Efficient Deep Learning-Based Data-Centric Approach for Autism Spectrum Disorder Diagnosis from Facial Images Using Explainable AI

被引:9
作者
Alam, Mohammad Shafiul [1 ]
Rashid, Muhammad Mahbubur [1 ]
Faizabadi, Ahmed Rimaz [1 ]
Mohd Zaki, Hasan Firdaus [1 ]
Alam, Tasfiq E. [2 ]
Ali, Md Shahin [3 ]
Gupta, Kishor Datta [4 ]
Ahsan, Md Manjurul [2 ]
机构
[1] Int Islamic Univ Malaysia, Dept Mechatron Engn, Jln Gomak, Kuala Lumpur 53100, Malaysia
[2] Univ Oklahoma, Ind & Syst Engn, Norman, OK 73019 USA
[3] Islamic Univ, Dept Biomed Engn, Kushtia 7003, Bangladesh
[4] Clark Atlanta Univ, Comp & Informat Sci, Atlanta, GA 30314 USA
关键词
deep learning; convolutional neural network; ASD diagnosis; augmentation; facial image; NEURAL-NETWORKS;
D O I
10.3390/technologies11050115
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The research describes an effective deep learning-based, data-centric approach for diagnosing autism spectrum disorder from facial images. To classify ASD and non-ASD subjects, this method requires training a convolutional neural network using the facial image dataset. As a part of the data-centric approach, this research applies pre-processing and synthesizing of the training dataset. The trained model is subsequently evaluated on an independent test set in order to assess the performance matrices of various data-centric approaches. The results reveal that the proposed method that simultaneously applies the pre-processing and augmentation approach on the training dataset outperforms the recent works, achieving excellent 98.9% prediction accuracy, sensitivity, and specificity while having 99.9% AUC. This work enhances the clarity and comprehensibility of the algorithm by integrating explainable AI techniques, providing clinicians with valuable and interpretable insights into the decision-making process of the ASD diagnosis model.
引用
收藏
页数:27
相关论文
共 61 条
[1]   A systematic literature review on hardware implementation of artificial intelligence algorithms [J].
Abu Talib, Manar ;
Majzoub, Sohaib ;
Nasir, Qassim ;
Jamal, Dina .
JOURNAL OF SUPERCOMPUTING, 2021, 77 (02) :1897-1938
[2]   RETRACTED: Facial Features Detection System To Identify Children With Autism Spectrum Disorder: Deep Learning Models (Retracted Article) [J].
Ahmed, Zeyad A. T. ;
Aldhyani, Theyazn H. H. ;
Jadhav, Mukti E. ;
Alzahrani, Mohammed Y. ;
Alzahrani, Mohammad Eid ;
Althobaiti, Maha M. ;
Alassery, Fawaz ;
Alshaflut, Ahmed ;
Alzahrani, Nouf Matar ;
Al-madani, Ali Mansour .
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2022, 2022
[3]   Monkeypox Diagnosis With Interpretable Deep Learning [J].
Ahsan, Md. Manjurul ;
Ali, Md. Shahin ;
Hassan, Md. Mehedi ;
Abdullah, Tareque Abu ;
Gupta, Kishor Datta ;
Bagci, Ulas ;
Kaushal, Chetna ;
Soliman, Naglaa F. .
IEEE ACCESS, 2023, 11 :81965-81980
[4]   Deep transfer learning approaches for Monkeypox disease diagnosis [J].
Ahsan, Md Manjurul ;
Uddin, Muhammad Ramiz ;
Ali, Md Shahin ;
Islam, Md Khairul ;
Farjana, Mithila ;
Sakib, Ahmed Nazmus ;
Al Momin, Khondhaker ;
Luna, Shahana Akter .
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 216
[5]   Machine-Learning-Based Disease Diagnosis: A Comprehensive Review [J].
Ahsan, Md Manjurul ;
Luna, Shahana Akter ;
Siddique, Zahed .
HEALTHCARE, 2022, 10 (03)
[6]   A Hybrid Deep Learning Model to Predict the Impact of COVID-19 on Mental Health From Social Media Big Data [J].
Al Banna, Md. Hasan ;
Ghosh, Tapotosh ;
Al Nahian, Md. Jaber ;
Kaiser, M. Shamim ;
Mahmud, Mufti ;
Abu Taher, Kazi ;
Hossain, Mohammad Shahadat ;
Andersson, Karl .
IEEE ACCESS, 2023, 11 :77009-77022
[7]   A Monitoring System for Patients of Autism Spectrum Disorder Using Artificial Intelligence [J].
Al Banna, Md Hasan ;
Ghosh, Tapotosh ;
Abu Taher, Kazi ;
Kaiser, M. Shamim ;
Mahmud, Mufti .
BRAIN INFORMATICS, BI 2020, 2020, 12241 :251-262
[8]   Empirical Study of Autism Spectrum Disorder Diagnosis Using Facial Images by Improved Transfer Learning Approach [J].
Alam, Md Shafiul ;
Rashid, Muhammad Mahbubur ;
Roy, Rupal ;
Faizabadi, Ahmed Rimaz ;
Gupta, Kishor Datta ;
Ahsan, Md Manjurul .
BIOENGINEERING-BASEL, 2022, 9 (11)
[9]  
Ali Md Shahin, 2021, 2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA), P1, DOI 10.1109/CAIDA51941.2021.9425212
[10]   A Novel Approach for Best Parameters Selection and Feature Engineering to Analyze and Detect Diabetes: Machine Learning Insights [J].
Ali, Md Shahin ;
Islam, Md Khairul ;
Das, A. Arjan ;
Duranta, D. U. S. ;
Haque, Mst. Farija ;
Rahman, Md Habibur .
BIOMED RESEARCH INTERNATIONAL, 2023, 2023