Automatic Facial Recognition of Williams-Beuren Syndrome Based on Deep Convolutional Neural Networks

Liu, Hui; Mo, Zihua; Yang, Hang; Zhang, Zhengfu; Hong, Dian; Long, Wen; Lin, Min-Yin; Zheng, Ying-Yi; Zhang, Zhiwei; Xu, Xiaowei; Zhuang, Jian; Wang, Shushui

doi:10.3389/fped.2021.648255

Cited by 23 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, we collected a dataset of publicly available WS and 22q images, which may be larger than others previously studied ( Gurovich et al, 2019 ; Liu et al, 2021 ; Porras et al, 2021 ). Second, beyond the dataset, our approaches (and available code) may be used as subcomponents of other algorithms ( Duong et al, 2021b ).…”

Section: Discussionmentioning

confidence: 99%

Neural Networks for Classification and Image Generation of Aging in Genetic Syndromes

Duong

Tekendo‐Ngongang

et al. 2022

Front. Genet.

View full text Add to dashboard Cite

Background: In medical genetics, one application of neural networks is the diagnosis of genetic diseases based on images of patient faces. While these applications have been validated in the literature with primarily pediatric subjects, it is not known whether these applications can accurately diagnose patients across a lifespan. We aimed to extend previous works to determine whether age plays a factor in facial diagnosis as well as to explore other factors that may contribute to the overall diagnostic accuracy.Methods: To investigate this, we chose two relatively common conditions, Williams syndrome and 22q11.2 deletion syndrome. We built a neural network classifier trained on images of affected and unaffected individuals of different ages and compared classifier accuracy to clinical geneticists. We analyzed the results of saliency maps and the use of generative adversarial networks to boost accuracy.Results: Our classifier outperformed clinical geneticists at recognizing face images of these two conditions within each of the age groups (the performance varied between the age groups): 1) under 2 years old, 2) 2–9 years old, 3) 10–19 years old, 4) 20–34 years old, and 5) ≥35 years old. The overall accuracy improvement by our classifier over the clinical geneticists was 15.5 and 22.7% for Williams syndrome and 22q11.2 deletion syndrome, respectively. Additionally, comparison of saliency maps revealed that key facial features learned by the neural network differed with respect to age. Finally, joint training real images with multiple different types of fake images created by a generative adversarial network showed up to 3.25% accuracy gain in classification accuracy.Conclusion: The ability of clinical geneticists to diagnose these conditions is influenced by the age of the patient. Deep learning technologies such as our classifier can more accurately identify patients across the lifespan based on facial features. Saliency maps of computer vision reveal that the syndromic facial feature attributes change with the age of the patient. Modest improvements in the classifier accuracy were observed when joint training was carried out with both real and fake images. Our findings highlight the need for a greater focus on age as a confounder in facial diagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

Neural Networks for Classification and Image Generation of Aging in Genetic Syndromes

Duong

Tekendo‐Ngongang

et al. 2022

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…In addition, the automatic recognition of facial expressions has resulted in applications that span several disciplines. For example, facial expressions are used to identify pain [29,30], diagnose syndromes in infants [31,32], detect driver's drowsiness [33][34][35], recognize emotions [36][37][38][39][40], and detect engagement [41,42].…”

Section: Related Workmentioning

confidence: 99%

Human Attention Assessment Using A Machine Learning Approach with GAN-based Data Augmentation Technique Trained Using a Custom Dataset

Napoli¹,

Russo²,

Iocchi³

et al. 2022

OBM Neurobiol

View full text Add to dashboard Cite

Human–robot interactions require the ability of the system to determine if the user is paying attention. However, to train such systems, massive amounts of data are required. In this study, we addressed the issue of data scarcity by constructing a large dataset (containing ~120,000 photographs) for the attention detection task. Then, by using this dataset, we established a powerful baseline system. In addition, we extended the proposed system by adding an auxiliary face detection module and introducing a unique GAN-based data augmentation technique. Experimental results revealed that the proposed system yields superior performance compared to baseline models and achieves an accuracy of 88% on the test set. Finally, we created a web application for testing the proposed model in real time.

show abstract

“…This examination takes a long time ranging from 2-3 weeks [6], but in some cases, it can take up to 8 weeks and the costs incurred are pretty significant. So, it is difficult for all groups to do this [7]. In addition, doctors sometimes perform a physical examination on specific physical characteristics such as facial features, and Geneticists mostly do physical examinations at an early stage.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, computer-assisted development using artificial intelligence can be helpful in the accurate diagnosis of genetic diseases. Such artificial intelligence can increase the efficiency of early diagnosis work and provide valuable information to doctors and patients [7].…”

Section: Introductionmentioning

confidence: 99%

Face recognition in identifying genetic diseases: a progress review

Aurellia

Rahman

2023

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">Genetic diseases vary widely. Practitioners often face the complexity of determining genetic diseases. In distinguishing one genetic disease from another, it is difficult to do without a thorough test on the patient or also known as genetic testing. However, in some previous studies, genetic diseases have unique physical characteristics in sufferers. This leads to detecting differences in these physical characteristics to assist doctors in diagnosing people with genetic diseases. In recent years, facial recognition research has been quite active. Researchers continue to develop it from various existing methods, algorithms, approaches, and databases where the application is applied in various fields, one of which is medical imagery. Face recognition is one of the options for identifying disease. The condition of a person's face can be said to be a representation of a person's health. Where the accuracy in early detection can be pretty good, so face recognition is also one of the solutions that can be used to identify various genetic diseases in collaboration with artificial intelligence. This article review will focus more on the development of facial recognition in 2-dimensional images, showing that different methods can produce different results and face recognition can also overcome complex genetic disease variations. </span>

show abstract

Automatic Facial Recognition of Williams-Beuren Syndrome Based on Deep Convolutional Neural Networks

Cited by 23 publications

References 29 publications

Neural Networks for Classification and Image Generation of Aging in Genetic Syndromes

Neural Networks for Classification and Image Generation of Aging in Genetic Syndromes

Human Attention Assessment Using A Machine Learning Approach with GAN-based Data Augmentation Technique Trained Using a Custom Dataset

Face recognition in identifying genetic diseases: a progress review

Contact Info

Product

Resources

About