Genetic syndromes screening by facial recognition technology: VGG-16 screening model construction and evaluation

Abstract

Background Many genetic syndromes (GSs) have distinct facial dysmorphism, and facial gestalts can be used as a diagnostic tool for recognizing a syndrome. Facial recognition technology has advanced in recent years, and the screening of GSs by facial recognition technology has become feasible. This study constructed an automatic facial recognition model for the identification of children with GSs. Results A total of 456 frontal facial photos were collected from 228 children with GSs and 228 healthy children in Guangdong Provincial People's Hospital from Jun 2016 to Jan 2021. Only one frontal facial image was selected for each participant. The VGG-16 network (named after its proposal lab, Visual Geometry Group from Oxford University) was pretrained by transfer learning methods, and a facial recognition model based on the VGG-16 architecture was constructed. The performance of the VGG-16 model was evaluated by five-fold cross-validation. Comparison of VGG-16 model to five physicians were also performed. The VGG-16 model achieved the highest accuracy of 0.8860 ± 0.0211, specificity of 0.9124 ± 0.0308, recall of 0.8597 ± 0.0190, F1-score of 0.8829 ± 0.0215 and an area under the receiver operating characteristic curve of 0.9443 ± 0.0276 (95% confidence interval: 0.9210–0.9620) for GS screening, which was significantly higher than that achieved by human experts. Conclusions This study highlighted the feasibility of facial recognition technology for GSs identification. The VGG-16 recognition model can play a prominent role in GSs screening in clinical practice.

A nomogram based on radiomics signature and deep-learning signature for preoperative prediction of axillary lymph node metastasis in breast cancer

“…VGG-16 was used to extract deep-learning features ( 23 , 24 ). The maximum cross-sectional area of the tumor ROI was selected and cropped to the two-dimensional rectangular image covering the entire tumor.…”

Review on Facial-Recognition-Based Applications in Disease Diagnosis

“…To acquire images with high quality, the process of image capture is standardized. In current studies, clinicians ask patients to expose the entire face and ears; to tidy up hair; to open the eyes and look straight; to close the mouth; to present a neutral and relaxed expression [ 16 , 17 ]. In neurological disorders, patients are asked to perform speech or motor tasks to evaluate their facial neuromuscular function [ 18 ].…”

“…Controls are normally age- and sex-matched individuals without the target disease. In some conditions, the sample is divided into a training set and a testing set processed by cross-validation [ 17 , 21 ]. The training set is to establish the algorithm and refine parameters.…”

Face recognition in identifying genetic diseases: a progress review

“…According to several previous studies, research has been carried out on the development of detecting genetic diseases using facial recognition [7], [19], [20]. In a study conducted by Liu et al in 2021, researching the faces of patients with WBS using the convolutional neural network (CNN) showed promising results of 92.7% [7].…”

“…Then a study conducted by a research group from Turkey in 2012 with down syndrome patients produced a maximum accuracy of 97.34% using the Gabor wavelet transform and support vector machine (SVM) [19]. Meanwhile, research by Hong et al also using CNN, can identify several genetic diseases with an accuracy of 88.6% from 456 children's facial data [20]. This means that the identification of genetic diseases from facial dysmorphology can be conducted and developed further.…”