci. 2023;13:4855. [DOI]
Tian Y, Wang S, Zhai G. Medical manifestation-aware de-identification.roc AAAI Conf Artif Intell. 2025;39:26363–72. [DOI]
Meden B, Rot P, Terhörst P, Damer N, Kuijper A, Scheirer WJ, et al. Privacy-enhancing face biometrics: a comprehensive survey.IEEE Trans Inf Forensics Secur. 2021;16:4147–83. [DOI]
Tian Y, Ji K, Zhang R, Jiang Y, Li C, Wang X, et al. Towards All-in-One Medical Image Re-Identification.arXiv:2503.08173v1 [Preprint]. 2025 [cited 2025 Sep 1]. Available from: https://arxiv.org/abs/2503.08173v1
Tian Y, Wang S, Zhang R, Chen Z, Jiang Y, Li C, et al. Semantics versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification.arXiv:2507.21703 [Preprint]. 2025 [cited 2025 Sep 1]. Available from: https://arxiv.org/abs/2507.21703
Ahmad I, Rashid J, Faheem M, Akram A, Khan NA, Amin RU. Autism spectrum disorder detection using facial images: A performance comparison of pretrained convolutional neural networks.Healthc Technol Lett. 2024;11:227–39. [DOI] [PubMed] [PMC]
Feichtenhofer C, Fan H, Malik J, He K. SlowFast Networks for Video Recognition. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul: IEEE; 2019. pp. 6202–11. [DOI]
Tian Y, Min X, Zhai G, Gao Z. Video-Based Early ASD Detection via Temporal Pyramid Networks. In: 2019 IEEE International Conference on Multimedia and Expo (ICME). Shanghai: IEEE; 2019. pp. 272–7. [DOI]
Tian Y, Yan Y, Zhai G, Guo G, Gao Z. EAN: Event Adaptive Network for enhanced action recognition.Int J Comput Vis. 2022;130:2453–71. [DOI]
Tian Y, Lu G, Yan Y, Zhai G, Chen L, Gao Z. A Coding Framework and Benchmark Towards Low-Bitrate Video Understanding.IEEE Trans Pattern Anal Mach Intell. 2024;46:5852–72. [DOI] [PubMed]
Tian Y, Lu G, Zhai G, Gao Z. Non-Semantics Suppressed Mask Learning for Unsupervised Video Semantic Compression. In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris: IEEE; 2023. pp. 13610–22. [DOI]
Tian Y, Lu G, Zhai G. Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression.In: Computer Vision—ECCV 2024. Cham: Springer Nature Switzerland; 2024. pp. 163–83. [DOI]
