Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by differences in social communication and repetitive behaviors, often associated with atypical visual attention patterns. In this paper, the Gaze-Based Autism Classifier (GBAC) is proposed, which is a Deep Neural Network...

Full description

Saved in:
Bibliographic Details
Main Authors: Federica Colonnese, Francesco Di Luzio, Antonello Rosato, Massimo Panella
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7792
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850106538979491840
author Federica Colonnese
Francesco Di Luzio
Antonello Rosato
Massimo Panella
author_facet Federica Colonnese
Francesco Di Luzio
Antonello Rosato
Massimo Panella
author_sort Federica Colonnese
collection DOAJ
description Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by differences in social communication and repetitive behaviors, often associated with atypical visual attention patterns. In this paper, the Gaze-Based Autism Classifier (GBAC) is proposed, which is a Deep Neural Network model that leverages both data distillation and data attribution techniques to enhance ASD classification accuracy and explainability. Using data sampled by eye tracking sensors, the model identifies unique gaze behaviors linked to ASD and applies an explainability technique called TracIn for data attribution by computing self-influence scores to filter out noisy or anomalous training samples. This refinement process significantly improves both accuracy and computational efficiency, achieving a test accuracy of 94.35% while using only 77% of the dataset, showing that the proposed GBAC outperforms the same model trained on the full dataset and random sample reductions, as well as the benchmarks. Additionally, the data attribution analysis provides insights into the most influential training examples, offering a deeper understanding of how gaze patterns correlate with ASD-specific characteristics. These results underscore the potential of integrating explainable artificial intelligence into neurodevelopmental disorder diagnostics, advancing clinical research by providing deeper insights into the visual attention patterns associated with ASD.
format Article
id doaj-art-27728367b13d4eb98012bf4fddf0a441
institution OA Journals
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-27728367b13d4eb98012bf4fddf0a4412025-08-20T02:38:48ZengMDPI AGSensors1424-82202024-12-012423779210.3390/s24237792Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural NetworksFederica Colonnese0Francesco Di Luzio1Antonello Rosato2Massimo Panella3Department of Information Engineering, Electronics and Telecommunications (DIET), University of Rome “La Sapienza”, Via Eudossiana 18, 00184 Rome, ItalyDepartment of Information Engineering, Electronics and Telecommunications (DIET), University of Rome “La Sapienza”, Via Eudossiana 18, 00184 Rome, ItalyDepartment of Information Engineering, Electronics and Telecommunications (DIET), University of Rome “La Sapienza”, Via Eudossiana 18, 00184 Rome, ItalyDepartment of Information Engineering, Electronics and Telecommunications (DIET), University of Rome “La Sapienza”, Via Eudossiana 18, 00184 Rome, ItalyAutism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by differences in social communication and repetitive behaviors, often associated with atypical visual attention patterns. In this paper, the Gaze-Based Autism Classifier (GBAC) is proposed, which is a Deep Neural Network model that leverages both data distillation and data attribution techniques to enhance ASD classification accuracy and explainability. Using data sampled by eye tracking sensors, the model identifies unique gaze behaviors linked to ASD and applies an explainability technique called TracIn for data attribution by computing self-influence scores to filter out noisy or anomalous training samples. This refinement process significantly improves both accuracy and computational efficiency, achieving a test accuracy of 94.35% while using only 77% of the dataset, showing that the proposed GBAC outperforms the same model trained on the full dataset and random sample reductions, as well as the benchmarks. Additionally, the data attribution analysis provides insights into the most influential training examples, offering a deeper understanding of how gaze patterns correlate with ASD-specific characteristics. These results underscore the potential of integrating explainable artificial intelligence into neurodevelopmental disorder diagnostics, advancing clinical research by providing deeper insights into the visual attention patterns associated with ASD.https://www.mdpi.com/1424-8220/24/23/7792autism spectrum disordergaze analysiseye tracking sensorsdeep neural networksexplainabilityTracIn method
spellingShingle Federica Colonnese
Francesco Di Luzio
Antonello Rosato
Massimo Panella
Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks
Sensors
autism spectrum disorder
gaze analysis
eye tracking sensors
deep neural networks
explainability
TracIn method
title Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks
title_full Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks
title_fullStr Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks
title_full_unstemmed Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks
title_short Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks
title_sort enhancing autism detection through gaze analysis using eye tracking sensors and data attribution with distillation in deep neural networks
topic autism spectrum disorder
gaze analysis
eye tracking sensors
deep neural networks
explainability
TracIn method
url https://www.mdpi.com/1424-8220/24/23/7792
work_keys_str_mv AT federicacolonnese enhancingautismdetectionthroughgazeanalysisusingeyetrackingsensorsanddataattributionwithdistillationindeepneuralnetworks
AT francescodiluzio enhancingautismdetectionthroughgazeanalysisusingeyetrackingsensorsanddataattributionwithdistillationindeepneuralnetworks
AT antonellorosato enhancingautismdetectionthroughgazeanalysisusingeyetrackingsensorsanddataattributionwithdistillationindeepneuralnetworks
AT massimopanella enhancingautismdetectionthroughgazeanalysisusingeyetrackingsensorsanddataattributionwithdistillationindeepneuralnetworks