Vision-based Approach for Autism Diagnosis using Transfer Learning and Eye-tracking

The potentials of Transfer Learning (TL) have been well-researched in areas such as Computer Vision and Natural Language Processing. This study aims to explore a novel application of TL to detect Autism Spectrum Disorder. We seek to develop an approach that combines TL and eye-tracking, which is commonly used for analyzing autistic features. The key idea is to transform eye-tracking scanpaths into a visual representation, which could facilitate using pretrained vision models. Our experiments implemented a set of widely used models including VGG-16, ResNet, and DenseNet. Our results showed that the TL approach could realize a promising accuracy of classification (ROC-AUC up to 0.78). The proposed approach is not claimed to provide superior performance compared to earlier work. However, the study is primarily thought to convey an interesting aspect regarding the use of (synthetic) visual representations of eye-tracking output as a means to transfer representations from models pretrained on large-scale datasets such as ImageNet.

• Publication year

  2022

• Venue

  International Conference on Health Informatics

• Publication date

  Unknown publication date

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.5220/0010975500003123
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Development and Validation of a New Substance Use Disorder Screening Test Based on the Diagnostic and Statistical Manual of Mental Disorders (DSM-5)

  2023cited by this paper
• Enhanced use of gaze cue in a face-following task after brief trial experience in individuals with autism spectrum disorder

  2021cited by this paper
• Deep transfer learning-based automated detection of COVID-19 from lung CT scan slices

  2020cited by this paper
• A Review of Early Detection of Autism Based on Eye-Tracking and Sensing Technology

  2020cited by this paper
• Visual Traces of Language Acquisition in Toddlers with Autism Spectrum Disorder During the Second Year of Life

  2020cited by this paper
• Computer vision in autism spectrum disorder research: a systematic review of published studies from 2009 to 2019

  2020cited by this paper
• Dynamic Eye Tracking as a Predictor and Outcome Measure of Social Skills Intervention in Adolescents and Adults with Autism Spectrum Disorder

  2020cited by this paper
• NLP-Based Approach to Detect Autism Spectrum Disorder in Saccadic Eye Movement

  2020cited by this paper
• Dynamic Eye Tracking as a Predictor and Outcome Measure of Social Skills Intervention in Adolescents and Adults with Autism Spectrum Disorder

  2020cited by this paper
• A Facial Affect Analysis System for Autism Spectrum Disorder

  2019cited by this paper
• Learning to Predict Autism Spectrum Disorder based on the Visual Patterns of Eye-tracking Scanpaths

  2019cited by this paper
• Examining How Types of Object Distractors Distinctly Compete for Facial Attention in Autism Spectrum Disorder Using Eye Tracking

  2019cited by this paper
• Attention-Based Autism Spectrum Disorder Screening With Privileged Modality

  2019cited by this paper
• Auto-ASD-Network: A Technique Based on Deep Learning and Support Vector Machines for Diagnosing Autism Spectrum Disorder using fMRI Data

  2019cited by this paper
• A novel deep learning based framework for the detection and classification of breast cancer using transfer learning

  2019cited by this paper
• Web users with autism: eye tracking evidence for differences

  2018cited by this paper
• Visualization of Eye-Tracking Patterns in Autism Spectrum Disorder: Method and Dataset

  2018influential reference
• Affective Computing of Childern with Authism Based on Feature Transfer

  2018cited by this paper
• Facial expression recognition as a candidate marker for autism spectrum disorder: how frequent and severe are deficits?

  2018cited by this paper
• Automatic Smile Detection of Infants in Mother-Infant Interaction via CNN-based Feature Learning

  2018cited by this paper
• Detecting Gaze Towards Eyes in Natural Social Interactions and Its Use in Child Assessment

  2017cited by this paper
• A Deep Learning Frame-Work for Recognizing Developmental Disorders

  2017cited by this paper
• Learning Visual Attention to Identify People with Autism Spectrum Disorder

  2017cited by this paper
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning

  2017cited by this paper
• Identifying children with autism spectrum disorder based on their face processing abnormality: A machine learning framework

  2016cited by this paper
• TensorFlow: A system for large-scale machine learning

  2016cited by this paper
• Improved relation classification by deep recurrent neural networks with data augmentation

  2016cited by this paper
• Densely Connected Convolutional Networks

  2016influential reference
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• Long-Term Outcomes of Early Intervention in 6-Year-Old Children With Autism Spectrum Disorder.

  2015cited by this paper
• Efficient autism spectrum disorder prediction with eye movement: A machine learning framework

  2015cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• Costs of autism spectrum disorders in the United Kingdom and the United States.

  2014cited by this paper
• Visual scanpath representation

  2010cited by this paper
• A Survey on Transfer Learning

  2010cited by this paper
• Randomized, Controlled Trial of an Intervention for Toddlers With Autism: The Early Start Denver Model

  2010cited by this paper
• ImageNet: A large-scale hierarchical image database

  2009influential reference
• Facial Expression Recognition

  2009cited by this paper
• Matplotlib: A 2D Graphics Environment

  2007cited by this paper
• Evidence-Based Assessment of Autism Spectrum Disorders in Children and Adolescents

  2005cited by this paper
• Human gaze control during real-world scene perception.

  2003cited by this paper
• Randomized trial of intensive early intervention for children with pervasive developmental disorder.

  2000cited by this paper
• The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions

  1998cited by this paper
• Eye tracking in advanced interface design

  1995cited by this paper
• Autism Diagnostic Interview-Revised: A revised version of a diagnostic interview for caregivers of individuals with possible pervasive developmental disorders

  1994cited by this paper
• Austism diagnostic observation schedule: A standardized observation of communicative and social behavior

  1989cited by this paper
• The salience of facial expression for autistic children.

  1987cited by this paper
• The autistic child's appraisal of expressions of emotion.

  1986cited by this paper
• Toward objective classification of childhood autism: Childhood Autism Rating Scale (CARS)

  1980influential reference
• NeuroImage: Clinical

  year unknowncited by this paper

• CNNs vs Transformers: Confirmatory factor analysis for eye gaze classification with explainable AI

  2026cites this paper
• Effectiveness of Histogram Equalization and Ensemble Deep Learning Techniques for Detecting Autism Using Eye-Tracking

  2026cites this paper
• Involution fused convolution for classifying eye-tracking patterns of children with Autism Spectrum Disorder

  2025cites this paper
• Diagnosis of autism spectrum disorder: a systematic review of clinical and artificial intelligence methods

  2025influential citation
• An image-based analytics framework for early autism detection using eye movements

  2025cites this paper
• Identifying Autistic Children Using Deep Learning Based on the Temporal and Spatial Information of Eye-Tracking

  2025cites this paper
• Few-Shot Learning with Pretrained Visual Embeddings of Eye-Tracking Patterns for Autism Detection

  2025influential citation
• Leveraging Transfer Learning with Stacked Ensemble Learning for theDetection of Autism Spectrum Disorder using Eye-tracking

  2024cites this paper
• Involution Fused ConvNet for Classifying Eye-Tracking Patterns of Children with Autism Spectrum Disorder

  2024cites this paper
• Machine Learning-Based Detection of Autism Spectrum Disorder Using Attention Mechanisms in Eye-Tracking Data

  2024influential citation
• A novel multi-modal model to assist the diagnosis of autism spectrum disorder using eye-tracking data

  2024influential citation
• ALATT-network: automated LSTM-based framework for classification and monitoring of autism spectrum disorder therapy tasks

  2024cites this paper
• ASD2-TL∗ GTO: Autism spectrum disorders detection via transfer learning with gorilla troops optimizer framework

  2023cites this paper
• Transfer Learning Approach for Detection of Autism Spectrum Disorder using Facial Images

  2023cites this paper
• Applying the Eye-Tracking Method for the Classification of Neurological Disorders, Mental Diseases, and Speech Impairments Based on Machine Learning: an Overview

  2023cites this paper
• Detection of autism spectrum disorder from changing of pupil diameter using multi-modal feature fusion based hybrid CNN model

  2023cites this paper
• Eye Tracking Biomarkers for Autism Spectrum Disorder Detection using Machine Learning and Deep Learning Techniques: Review

  2023cites this paper
• Efficient Deep Learning-Based Data-Centric Approach for Autism Spectrum Disorder Diagnosis from Facial Images Using Explainable AI

  2023cites this paper
• Eye-tracking Dataset to Support the Research on Autism Spectrum Disorder

  2022cites this paper