Williams-Beuren syndrome (WBS) is a rare genetic disorder characterized by special facial gestalt, delayed development, and supravalvular aortic stenosis or/and stenosis of the branches of the pulmonary artery. We aim to develop and optimize accurate models of facial recognition to assist in the diagnosis of WBS, and to evaluate their effectiveness by using both five-fold cross-validation and an external test set. We used a total of 954 images from 135 patients with WBS, 124 patients suffering from other genetic disorders, and 183 healthy children. The training set comprised 852 images of 104 WBS cases, 91 cases of other genetic disorders, and 145 healthy children from September 2017 to December 2021 at the Guangdong Provincial People\'s Hospital. We constructed six binary classification models of facial recognition for WBS by using EfficientNet-b3, ResNet-50, VGG-16, VGG-16BN, VGG-19, and VGG-19BN. Transfer learning was used to pre-train the models, and each model was modified with a variable cosine learning rate. Each model was first evaluated by using five-fold cross-validation and then assessed on the external test set. The latter contained 102 images of 31 children suffering from WBS, 33 children with other genetic disorders, and 38 healthy children. To compare the capabilities of these models of recognition with those of human experts in terms of identifying cases of WBS, we recruited two pediatricians, a pediatric cardiologist, and a pediatric geneticist to identify the WBS patients based solely on their facial images. We constructed six models of facial recognition for diagnosing WBS using EfficientNet-b3, ResNet-50, VGG-16, VGG-16BN, VGG-19, and VGG-19BN. The model based on VGG-19BN achieved the best performance in terms of five-fold cross-validation, with an accuracy of 93.74% ± 3.18%, precision of 94.93% ± 4.53%, specificity of 96.10% ± 4.30%, and F1 score of 91.65% ± 4.28%, while the VGG-16BN model achieved the highest recall value of 91.63% ± 5.96%. The VGG-19BN model also achieved the best performance on the external test set, with an accuracy of 95.10%, precision of 100%, recall of 83.87%, specificity of 93.42%, and F1 score of 91.23%. The best performance by human experts on the external test set yielded values of accuracy, precision, recall, specificity, and F1 scores of 77.45%, 60.53%, 77.42%, 83.10%, and 66.67%, respectively. The F1 score of each human expert was lower than those of the EfficientNet-b3 (84.21%), ResNet-50 (74.51%), VGG-16 (85.71%), VGG-16BN (85.71%), VGG-19 (83.02%), and VGG-19BN (91.23%) models.
CONCLUSIONS: The results showed that facial recognition technology can be used to accurately diagnose patients with WBS. Facial recognition models based on VGG-19BN can play a crucial role in its clinical diagnosis. Their performance can be improved by expanding the size of the training dataset, optimizing the CNN architectures applied, and modifying them with a variable cosine learning rate.
BACKGROUND: • The facial gestalt of WBS, often described as \"elfin,\" includes a broad forehead, periorbital puffiness, a flat nasal bridge, full cheeks, and a small chin. • Recent studies have demonstrated the potential of deep convolutional neural networks for facial recognition as a diagnostic tool for WBS.
BACKGROUND: • This study develops six models of facial recognition, EfficientNet-b3, ResNet-50, VGG-16, VGG-16BN, VGG-19, and VGG-19BN, to improve WBS diagnosis. • The VGG-19BN model achieved the best performance, with an accuracy of 95.10% and specificity of 93.42%. The facial recognition model based on VGG-19BN can play a crucial role in the clinical diagnosis of WBS.

With the continuous progress of technology, the subject of life science plays an increasingly important role, among which the application of artificial intelligence in the medical field has attracted more and more attention. Bell facial palsy, a neurological ailment characterized by facial muscle weakness or paralysis, exerts a profound impact on patients\' facial expressions and masticatory abilities, thereby inflicting considerable distress upon their overall quality of life and mental well-being. In this study, we designed a facial attribute recognition model specifically for individuals with Bell\'s facial palsy. The model utilizes an enhanced SSD network and scientific computing to perform a graded assessment of the patients\' condition. By replacing the VGG network with a more efficient backbone, we improved the model\'s accuracy and significantly reduced its computational burden. The results show that the improved SSD network has an average precision of 87.9% in the classification of light, middle and severe facial palsy, and effectively performs the classification of patients with facial palsy, where scientific calculations also increase the precision of the classification. This is also one of the most significant contributions of this article, which provides intelligent means and objective data for future research on intelligent diagnosis and treatment as well as progressive rehabilitation.

BACKGROUND: Noonan syndrome (NS) is a rare genetic disease, and patients who suffer from it exhibit a facial morphology that is characterized by a high forehead, hypertelorism, ptosis, inner epicanthal folds, down-slanting palpebral fissures, a highly arched palate, a round nasal tip, and posteriorly rotated ears. Facial analysis technology has recently been applied to identify many genetic syndromes (GSs). However, few studies have investigated the identification of NS based on the facial features of the subjects.
OBJECTIVE: This study develops advanced models to enhance the accuracy of diagnosis of NS.
METHODS: A total of 1,892 people were enrolled in this study, including 233 patients with NS, 863 patients with other GSs, and 796 healthy children. We took one to 10 frontal photos of each subject to build a dataset, and then applied the multi-task convolutional neural network (MTCNN) for data pre-processing to generate standardized outputs with five crucial facial landmarks. The ImageNet dataset was used to pre-train the network so that it could capture generalizable features and minimize data wastage. We subsequently constructed seven models for facial identification based on the VGG16, VGG19, VGG16-BN, VGG19-BN, ResNet50, MobileNet-V2, and squeeze-and-excitation network (SENet) architectures. The identification performance of seven models was evaluated and compared with that of six physicians.
RESULTS: All models exhibited a high accuracy, precision, and specificity in recognizing NS patients. The VGG19-BN model delivered the best overall performance, with an accuracy of 93.76%, precision of 91.40%, specificity of 98.73%, and F1 score of 78.34%. The VGG16-BN model achieved the highest AUC value of 0.9787, while all models based on VGG architectures were superior to the others on the whole. The highest scores of six physicians in terms of accuracy, precision, specificity, and the F1 score were 74.00%, 75.00%, 88.33%, and 61.76%, respectively. The performance of each model of facial recognition was superior to that of the best physician on all metrics.
CONCLUSIONS: Models of computer-assisted facial recognition can improve the rate of diagnosis of NS. The models based on VGG19-BN and VGG16-BN can play an important role in diagnosing NS in clinical practice.

Face Anti-Spoofing (FAS) seeks to protect face recognition systems from spoofing attacks, which is applied extensively in scenarios such as access control, electronic payment, and security surveillance systems. Face anti-spoofing requires the integration of local details and global semantic information. Existing CNN-based methods rely on small stride or image patch-based feature extraction structures, which struggle to capture spatial and cross-layer feature correlations effectively. Meanwhile, Transformer-based methods have limitations in extracting discriminative detailed features. To address the aforementioned issues, we introduce a multi-stage CNN-Transformer-based framework, which extracts local features through the convolutional layer and long-distance feature relationships via self-attention. Based on this, we proposed a cross-attention multi-stage feature fusion, employing semantically high-stage features to query task-relevant features in low-stage features for further cross-stage feature fusion. To enhance the discrimination of local features for subtle differences, we design pixel-wise material classification supervision and add a auxiliary branch in the intermediate layers of the model. Moreover, to address the limitations of a single acquisition environment and scarcity of acquisition devices in the existing Near-Infrared dataset, we create a large-scale Near-Infrared Face Anti-Spoofing dataset with 380k pictures of 1040 identities. The proposed method could achieve the state-of-the-art in OULU-NPU and our proposed Near-Infrared dataset at just 1.3GFlops and 3.2M parameter numbers, which demonstrate the effective of the proposed method.

Face recognition systems have been widely applied in various scenarios in people\'s daily lives. The recognition rate and speed of face recognition systems have always been the two key technical factors that researchers focus on. Many excellent recognition algorithms achieve high recognition rates or good recognition speeds. However, more research is needed to develop algorithms that can effectively balance these two indicators. In this study, we introduce an improved particle swarm optimization algorithm into a face recognition algorithm based on image feature compensation techniques. This allows the system to achieve high recognition rates while simultaneously enhancing the recognition efficiency, aiming to strike a balance between the two aspects. This approach provides a new perspective for the application of image feature compensation techniques in face recognition systems. It helps achieve a broader range of applications for face recognition technology by reducing the recognition speed as much as possible while maintaining a satisfactory recognition rate. Ultimately, this leads to an improved user experience.

BACKGROUND: Age prediction powered by artificial intelligence (AI) can be used as an objective technique to assess the cosmetic effect of rejuvenation surgery. Existing age-estimation models are trained on public datasets with the Caucasian race as the main reference, thus they are impractical for clinical application in Chinese patients.
METHODS: To develop and select an age-estimation model appropriate for Chinese patients receiving rejuvenation treatment, we obtained a face database of 10 529 images from 1821 patients from the author\'s hospital and selected two representative age-estimation algorithms for the model training. The prediction accuracies and the interpretability of calculation logic of these two facial age predictors were compared and analyzed.
RESULTS: The mean absolute error (MAE) of a traditional support vector machine-learning model was 10.185 years; the proportion of absolute error ≤6 years was 35.90% and 68.50% ≤12 years. The MAE of a deep-learning model based on the VGG-16 framework was 3.011 years; the proportion of absolute error ≤6 years was 90.20% and 100% ≤12 years. Compared with deep learning, traditional machine-learning models have clearer computational logic, which allows them to give clinicians more specific treatment recommendations.
CONCLUSIONS: Experimental results show that deep-learning exceeds traditional machine learning in the prediction of Chinese cosmetic patients\' age. Although traditional machine learning model has better interpretability than deep-learning model, deep-learning is more accurate for clinical quantitative evaluation. Knowing the decision-making logic behind the accurate prediction of deep-learning is crucial for deeper clinical application, and requires further exploration.

Facial approximation (FA) provides a promising means of generating the possible facial appearance of a deceased person. It facilitates exploration of the evolutionary forces driving anatomical changes in ancestral humans and can capture public attention. Despite the recent progress made toward improving the performance of FA methods, a limited understanding of detailed quantitative craniofacial relationships between facial bone and soft tissue morphology may hinder their accuracy, and hence subjective experience and artistic interpretation are required. In this study, we explored craniofacial relationships among human populations based upon average facial soft tissue thickness depths (FSTDs) and covariations between hard and soft tissues of the nose and mouth using geometric morphometrics. Furthermore, we proposed a computerized method to assign the learned craniofacial relationships to generate a probable facial appearance of Homo sapiens, reducing human intervention. A smaller resemblance comparison (an average Procrustes distance was 0.0258 and an average Euclidean distance was 1.79 mm) between approximated and actual faces and a greater recognition rate (91.67%) tested by a face pool indicated that average dense FSTDs contributed to raising the accuracy of approximated faces. Results of partial least squares (PLS) analysis showed that nasal and oral hard tissues have an effect on their soft tissues separately. However, relatively weaker RV correlations (<0.4) and greater approximation errors suggested that we need to be cautious about the accuracy of the approximated nose and mouth soft tissue shapes from bony structures. Overall, the proposed method can facilitate investigations of craniofacial relationships and potentially improve the reliability of the approximated faces for use in numerous applications in forensic science, archaeology, and anthropology.

The diagnosis of obstructive sleep apnea (OSA) relies on time-consuming and complicated procedures which are not always readily available and may delay diagnosis. With the widespread use of artificial intelligence, we presumed that the combination of simple clinical information and imaging recognition based on facial photos may be a useful tool to screen for OSA.
We recruited consecutive subjects suspected of OSA who had received sleep examination and photographing. Sixty-eight points from 2-dimensional facial photos were labelled by automated identification. An optimized model with facial features and basic clinical information was established and tenfold cross-validation was performed. Area under the receiver operating characteristic curve (AUC) indicated the model\'s performance using sleep monitoring as the reference standard.
A total of 653 subjects (77.2% males, 55.3% OSA) were analyzed. CATBOOST was the most suitable algorithm for OSA classification with a sensitivity, specificity, accuracy, and AUC of 0.75, 0.66, 0.71, and 0.76 respectively (P < 0.05), which was better than STOP-Bang questionnaire, NoSAS scores, and Epworth scale. Witnessed apnea by sleep partner was the most powerful variable, followed by body mass index, neck circumference, facial parameters, and hypertension. The model\'s performance became more robust with a sensitivity of 0.94, for patients with frequent supine sleep apnea.
The findings suggest that craniofacial features extracted from 2-dimensional frontal photos, especially in the mandibular segment, have the potential to become predictors of OSA in the Chinese population. Machine learning-derived automatic recognition may facilitate the self-help screening for OSA in a quick, radiation-free, and repeatable manner.

The abuse of deepfakes, a rising face swap technique, causes severe concerns about the authenticity of visual content and the dissemination of misinformation. To alleviate the threats imposed by deepfakes, a vast body of data-centric detectors has been deployed. However, the performance of these methods can be easily defected by degradations on deepfakes. To improve the performance of degradation deepfake detection, we creatively explore the recovery method in the feature space to preserve the artifacts for detection instead of directly in the image domain. In this paper, we propose a method, namely DF-UDetector, against degradation deepfakes by modeling the degraded images and transforming the extracted features to a high-quality level. To be specific, the whole model consists of three key components: an image feature extractor to capture image features, a feature transforming module to map the degradation features into a higher quality, and a discriminator to determine whether the feature map is of high quality enough. Extensive experiments on multiple video datasets show that our proposed model performs comparably or even better than state-of-the-art counterparts. Moreover, DF-UDetector outperforms by a small margin when detecting deepfakes in the wild.

The present study investigates the Chinese public\'s perception toward the widely adopted (and often accused of misuse) technology of face recognition. Through topic modeling and a social network analysis of 151,654 Weibo posts, we examine the \"content dimension\" and the \"actor dimension\" of civic discussions on facial recognition technology. Our results demonstrate that there is rising social concern and skepticism directed at the commercial use of this biodata-collected technology in China\'s cyberspace, despite the state\'s adoption, supervision, and regulation of facial recognition technology being broadly granted. Moreover, while our findings illustrate an extent of openness and equality within the public debates on facial recognition technology, they also show the Chinese government becoming an important \"interlocutor\" within the said debates, with discursive engagement from industry and academia largely marginalized. Drawing on the results, we suggest that further investigation into the formation of China\'s scientific public sphere should be located within the broader context of China\'s vision of a centrally planned digital economy.