Autism Spectrum Disorder (ASD) is a neurodevelopmental condition affecting communication, social interaction, and behavior. ASD often causes delays in reaching developmental milestones.
Purpose
Early therapeutic intervention can aid in progress. Detection methods typically involve psychological assessments and activity analysis. Studies indicate that craniofacial abnormalities are associated with ASD, proposing facial features as a potential biomarker for early diagnosis.
Research Design
This study presents a deep learning-based mobile application for ASD detection, utilizing pre-trained models—InceptionV3, Xception, MobileNet, and ResNet 50—andhybrid dataset containing local (Pakistani) and available labeled images.
Data Anaysis
Experimental results show InceptionV3 achieving the highest accuracy of 88%, highlighting its potential for reliable ASD detection.
Conclusions
Our work contributes by introducing a mobile-based ASD detection system that leverages static facial features and a hybrid Pakistani corpus, offering a culturally adapted and accessible tool for early screening.
ZwaigenbaumLBaumanMLChoueiriR, et al.Early intervention for children with autism spectrum disorder under 3 years of age: recommendations for practice and research. Pediatrics2015; 136(Supplement_1): S60–S81.
2.
TripiGRouxSMatrangaD, et al.Cranio-facial characteristics in children with Autism Spectrum Disorders (ASD). J Clin Med2019; 8(5): 641. https://www.mdpi.com/2077-0383/8/5/641
3.
SaccoTLCiurzynskiSMHarveyME, et al.Compassion satisfaction and compassion fatigue among critical care nurses. Crit Care Nurse2015; 35(4): 32–42.
4.
AldridgeGInouyeDWForrestJR, et al.Emergence of a mid season period of low floral resources in a montane meadow ecosystem associated with climate change. J Ecol2011; 99(4): 905–913.
5.
ÖzgenATuzkayaGTuzkayaUR, et al.A multi-criteria decision making approach for machine tool selection problem in a fuzzy environment. Int J Comput Intell Syst2011; 4(4): 431–445.
6.
AlamMSRashidMMRoyR, et al.Empirical study of autism spectrum disorder diagnosis using facial images by improved transfer learning approach. Bioengineering2022; 9(11): 710.
7.
MaennerMJWarrenZWilliamsAR, et al.Prevalence and characteristics of autism spectrum disorder among children aged 8 years—Autism and developmental disabilities monitoring network, 11 sites, United States, 2020. MMWR Surveill Summ2023; 72: 1–14.
8.
Mujeeb RahmanKSubashiniMM. Identification of autism in children using static facial features and deep neural networks. Brain Sci2022; 12(1): 94.
9.
ElsabbaghMDivanGKohYJ, et al.Global prevalence of autism and other pervasive developmental disorders. Autism Res2012; 5(3): 160–179.
10.
HussainMFarooqMNawazA, et al.Biochar for crop production: potential benefits and risks. J Soils Sediments2017; 17(3): 685–716.
11.
EshraghiMAdlimoghaddamAMahmoodzadehA, et al.Alzheimer’s disease pathogenesis: role of autophagy and mitophagy focusing in microglia. Int J Mol Sci2021; 22(7): 3330.
12.
SharmaSHuckerAMatthewsT, et al.Cognitive behavioural therapy for anxiety in children and young people on the autism spectrum: a systematic review and meta-analysis. Bmc Psychology2021; 9: 1–16.
13.
AhmedZAAldhyaniTHJadhavME, et al.[retracted] facial features detection system to identify children with autism spectrum disorder: deep learning models. Comput Math Methods Med2022; 2022(1): 3941049.
14.
UddinMZShahriarMAMahamoodMN, et al.Deep learning with image-based autism spectrum disorder analysis: a systematic review. Eng Appl Artif Intell2024; 127: 107185.
15.
HammSJ. The effect of ETFs on stock liquidity. University of Pennsylvania, 2010.
LiuWWangZLiuX, et al.A survey of deep neural network architectures and their applications. Neurocomputing2017; 234: 11–26.
18.
AbbasJ. The impact of coronavirus (SARS-CoV2) epidemic on individuals mental health: the protective measures of Pakistan in managing and sustaining transmissible disease. Psychiatr Danub2020; 32(3-4): 472–477.
19.
HashemiHBAsiaeeAKraftR. Query intent detection using convolutional neural networks. In: International conference on web search and data mining, workshop on query understanding, California, USA, 22–25 February 2016.
20.
ScassellatiBBoccanfusoLHuangC-M, et al.Improving social skills in children with ASD using a long-term, in-home social robot. Sci Robot2018; 3(21): eaat7544.
21.
WangCWangZWangG, et al.COVID-19 in early 2021: current status and looking forward. Signal Transduct Targeted Ther2021; 6(1): 114.
22.
PierceJRSchottPK. The surprisingly swift decline of US manufacturing employment. Am Econ Rev2016; 106(7): 1632–1662.
23.
HazlettHCGuHMunsellBC, et al.Early brain development in infants at high risk for autism spectrum disorder. Nature2017; 542(7641): 348–351.
24.
ShahzadIKhanSURWaseemA, et al.Enhancing ASD classification through hybrid attention-based learning of facial features. Signal, Image and Video Processing2024; 18(1): 475–488.
25.
KoonceBKoonceB. ResNet 50. Convolutional neural networks with swift for tensorflow: image recognition and dataset categorization, 2021, pp. 63–72.
26.
SinhaDEl-SharkawyM. Thin mobilenet: an enhanced mobilenet architecture. In: 2019 IEEE 10th annual ubiquitous computing, electronics & mobile communication conference (UEMCON), New York, USA, 10–12 October 2019.
27.
LinCLiLLuoW, et al.Transfer learning based traffic sign recognition using inception-v3 model. Period Polytech Transp Eng2019; 47(3): 242–250.
28.
CholletF. Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, Hawaii, 21–26 July 2017, pp. 1251–1258.
29.
ThabtahFPeeblesD. Early autism screening: a comprehensive review. Int J Environ Res Publ Health2019; 16(18): 3502.
30.
RajSMasoodS. Analysis and detection of autism spectrum disorder using machine learning techniques. Procedia Comput Sci2020; 167: 994–1004.
31.
JahanaraSPadmanabhanS. Detecting autism from facial image. International Journal of Advance Research, Ideas and Innovations in Technology2021; 7(2): 219–225.
32.
WangLWangBWuC, et al.Autism spectrum disorder: neurodevelopmental risk factors, biological mechanism, and precision therapy. Int J Mol Sci2023; 24(3): 1819.
33.
PatelSDaleRCRoseD, et al.Maternal immune conditions are increased in males with autism spectrum disorders and are associated with behavioural and emotional but not cognitive co-morbidity. Transl Psychiatry2020; 10(1): 286.
34.
GuptaUGuptaDAgarwalU. Analysis of randomization-based approaches for autism spectrum disorder. In: Pattern Recognition and Data Analysis with Applications. Springer, 2022, pp. 701–713.
35.
AlzubaidiLZhangJHumaidiAJ, et al.Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data2021; 8: 1–74.
36.
DhillonAVermaGK. Convolutional neural network: a review of models, methodologies and applications to object detection. Progress in Artificial Intelligence2020; 9(2): 85–112.
37.
YasashviniRPanjanathanRGracelineJS, et al.Diabetic retinopathy classification using CNN and hybrid deep convolutional neural networks. Symmetry2022; 14(9): 1932.
38.
RobinsonJPFuY. Pre-trained D-CNN models for detecting complex events in unconstrained videos. In: Sensing and Analysis Technologies for Biomedical and Cognitive Applications 2016. SPIE, 2016, vol 9871, pp. 191–199.
39.
HussainMBirdJJFariaDR. A study on CNN transfer learning for image classification. In: Advances in Computational Intelligence Systems: Contributions Presented at the 18th UK Workshop on Computational Intelligence, Nottingham, UK, 5–7 September 2018: Springer International Publishing, pp. 191–202.
40.
HowardAGZhuMChenB, et al.Mobilenets: efficient convolutional neural networks for Mobile vision applications. arXiv preprint arXiv:1704.048612017.
41.
XuWFuY-LZhuD. ResNet and its application to medical image processing: research progress and challenges. Comput Methods Progr Biomed2023; 240: 107660.
42.
DongNZhaoLWuC-H, et al.Inception v3 based cervical cell classification combined with artificially extracted features. Appl Soft Comput2020; 93: 106311.
43.
SarvepalliSK. Deep learning in neural networks: the science behind an artificial brain. Liverpool Hope University, Liverpool, 2015.
44.
NitishS. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res2014; 15: 1.
45.
SammutCWebbGI. Encyclopedia of machine learning and data mining. Springer Publishing Company, Incorporated, 2017.
46.
HuangJLingCX. Using AUC and accuracy in evaluating learning algorithms. IEEE Trans Knowl Data Eng2005; 17(3): 299–310.
47.
KumarAJaiswalUC. Predicting autism spectrum disorder in adults through facial image analysis: a Multi-CNN with BiLSTM model. SN Computer Science2025; 6(3): 254.
48.
BaltrušaitisTAhujaCMorencyL-P (2018). Challenges and applications in multimodal machine learning. In: The Handbook of Multimodal-Multisensor Interfaces: Signal Processing, Architectures, and Detection of Emotion and Cognition-, Vol 2, pp. 17–48.
49.
RuanM. Image and video-based autism spectrum disorder detection via deep learning. West Virginia University, 2020.
