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

Alam, Mohammad Shafiul; Rashid, Muhammad Mahbubur; Faizabadi, Ahmed Rimaz; Mohd Zaki, Hasan Firdaus; Alam, Tasfiq E.; Ali, Md Shahin; Gupta, Kishor Datta; Ahsan, Md Manjurul

doi:10.3390/technologies11050115

Cited by 6 publications

(2 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 7 a depicts the first sample, which, when assessed using the weight w 1 (different domain), incorrectly classified the sample as NC due to the model’s failure to consider the specific facial landmarks accurately. According to previous research [ 40 ], the Xception model should primarily concentrate on the eye and nose region. The model accurately predicted the sample using the weight w 2 , which belonged to the same domain as the model trained with D2, as shown in Figure 7 b.…”

Section: Discussionmentioning

confidence: 99%

Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization

Alam,

Elsheikh,

Suliman

et al. 2024

Diagnostics

Self Cite

View full text Add to dashboard Cite

The early diagnosis of autism spectrum disorder (ASD) encounters challenges stemming from domain variations in facial image datasets. This study investigates the potential of active learning, particularly uncertainty-based sampling, for domain adaptation in early ASD diagnosis. Our focus is on improving model performance across diverse data sources. Utilizing the Kaggle ASD and YTUIA datasets, we meticulously analyze domain variations and assess transfer learning and active learning methodologies. Two state-of-the-art convolutional neural networks, Xception and ResNet50V2, pretrained on distinct datasets, demonstrate noteworthy accuracies of 95% on Kaggle ASD and 96% on YTUIA, respectively. However, combining datasets results in a modest decline in average accuracy, underscoring the necessity for effective domain adaptation techniques. We employ uncertainty-based active learning to address this, which significantly mitigates the accuracy drop. Xception and ResNet50V2 achieve 80% and 79% accuracy when pretrained on Kaggle ASD and applying active learning on YTUIA, respectively. Our findings highlight the efficacy of uncertainty-based active learning for domain adaptation, showcasing its potential to enhance accuracy and reduce annotation needs in early ASD diagnosis. This study contributes to the growing body of literature on ASD diagnosis methodologies. Future research should delve deeper into refining active learning strategies, ultimately paving the way for more robust and efficient ASD detection tools across diverse datasets.

show abstract

Section: Discussionmentioning

confidence: 99%

Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization

Alam,

Elsheikh,

Suliman

et al. 2024

Diagnostics

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition to EEG and fMRI, less prevalent modalities such as electrocorticography (ECoG), functional near-infrared spectroscopy (fNIRS), and Magnetoencephalography (MEG) have shown reasonable performance in ASD diagnosis [58]. An effective approach involves integrating machine-learning techniques with both functional and structural data to aid physicians in accurately assessing ASD [60].…”

Section: Neuroimaging and Monitoringmentioning

confidence: 99%

Nanotechnology - an innovative approach to cope with the distinctive challenges linked with Autism Spectrum Disorder

Bhat,

Alkhudhairy,

Alshehri

et al. 2024

IJACS

View full text Add to dashboard Cite

The brain stands out as the most intricate organ in the human body, governing cognitive, behavioral, and emotional functions. It is susceptible to various diseases, ranging from injuries to cancers and neurodegenerative conditions, making brain disorders a significant cause of disability and mortality. Overcoming challenges such as delivery, specificity, and toxicity has been a persistent issue in developing drugs that enhance brain structure and function, especially those that can traverse the complex barriers surrounding the brain. Nanotechnology represents a groundbreaking approach to address the unique challenges associated with Autism Spectrum Disorder (ASD). One significant challenge in ASD is early and accurate diagnosis. Nanotechnology can contribute to the development of highly sensitive and specific diagnostic tools, enabling the identification of biomarkers associated with ASD at an earlier stage. These nanoscale devices may facilitate a more precise understanding of the underlying biological mechanisms, leading to improved diagnostic capabilities. In terms of intervention, nanotechnology can enhance drug delivery systems, allowing for the more targeted and efficient administration of medications. This targeted drug delivery can potentially mitigate side effects while maximizing the therapeutic impact, addressing some of the challenges in managing the diverse symptoms of ASD. Despite the promising potential of nanotechnology in addressing ASD challenges, it is essential to approach these innovations with ethical considerations, ensuring that the benefits are accessible and equitable for individuals with ASD. Ongoing research and collaboration between experts in nanotechnology and autism can lead to transformative advancements in understanding, diagnosing, and managing ASD. This review delves into the application of nanotechnology in diagnosing and treating ASD and shedding light on the promising role of nanoparticles.

show abstract

Attention-Focused Eye Gaze Analysis to Predict Autistic Traits Using Transfer Learning

Vasant Bidwe,

Mishra,

Kamini Bajaj

et al. 2024

Int J Comput Intell Syst

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) is a complex developmental issue that affects the behavior and communication abilities of children. It is extremely needed to perceive it at an early age. The research article focuses on attentiveness by considering eye positioning as a key feature and its implementation is completed in two phases. In the first phase, various transfer learning algorithms are implemented and evaluated to predict ASD traits on available open-source image datasets Kaggle and Zenodo. To reinforce the result, fivefold cross-validation is used on the dataset. Progressive pre-trained algorithms named VGG 16, VGG 19, InceptionV3, ResNet152V2, DenseNet201, ConNextBase, EfficientNetB1, NasNetMobile, and InceptionResNEtV2 implemented to establish the correctness of the result. The result is being compiled and analyzed that ConvNextBase model has the best diagnosing ability on both datasets. This model achieved a prediction accuracy of 80.4% on Kaggle with a batch size of 16, a learning rate of 0.00002, 10 epochs and 6 units, and a prediction accuracy of 80.71% on the Zenodo dataset with a batch size of 4, a learning rate of 0.00002, 10 epochs and 4 units. The accuracy of the model ConvNextBase is found challenging in nature as compared to an existing model. Attentiveness is a parameter that will accurately diagnose the visual behavior of the participant which helps in the automatic prediction of autistic traits. In the second phase of the proposed model, attentiveness is engrossed in identifying autistic traits. The model uses a dlib library that uses HOG and Linear SVM-based face detectors to identify a particular facial parameter called EAR and it is used to measure participants' attentiveness based on the eye gaze analysis. If the EAR value is less than 0.20 for more than 100 consecutive frames, the model concludes the participant is un-attentive. The model generated a special graph for a time period by continuously plotting the value of EAR based on the attention level. The average EAR value will depict the attentiveness of the participant.

show abstract

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

Cited by 6 publications

References 56 publications

Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization

Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization

Nanotechnology - an innovative approach to cope with the distinctive challenges linked with Autism Spectrum Disorder

Attention-Focused Eye Gaze Analysis to Predict Autistic Traits Using Transfer Learning

Contact Info

Product

Resources

About