RESUMO
This research letter presents the co-design process for RG4Face, a mime therapy-based serious game that uses computer vision for human facial movement recognition and estimation to help health care professionals and patients in the facial rehabilitation process.
RESUMO
AIMS: Facial features were associated with increased risk of coronary artery disease (CAD). We developed and validated a deep learning algorithm for detecting CAD based on facial photos. METHODS AND RESULTS: We conducted a multicentre cross-sectional study of patients undergoing coronary angiography or computed tomography angiography at nine Chinese sites to train and validate a deep convolutional neural network for the detection of CAD (at least one ≥50% stenosis) from patient facial photos. Between July 2017 and March 2019, 5796 patients from eight sites were consecutively enrolled and randomly divided into training (90%, n = 5216) and validation (10%, n = 580) groups for algorithm development. Between April 2019 and July 2019, 1013 patients from nine sites were enrolled in test group for algorithm test. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated using radiologist diagnosis as the reference standard. Using an operating cut point with high sensitivity, the CAD detection algorithm had sensitivity of 0.80 and specificity of 0.54 in the test group; the AUC was 0.730 (95% confidence interval, 0.699-0.761). The AUC for the algorithm was higher than that for the Diamond-Forrester model (0.730 vs. 0.623, P < 0.001) and the CAD consortium clinical score (0.730 vs. 0.652, P < 0.001). CONCLUSION: Our results suggested that a deep learning algorithm based on facial photos can assist in CAD detection in this Chinese cohort. This technique may hold promise for pre-test CAD probability assessment in outpatient clinics or CAD screening in community. Further studies to develop a clinical available tool are warranted.
Assuntos
Doença da Artéria Coronariana , Estenose Coronária , Aprendizado Profundo , Angiografia Coronária , Doença da Artéria Coronariana/diagnóstico por imagem , Estenose Coronária/diagnóstico por imagem , Estudos Transversais , Estudos de Viabilidade , Humanos , Valor Preditivo dos TestesRESUMO
Previous research shows that larger interference is observed in contexts associated with a high proportion of congruent trials than in those associated with a low proportion of congruent trials. Given that one of the most relevant contexts for human beings is social context, researchers have recently explored the possibility that social stimuli could also work as contextual cues for the allocation of attentional control. In fact, it has been shown that individuals use social categories (i.e., men and women) as cues to allocate attentional control. In this work, we go further by showing that individual faces (instead of the social categories they belong to) associated with a high proportion of congruent trials can also lead to larger interference effects compared to individual faces predicting a relatively low proportion of congruent trials. Furthermore, we show that faces associated with a high proportion of congruent trials are more positively evaluated than faces associated with a high proportion of incongruent trials. These results demonstrate that unique human faces are potential contextual cues than can be employed to apply cognitive control when performing an automatic task.
Assuntos
Atenção , Sinais (Psicologia) , Expressão Facial , Adulto , Face , Feminino , Humanos , Percepção Social , Adulto JovemRESUMO
Native human populations from South America display high levels of craniofacial variation encompassing gracile and robust skulls. Nevertheless, the processes of bone modeling by which morphological variation among populations were attained, remain poorly understood. Here we analyze the relationship between patterns of bone formation and resorption and morphometric variation in the upper face of adults belonging to farmers and hunter-gatherers from northwestern and south Argentina. Our analyses reveal a common pattern of bone modeling of the malar bone characterized by the presence of formation areas. Thus, the larger size and greater development of malar bone exhibited by hunter-gatherers would be linked to a greater magnitude of bone formation activity. Conversely, the glabella and the superciliary arch presented both formation and resorption areas with a variable distribution among individuals. In the extreme corresponding to more robust morphologies, the great development of the glabella is related to the presence of large formation fields, both in the upper region and toward the frontonasal suture. The less robust morphologies show resorption fields at the upper margin of the glabella, which would contribute to the weaker development of this region. The superciliary arch showed a complex relationship between its morphometric and histological variation; the individuals located at both extremes of the shape space presented large resorption areas located on its upper margin. Overall, our results show the existence of intraspecific variation in the patterns of bone modeling in the human upper face.