Early detection of children with Autism Spectrum Disorder based on visual exploration of images

Mazumdar, Pramit; Arru, Giuliano; Battisti, Federica

doi:10.1016/j.image.2021.116184

Cited by 38 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The features were extracted from display behaviour, image content and scene centres. The system achieved high performance in distinguishing children with autism spectrum from typically developing children [18]. Belen et al presented the EyeXplain Autism method that enables clinicians to track eyes, analyse data and interpret data extracted by DNN [19].…”

Section: Related Workmentioning

confidence: 99%

“…x(t) is the input, w(t) is the filter, and s(t) is the output of the convolutional layer called the deep feature map. If t is an integer value and w is defined only with integer values, then as Equation (18):…”

Section: Cnn Modelsmentioning

confidence: 99%

“…Accuracy % Precision % Sensitivity % Specificity % AUC % Zhao, Z.; et al [38] 84.62 -89.47 80 86.00 Akter, T.; et al [39] 74.20 -74.20 68.8 71.5 Oliveira, J.S. ; et al [20] 79.50 90.00 69.00 93 -Mazumdar, P.; et al [18] 59.00 57.00 68.00 50.00 -Raj, S.; et al [40] 95…”

Section: Previous Studiesmentioning

confidence: 99%

See 2 more Smart Citations

Eye Tracking-Based Diagnosis and Early Detection of Autism Spectrum Disorder Using Machine Learning and Deep Learning Techniques

et al. 2022

View full text Add to dashboard Cite

Eye tracking is a useful technique for detecting autism spectrum disorder (ASD). One of the most important aspects of good learning is the ability to have atypical visual attention. The eye-tracking technique provides useful information about children’s visual behaviour for early and accurate diagnosis. It works by scanning the paths of the eyes to extract a sequence of eye projection points on the image to analyse the behaviour of children with autism. In this study, three artificial-intelligence techniques were developed, namely, machine learning, deep learning, and a hybrid technique between them, for early diagnosis of autism. The first technique, neural networks [feedforward neural networks (FFNNs) and artificial neural networks (ANNs)], is based on feature classification extracted by a hybrid method between local binary pattern (LBP) and grey level co-occurrence matrix (GLCM) algorithms. This technique achieved a high accuracy of 99.8% for FFNNs and ANNs. The second technique used a pre-trained convolutional neural network (CNN) model, such as GoogleNet and ResNet-18, on the basis of deep feature map extraction. The GoogleNet and ResNet-18 models achieved high performances of 93.6% and 97.6%, respectively. The third technique used the hybrid method between deep learning (GoogleNet and ResNet-18) and machine learning (SVM), called GoogleNet + SVM and ResNet-18 + SVM. This technique depends on two blocks. The first block used CNN to extract deep feature maps, whilst the second block used SVM to classify the features extracted from the first block. This technique proved its high diagnostic ability, achieving accuracies of 95.5% and 94.5% for GoogleNet + SVM and ResNet-18 + SVM, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Cnn Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Eye Tracking-Based Diagnosis and Early Detection of Autism Spectrum Disorder Using Machine Learning and Deep Learning Techniques

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The study suggested that the facial expressions of these children have a typical behavior. The study [16] used an eye‐tracking image dataset to train an ML classifier to identify children affected by autism. The paper [17] presented a review of using computer vision to analyze faces face in health and medical applications.…”

Section: Related Workmentioning

confidence: 99%

Comparing automated and non‐automated machine learning for autism spectrum disorders classification using facial images

et al. 2022

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) is a developmental disorder associated with cognitive and neurobehavioral disorders. It affects the person's behavior and performance. Autism affects verbal and non-verbal communication in social interactions. Early screening and diagnosis of ASD are essential and helpful for early educational planning and treatment, the provision of family support, and for providing appropriate medical support for the child on time. Thus, developing automated methods for diagnosing ASD is becoming an essential need. Herein, we investigate using various machine learning methods to build predictive models for diagnosing ASD in children using facial images. To achieve this, we used an autistic children dataset containing 2936 facial images of children with autism and typical children. In application, we used classical machine learning methods, such as support vector machine and random forest. In addition to using deep-learning methods, we used a state-of-the-art method, that is, automated machine learning (AutoML). We compared the results obtained from the existing techniques. Consequently, we obtained that AutoML achieved the highest performance of approximately 96% accuracy via the Hyperpot and tree-based pipeline optimization tool optimization. Furthermore, AutoML methods enabled us to easily find the best parameter settings without any human efforts for feature engineering.

show abstract

“…Intuitively attention modelling can be considered as an important indicator for estimating which FOVs a subject would look at. Attention modelling has also been successfully utilised in parallel domain of research such as medical image analysis [2,5], autism spectrum disorder classification [1,12], etc.…”

Section: Introductionmentioning

confidence: 99%

Deep reinforcement learning approach to predict head movement in 360° videos

Tanmay¹,

Pramit²

2022

Self Cite

View full text Add to dashboard Cite

The popularity of 360°videos has grown immensely in the last few years. One probable reason is the availability of lowcost devices and ease in capturing them. Additionally, users have shown interest in this particular type of media due to its inherent feature of being immersive, which is completely absent in traditional 2D videos. Nowadays such powerful 360°videos have many applications such as generating various content-specific videos (gaming, knowledge, travel, sports, educational, etc.), during surgeries by medical professionals, in autonomous vehicles, etc. A typical 360°video when seen through a Head Mounted Display (HMD) gives an immersive feeling, where the viewer perceives standing within the real environment in a virtual platform. Similar to real life, at any point in time, the viewer can view only a particular region and not the entire 360°content. Viewers adopts physical movement for exploring the total 360°content. However, due to the large volume of 360°media, it faces challenges during transmission. Adaptive compression techniques have been incorporated in this regard, which is in accordance with the viewing behaviour of a viewer. Therefore, with the growing popularity and usage of 360°media, the adaptive compression methodologies are in development. One important factor in adaptive compression is the estimation of the natural field-of-view (FOV) of a viewer watching 360°content using a HMD. The FOV estimation task becomes more challenging due to the spatial displacement of the viewer with respect to the dynamically changing video content. In this work, we propose a model to estimate the FOV of a user viewing a 360°video using an HMD. This task is popularly known as the Virtual Cinematography. The proposed FOVS-electionNet is primarily based on a reinforcement learning framework. In addition to this, saliency estimation is proved to be a very powerful indicator for attention modelling. Therefore, in this proposed network we utilise a saliency indicator for driving the reward function of the reinforcement learning framework. Experiments are performed on the benchmark Pano2Vid 360°dataset, and the results are observed to be similar to human exploration.

show abstract

Early detection of children with Autism Spectrum Disorder based on visual exploration of images

Cited by 38 publications

References 26 publications

Eye Tracking-Based Diagnosis and Early Detection of Autism Spectrum Disorder Using Machine Learning and Deep Learning Techniques

Eye Tracking-Based Diagnosis and Early Detection of Autism Spectrum Disorder Using Machine Learning and Deep Learning Techniques

Comparing automated and non‐automated machine learning for autism spectrum disorders classification using facial images

Deep reinforcement learning approach to predict head movement in 360° videos

Contact Info

Product

Resources

About

Early detection of children with Autism Spectrum Disorder based on visual exploration of images

Cited by 38 publications

References 26 publications

Eye Tracking-Based Diagnosis and Early Detection of Autism Spectrum Disorder Using Machine Learning and Deep Learning Techniques

Eye Tracking-Based Diagnosis and Early Detection of Autism Spectrum Disorder Using Machine Learning and Deep Learning Techniques

Comparing automated and non‐automated machine learning for autism spectrum disorders classification using facial images

Deep reinforcement learning approach to predict head movement in 360&#xB0; videos

Contact Info

Product

Resources

About

Deep reinforcement learning approach to predict head movement in 360° videos