The role of facial cues in signalling cooperativeness is limited and nuanced.

Humans display a remarkable tendency to cooperate with strangers; however, identifying prospective cooperation partners accurately before entering any new relationship is essential to mitigate the risk of being exploited. Visual appearance, as inferrable, for example, from facial images on job portals and dating sites, may serve as a potential signal of cooperativeness. This experimental study examines whether static images enable the correct detection of an individual's propensity to cooperate. Participants first played the Prisoner's Dilemma (PD) game, a standard cooperation task. Subsequently, they were asked to predict the cooperativeness of participants from a prior PD study relying solely on their static facial photographs. While our main results indicate only marginal accuracy improvements over random guessing, a more detailed analysis reveals that participants were more successful at identifying cooperative tendencies similar to their own. Despite no detectable main effect in our primary treatment variations (time pressure versus time delay), participants exhibited increased accuracy in identifying male cooperators under time pressure. These findings point towards a limited yet nuanced role of static facial images in predicting cooperativeness, advancing our understanding of non-behavioral cues in cooperative interactions.

Prediagnosis recognition of acute ischemic stroke by artificial intelligence from facial images.

Stroke is a major threat to life and health in modern society, especially in the aging population. Stroke may cause sudden death or severe sequela-like hemiplegia. Although computed tomography (CT) and magnetic resonance imaging (MRI) are standard diagnosis methods, and artificial intelligence models have been built based on these images, shortage in medical resources and the time and cost of CT/MRI imaging hamper fast detection, thus increasing the severity of stroke. Here, we developed a convolutional neural network model by integrating four networks, Xception, ResNet50, VGG19, and EfficientNetb1, to recognize stroke based on 2D facial images with a cross-validation area under curve (AUC) of 0.91 within the training set of 185 acute ischemic stroke patients and 551 age- and sex-matched controls, and AUC of 0.82 in an independent data set regardless of age and sex. The model computed stroke probability was quantitatively associated with facial features, various clinical parameters of blood clotting indicators and leukocyte counts, and, more importantly, stroke incidence in the near future. Our real-time facial image artificial intelligence model can be used to rapidly screen and prediagnose stroke before CT scanning, thus meeting the urgent need in emergency clinics, potentially translatable to routine monitoring.

Automatic Measurement and Comparison of Normal Eyelid Contour by Age and Gender Using Image-Based Deep Learning.

Purpose: This study aimed to propose a fully automatic eyelid measurement system and compare the contours of both the upper and lower eyelids of normal individuals according to age and gender. Design: Prospective study. Participants: Five hundred and forty healthy Chinese aged 0 to 79 years in a tertiary hospital were included. Methods: Facial images in the primary gazing position were used to train and test the proposed automatic system for eye recognition and eye segmentation. According to the 10-millimeter diameter circular marker, measurements were transformed from pixel sizes into factual distances. Main Outcome Measures: Midpupil lid distances (MPLDs) every 15° of all participants were automatically measured in both genders (30 males and 30 females in each age group) by the proposed deep learning (DL)-based system. Intraclass correlation coefficients (ICCs) were performed to assess the agreement between the automatic and manual margin reflex distances (MRDs). The eyelid contour, eyelid asymmetry, and palpebral fissure obliquity were analyzed using MPLD, temporal-versus-nasal MPLD ratio, and the angle between the inner and outer canthi, respectively. Results: The measurement of MRDs by the automatic system excellently agreed with that of the expert, with ICCs ranging from 0.863 to 0.886. As the age of the participants increased, the values of MPLDs reached a peak in those in their 20s or 30s and then gradually decreased at all angles. The temporal sector showed greater changes in MPLDs than the nasal sector, and the changes were more significant in females than in males. The maximum value of palpebral fissure obliquity appeared before 10 years in both genders and remained relatively stable after the 20s (P > 0.05). Conclusions: The proposed DL-based eyelid analysis system allowed automatic, accurate, and comprehensive measurement of the eyelid contour. The refinement of eyelid shape quantification could be beneficial for future objective assessment preocular and postocular plastic surgery. Financial Disclosures: The authors have no proprietary or commercial interest in any materials discussed in this article.

Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization.

The early diagnosis of autism spectrum disorder (ASD) encounters challenges stemming from domain variations in facial image datasets. This study investigates the potential of active learning, particularly uncertainty-based sampling, for domain adaptation in early ASD diagnosis. Our focus is on improving model performance across diverse data sources. Utilizing the Kaggle ASD and YTUIA datasets, we meticulously analyze domain variations and assess transfer learning and active learning methodologies. Two state-of-the-art convolutional neural networks, Xception and ResNet50V2, pretrained on distinct datasets, demonstrate noteworthy accuracies of 95% on Kaggle ASD and 96% on YTUIA, respectively. However, combining datasets results in a modest decline in average accuracy, underscoring the necessity for effective domain adaptation techniques. We employ uncertainty-based active learning to address this, which significantly mitigates the accuracy drop. Xception and ResNet50V2 achieve 80% and 79% accuracy when pretrained on Kaggle ASD and applying active learning on YTUIA, respectively. Our findings highlight the efficacy of uncertainty-based active learning for domain adaptation, showcasing its potential to enhance accuracy and reduce annotation needs in early ASD diagnosis. This study contributes to the growing body of literature on ASD diagnosis methodologies. Future research should delve deeper into refining active learning strategies, ultimately paving the way for more robust and efficient ASD detection tools across diverse datasets.

netMUG: a novel network-guided multi-view clustering workflow for dissecting genetic and facial heterogeneity.

Introduction: Multi-view data offer advantages over single-view data for characterizing individuals, which is crucial in precision medicine toward personalized prevention, diagnosis, or treatment follow-up. Methods: Here, we develop a network-guided multi-view clustering framework named netMUG to identify actionable subgroups of individuals. This pipeline first adopts sparse multiple canonical correlation analysis to select multi-view features possibly informed by extraneous data, which are then used to construct individual-specific networks (ISNs). Finally, the individual subtypes are automatically derived by hierarchical clustering on these network representations. Results: We applied netMUG to a dataset containing genomic data and facial images to obtain BMI-informed multi-view strata and showed how it could be used for a refined obesity characterization. Benchmark analysis of netMUG on synthetic data with known strata of individuals indicated its superior performance compared with both baseline and benchmark methods for multi-view clustering. The clustering derived from netMUG achieved an adjusted Rand index of 1 with respect to the synthesized true labels. In addition, the real-data analysis revealed subgroups strongly linked to BMI and genetic and facial determinants of these subgroups. Discussion: netMUG provides a powerful strategy, exploiting individual-specific networks to identify meaningful and actionable strata. Moreover, the implementation is easy to generalize to accommodate heterogeneous data sources or highlight data structures.

Deep learning-based image analysis of eyelid morphology in thyroid-associated ophthalmopathy.

Background: We aimed to propose a deep learning-based approach to automatically measure eyelid morphology in patients with thyroid-associated ophthalmopathy (TAO). Methods: This prospective study consecutively included 74 eyes of patients with TAO and 74 eyes of healthy volunteers visiting the ophthalmology department in a tertiary hospital. Patients diagnosed as TAO and healthy volunteers who were age- and gender-matched met the eligibility criteria for recruitment. Facial images were taken under the same light conditions. Comprehensive eyelid morphological parameters, such as palpebral fissure (PF) length, margin reflex distance (MRD), eyelid retraction distance, eyelid length, scleral area, and mid-pupil lid distance (MPLD), were automatically calculated using our deep learning-based analysis system. MRD1 and 2 were manually measured. Bland-Altman plots and intraclass correlation coefficients (ICCs) were performed to assess the agreement between automatic and manual measurements of MRDs. The asymmetry of the eyelid contour was analyzed using the temporal: nasal ratio of the MPLD. All eyelid features were compared between TAO eyes and control eyes using the independent samples t-test. Results: A strong agreement between automatic and manual measurement was indicated. Biases of MRDs in TAO eyes and control eyes ranged from -0.01 mm [95% limits of agreement (LoA): -0.64 to 0.63 mm] to 0.09 mm (LoA: -0.46 to 0.63 mm). ICCs ranged from 0.932 to 0.980 (P<0.001). Eyelid features were significantly different in TAO eyes and control eyes, including MRD1 (4.82±1.59 vs. 2.99±0.81 mm; P<0.001), MRD2 (5.89±1.16 vs. 5.47±0.73 mm; P=0.009), upper eyelid length (UEL) (27.73±4.49 vs. 25.42±4.35 mm; P=0.002), lower eyelid length (LEL) (31.51±4.59 vs. 26.34±4.72 mm; P<0.001), and total scleral area (SATOTAL) (96.14±34.38 vs. 56.91±14.97 mm2; P<0.001). The MPLDs at all angles showed significant differences in the 2 groups of eyes (P=0.008 at temporal 180°; P<0.001 at other angles). The greatest temporal-nasal asymmetry appeared at 75° apart from the midline in TAO eyes. Conclusions: Our proposed system allowed automatic, comprehensive, and objective measurement of eyelid morphology by only using facial images, which has potential application prospects in TAO. Future work with a large sample of patients that contains different TAO subsets is warranted.

Research progress and application of artificial intelligence in thyroid associated ophthalmopathy.

Thyroid-associated ophthalmopathy (TAO) is a complicated orbitopathy related to dysthyroid, which severely destroys the facial appearance and life quality without medical interference. The diagnosis and management of thyroid-associated ophthalmopathy are extremely intricate, as the number of professional ophthalmologists is limited and inadequate compared with the number of patients. Nowadays, medical applications based on artificial intelligence (AI) algorithms have been developed, which have proved effective in screening many chronic eye diseases. The advanced characteristics of automated artificial intelligence devices, such as rapidity, portability, and multi-platform compatibility, have led to significant progress in the early diagnosis and elaborate evaluation of these diseases in clinic. This study aimed to provide an overview of recent artificial intelligence applications in clinical diagnosis, activity and severity grading, and prediction of therapeutic outcomes in thyroid-associated ophthalmopathy. It also discussed the current challenges and future prospects of the development of artificial intelligence applications in treating thyroid-associated ophthalmopathy.

Parents' perspectives on the use of children's facial images for research and diagnosis: a survey.

Computer-aided facial diagnostic tools are valuable emerging technologies for the early detection and initial diagnosis of congenital disorders. These tools require large datasets of facial photographs, especially of infants and children, to identify these disorders and improve classification accuracies. Researchers need to balance this need for larger datasets with patients' privacy rights, needs and preferences. This study aimed to investigate parents' views regarding the collection, storage, use and publication of their children's facial images for research and diagnostic purposes. A total of 151 parents of children with and without congenital disorders completed an online survey evaluating their views on the collection, storage, use and publication of children's facial images for research and diagnosis. Overall, 72.5% of parents would allow researchers to take facial photographs of their children, preferring the images to be stored in a secure database that is not available to the public. Parents of children with congenital disorders were more accepting of researchers taking facial photographs of their children, compared to parents of children without these conditions. Half of the respondents would allow facial photographs of their children to be published in academic journals, without their eyes covered, and this acceptance increased as the proportion of the child's face covered increased. Parents also indicated specific requirements to allow the use of these images in other similar research studies which need to be taken into consideration when planning studies that involve facial analysis research.

An Intelligent Diagnostic System for Thyroid-Associated Ophthalmopathy Based on Facial Images.

Background: Thyroid-associated ophthalmopathy (TAO) is one of the most common orbital diseases that seriously threatens visual function and significantly affects patients' appearances, rendering them unable to work. This study established an intelligent diagnostic system for TAO based on facial images. Methods: Patient images and data were obtained from medical records of patients with TAO who visited Shanghai Changzheng Hospital from 2013 to 2018. Eyelid retraction, ocular dyskinesia, conjunctival congestion, and other signs were noted on the images. Patients were classified according to the types, stages, and grades of TAO based on the diagnostic criteria. The diagnostic system consisted of multiple task-specific models. Results: The intelligent diagnostic system accurately diagnosed TAO in three stages. The built-in models pre-processed the facial images and diagnosed multiple TAO signs, with average areas under the receiver operating characteristic curves exceeding 0.85 (F1 score >0.80). Conclusion: The intelligent diagnostic system introduced in this study accurately identified several common signs of TAO.

Knowledge-based tensor subspace analysis system for kinship verification.

Most existing automatic kinship verification methods focus on learning the optimal distance metrics between family members. However, learning facial features and kinship features simultaneously may cause the proposed models to be too weak. In this work, we explore the possibility of bridging this gap by developing knowledge-based tensor models based on pre-trained multi-view models. We propose an effective knowledge-based tensor similarity extraction framework for automatic facial kinship verification using four pre-trained networks (i.e., VGG-Face, VGG-F, VGG-M, and VGG-S). Therefore, knowledge-based deep face and general features (such as identity, age, gender, ethnicity, expression, lighting, pose, contour, edges, corners, shape, etc.) were successfully fused by our tensor design to understand the kinship cue. Multiple effective representations are learned for kinship verification statements (children and parents) using a margin maximization learning scheme based on Tensor Cross-view Quadratic Exponential Discriminant Analysis. Through the exponential learning process, the large gap between distributions of the same family can be reduced to the maximum, while the small gap between distributions of different families is simultaneously increased. The WCCN metric successfully reduces the intra-class variability problem caused by deep features. The explanation of black-box models and the problems of ubiquitous face recognition are considered in our system. The extensive experiments on four challenging datasets show that our system performs very well compared to state-of-the-art approaches.

Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application.

Autism spectrum disorder (ASD) is a developmental disability that can cause significant social, communication, and behavioral challenges. Early intervention for children with ASD can help to improve their intellectual ability and reduces autistic symptoms. Multiple clinical researches have suggested that facial phenotypic differences exist between ASD children and typically developing (TD) children. In this research, we propose a practical ASD screening solution using facial images through applying VGG16 transfer learning-based deep learning to a unique ASD dataset of clinically diagnosed children that we collected. Our model produced a 95% classification accuracy and 0.95 F1-score. The only other reported study using facial images to detect ASD was based on the Kaggle ASD Facial Image Dataset, which is an internet search-produced, low-quality, and low-fidelity dataset. Our results support the clinical findings of facial feature differences between children with ASD and TD children. The high F1-score achieved indicates that it is viable to use deep learning models to screen children with ASD. We concluded that the racial and ethnic-related factors in deep-learning based ASD screening with facial images are critical to solution viability and accuracy.

Improved Transfer-Learning-Based Facial Recognition Framework to Detect Autistic Children at an Early Stage.

Autism spectrum disorder (ASD) is a complex neuro-developmental disorder that affects social skills, language, speech and communication. Early detection of ASD individuals, especially children, could help to devise and strategize right therapeutic plan at right time. Human faces encode important markers that can be used to identify ASD by analyzing facial features, eye contact, and so on. In this work, an improved transfer-learning-based autism face recognition framework is proposed to identify kids with ASD in the early stages more precisely. Therefore, we have collected face images of children with ASD from the Kaggle data repository, and various machine learning and deep learning classifiers and other transfer-learning-based pre-trained models were applied. We observed that our improved MobileNet-V1 model demonstrates the best accuracy of 90.67% and the lowest 9.33% value of both fall-out and miss rate compared to the other classifiers and pre-trained models. Furthermore, this classifier is used to identify different ASD groups investigating only autism image data using k-means clustering technique. Thus, the improved MobileNet-V1 model showed the highest accuracy (92.10%) for k = 2 autism sub-types. We hope this model will be useful for physicians to detect autistic children more explicitly at the early stage.

The Mirror of Mind: Visualizing Mental Representations of Self Through Reverse Correlation.

The reverse correlation (RC) method has been widely used, because it allows visualization of mental representations without a priori assumptions about relevant dimensions. We employed the RC method to visualize mental representations of self and examined their relationships with traits related to self-image. For this purpose, 110 participants (70 women) performed a two-image forced choice RC task to generate a classification image of self (self-CI). Participants perceived their self-CIs as bearing a stronger resemblance to themselves than did CIs of others (filler-CIs). Valence ratings of participants who performed the RC task (RC sample) and of 30 independent raters both showed positive correlations with self-esteem, explicit self-evaluation, and extraversion. Moreover, valence ratings of independent raters were negatively correlated with social anxiety symptoms. On the other hand, valence ratings of the RC sample and independent raters were not correlated with depression symptoms, trait anxiety, or social desirability. The results imply that mental representations of self can be properly visualized by using the RC method.

Effect of frontal facial type and sex on preferred chin projection.

OBJECTIVE: To investigate the effects of frontal facial type (FFT) and sex on preferred chin projection (CP) in three-dimensional (3D) facial images. METHODS: Six 3D facial images were acquired using a 3D facial scanner (euryprosopic [Eury-FFT], mesoprosopic [Meso-FFT], and leptoprosopic [Lepto-FFT] for each sex). After normal CP in each 3D facial image was set to 10° of the facial profile angle (glabella-subnasale-pogonion), CPs were morphed by gradations of 2° from normal (moderately protrusive [6°], slightly protrusive [8°], slightly retrusive [12°], and moderately retrusive [14°]). Seventy-five dental students (48 men and 27 women) were asked to rate the CPs (6°, 8°, 10°, 12°, and 14°) from the most to least preferred in each 3D image. Statistical analyses included the Kolmogorov-Smirnov test, Kruskal-Wallis test, and Bonferroni correction. RESULTS: No significant difference was observed in the distribution of preferred CP in the same FFT between male and female evaluators. In Meso-FFT, the normal CP was the most preferred without any sex difference. However, in Eury-FFT, the slightly protrusive CP was favored in male 3D images, but the normal CP was preferred in female 3D images. In Lepto-FFT, the normal CP was favored in male 3D images, whereas the slightly retrusive CP was favored in female 3D images. The mean preferred CP angle differed significantly according to FFT (Eury-FFT: male, 8.7°, female, 9.9°; Meso-FFT: male, 9.8°, female, 10.7°; Lepto-FFT: male, 10.8°, female, 11.4°; p < 0.001). CONCLUSIONS: Our findings might serve as guidelines for setting the preferred CP according to FFT and sex.

Effect of frontal facial type and sex on preferred chin projection / 대한치과교정학회지

OBJECTIVE: To investigate the effects of frontal facial type (FFT) and sex on preferred chin projection (CP) in three-dimensional (3D) facial images. METHODS: Six 3D facial images were acquired using a 3D facial scanner (euryprosopic [Eury-FFT], mesoprosopic [Meso-FFT], and leptoprosopic [Lepto-FFT] for each sex). After normal CP in each 3D facial image was set to 10° of the facial profile angle (glabella–subnasale-pogonion), CPs were morphed by gradations of 2° from normal (moderately protrusive [6°], slightly protrusive [8°], slightly retrusive [12°], and moderately retrusive [14°]). Seventy-five dental students (48 men and 27 women) were asked to rate the CPs (6°, 8°, 10°, 12°, and 14°) from the most to least preferred in each 3D image. Statistical analyses included the Kolmogorov-Smirnov test, Kruskal-Wallis test, and Bonferroni correction. RESULTS: No significant difference was observed in the distribution of preferred CP in the same FFT between male and female evaluators. In Meso-FFT, the normal CP was the most preferred without any sex difference. However, in Eury-FFT, the slightly protrusive CP was favored in male 3D images, but the normal CP was preferred in female 3D images. In Lepto-FFT, the normal CP was favored in male 3D images, whereas the slightly retrusive CP was favored in female 3D images. The mean preferred CP angle differed significantly according to FFT (Eury-FFT: male, 8.7°, female, 9.9°; Meso-FFT: male, 9.8°, female, 10.7°; Lepto-FFT: male, 10.8°, female, 11.4°; p < 0.001). CONCLUSIONS: Our findings might serve as guidelines for setting the preferred CP according to FFT and sex.

Pgu-Face: A dataset of partially covered facial images.

In this article we introduce a human face image dataset. Images were taken in close to real-world conditions using several cameras, often mobile phone׳s cameras. The dataset contains 224 subjects imaged under four different figures (a nearly clean-shaven countenance, a nearly clean-shaven countenance with sunglasses, an unshaven or stubble face countenance, an unshaven or stubble face countenance with sunglasses) in up to two recording sessions. Existence of partially covered face images in this dataset could reveal the robustness and efficiency of several facial image processing algorithms. In this work we present the dataset and explain the recording method.