Automatic Identification of Down Syndrome Using Facial Images with Deep Convolutional Neural Network

Qin, Bosheng; Liang, Letian; Wu, Jingchao; Quan, Qiyao; Wang, Zeyu; Li, Dongxiao

doi:10.3390/diagnostics10070487

Cited by 35 publications

(22 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The distinctive facial characteristics in facemask-wearing conditions provide an opportunity for automatic identification. Recent rapid technological innovations in deep learning and computer vision have presented opportunities for development in many fields [ 9 , 10 ]. As the main component of deep learning methods, deep neural networks (DNNs) have demonstrated superior performance in many fields, including object detection, image classification, image segmentation, and distancing detection [ 11 , 12 , 13 , 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Identifying Facemask-Wearing Condition Using Image Super-Resolution with Classification Network to Prevent COVID-19

Qin

2020

Sensors

Self Cite

203

View full text Add to dashboard Cite

The rapid worldwide spread of Coronavirus Disease 2019 (COVID-19) has resulted in a global pandemic. Correct facemask wearing is valuable for infectious disease control, but the effectiveness of facemasks has been diminished, mostly due to improper wearing. However, there have not been any published reports on the automatic identification of facemask-wearing conditions. In this study, we develop a new facemask-wearing condition identification method by combining image super-resolution and classification networks (SRCNet), which quantifies a three-category classification problem based on unconstrained 2D facial images. The proposed algorithm contains four main steps: Image pre-processing, facial detection and cropping, image super-resolution, and facemask-wearing condition identification. Our method was trained and evaluated on the public dataset Medical Masks Dataset containing 3835 images with 671 images of no facemask-wearing, 134 images of incorrect facemask-wearing, and 3030 images of correct facemask-wearing. Finally, the proposed SRCNet achieved 98.70% accuracy and outperformed traditional end-to-end image classification methods using deep learning without image super-resolution by over 1.5% in kappa. Our findings indicate that the proposed SRCNet can achieve high-accuracy identification of facemask-wearing conditions, thus having potential applications in epidemic prevention involving COVID-19.

show abstract

Section: Introductionmentioning

confidence: 99%

Identifying Facemask-Wearing Condition Using Image Super-Resolution with Classification Network to Prevent COVID-19

Qin

2020

Sensors

Self Cite

203

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Based on the automatic detection of facial features, CNNs have been incorporated into the assisted diagnosis of genetic syndromes. Several studies showed that CNN-based facial recognition models for genetic syndrome diagnosis achieved high accuracy ( 9 – 12 ). In 2019, Gurovich et al ( 10 ) reported a deep CNN framework, DeepGestalt, trained on a dataset of over 17,000 pictures of faces representing more than 200 syndromes.…”

Section: Introductionmentioning

confidence: 99%

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

Liu

Yang

et al. 2021

Front. Pediatr.

View full text Add to dashboard Cite

Background: Williams-Beuren syndrome (WBS) is a rare genetic syndrome with a characteristic “elfin” facial gestalt. The “elfin” facial characteristics include a broad forehead, periorbital puffiness, flat nasal bridge, short upturned nose, wide mouth, thick lips, and pointed chin. Recently, deep convolutional neural networks (CNNs) have been successfully applied to facial recognition for diagnosing genetic syndromes. However, there is little research on WBS facial recognition using deep CNNs.Objective: The purpose of this study was to construct an automatic facial recognition model for WBS diagnosis based on deep CNNs.Methods: The study enrolled 104 WBS children, 91 cases with other genetic syndromes, and 145 healthy children. The photo dataset used only one frontal facial photo from each participant. Five face recognition frameworks for WBS were constructed by adopting the VGG-16, VGG-19, ResNet-18, ResNet-34, and MobileNet-V2 architectures, respectively. ImageNet transfer learning was used to avoid over-fitting. The classification performance of the facial recognition models was assessed by five-fold cross validation, and comparison with human experts was performed.Results: The five face recognition frameworks for WBS were constructed. The VGG-19 model achieved the best performance. The accuracy, precision, recall, F1 score, and area under curve (AUC) of the VGG-19 model were 92.7 ± 1.3%, 94.0 ± 5.6%, 81.7 ± 3.6%, 87.2 ± 2.0%, and 89.6 ± 1.3%, respectively. The highest accuracy, precision, recall, F1 score, and AUC of human experts were 82.1, 65.9, 85.6, 74.5, and 83.0%, respectively. The AUCs of each human expert were inferior to the AUCs of the VGG-16 (88.6 ± 3.5%), VGG-19 (89.6 ± 1.3%), ResNet-18 (83.6 ± 8.2%), and ResNet-34 (86.3 ± 4.9%) models.Conclusions: This study highlighted the possibility of using deep CNNs for diagnosing WBS in clinical practice. The facial recognition framework based on VGG-19 could play a prominent role in WBS diagnosis. Transfer learning technology can help to construct facial recognition models of genetic syndromes with small-scale datasets.

show abstract

“…on the one hand, arti cial intelligence and machine learning methods can quickly and accurately complete the basic data cleaning and large-scale data sorting, and on the other hand, do data mining for massive tongue & pulse data. Different recognition algorithms and machine learning methods have been widely used in image recognition, target detection, natural language processing, and other elds [10][11][12]. Nowadays, breakthroughs have been made in fatigue quanti cation and standardization.…”

Section: Introductionmentioning

confidence: 99%

Clinical data mining on network of symptom and index and correlation of tongue-pulse data in fatigue population

Shi

Cui

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Fatigue is a kind of non-specific symptom, which occurs widely in sub-health and various diseases. It is closely related to people's physical and mental health. Due to the lack of objective diagnosis criteria, it is often neglected in clinical diagnosis, especially in the early disease stage. Many clinical practices and research have shown that tongue and pulse conditions reflect the body's overall state. Establishing an objective evaluation method for diagnosing disease fatigue and non-disease fatigue by combining clinical symptoms, indexes, and tongue & pulse data is of great significance for timely and effective clinical treatment.Methods: In this study, 2632 physical examination populations were divided into healthy controls, sub-health fatigue group, and disease fatigue group. Complex network technology was used to screen out the core symptoms and Western medicine indexes of sub-health fatigue and disease fatigue populations. Pajek software was used to construct the core symptoms/indexes network and core symptoms-indexes combined network. Simultaneously, the canonical correlation analysis method was used to analyze the objective tongue & pulse data between the two groups of fatigue population and analyze the distribution of tongue & pulse data.Results: Some similarities were found in the core symptoms of sub-health fatigue and disease fatigue population, but with different node importance. The node-importance difference indicated that the diagnostic contribution rate of the same symptom to the two groups was different. The canonical correlation coefficient of tongue & pulse data in the disease fatigue group was 0.42 (P < 0.05). On the contrast, correlation analysis of tongue & pulse in the sub-health fatigue group showed no statistical significance. Conclusions: The complex network technology was suitable for the correlation analysis of symptoms and indexes in the fatigue population, and the tongue & pulse data had a certain diagnostic contribution to the classification of the fatigue population.Name of the registry: Chinese Clinical Trial RegistryTrial registration number: ChiCTR-IOR-15006502; ChiCTR1900026008Date of registration: Jun. 04th, 2015URL of trial registry record: http://www.chictr.org.cn/showprojen.aspx?proj=11119;http://www.chictr.org.cn/edit.aspx?pid=38828&htm=4 (This is a retrospective registration)

show abstract

Automatic Identification of Down Syndrome Using Facial Images with Deep Convolutional Neural Network

Cited by 35 publications

References 42 publications

Identifying Facemask-Wearing Condition Using Image Super-Resolution with Classification Network to Prevent COVID-19

Identifying Facemask-Wearing Condition Using Image Super-Resolution with Classification Network to Prevent COVID-19

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

Clinical data mining on network of symptom and index and correlation of tongue-pulse data in fatigue population

Contact Info

Product

Resources

About