Attempt to extract features and classify subjective poor physical conditions in facial images using deep metric learning.

With the spread of COVID-19, the need for remote detection of physical conditions is increasing, for example, there are several situations wherein the body temperature has to be measured remotely to detect febrile individuals. Aiming to remotely detect physical conditions, the study attempted to investigate anomaly detection based on facial color and skin temperature, which are indicators related to hemodynamics. Triplet loss was used to extract features related to subjective health feelings from facial images to evaluate whether there is a relationship between subjective health feelings and facial images. A classification of subjective health feelings related to poor physical conditions based on these features was also attempted. To obtain the data, an experiment was conducted for approximately 1 year to measure facial visual and thermal images, and subjective feelings related to physical conditions. Anomaly levels were defined based on subjective health feelings. Anomaly detection models were constructed by classifying anomaly and normal data based on subjective health feelings. Facial visible and thermal images were applied to the trained model to quantitatively evaluate the accuracy of the classification of anomaly conditions related to subjective health. At higher levels of anomaly, a combination of facial visible and thermal images resulted in the classification of subjective health feelings with moderate accuracy. Further, the results suggest that the eyes and sides of the nose may indicate subjective health feelings.

An online feedback system for laparoscopic training during the COVID-19 pandemic: evaluation from the trainer perspective.

Objective: A system to provide feedback for laparoscopic training using an online conferencing system during the COVID-19 pandemic was developed. The purpose of this study is to evaluate this system from the trainer perspective. Design: A procedural feedback system using an online conferencing system was devised. Setting: Surgical training was observed using an online conferencing system (Zoom). Feedback was provided while viewing suture videos which are, as a feature of this system, pre-recorded. Feedback was then recorded. Trainer comments were then converted into text, summarized as feedback items, and sorted by suture phase which facilitates reflection. Trainers completed a questionnaire concerning the usability of the online feedback session. Results: Eleven trainers were selected. Physicians had an average experience of 21.9 ± 5.9 years (mean ± standard deviation). The total number of feedback items obtained by classifying each phase was 32. Based on questionnaire results, 91% of trainers were accustomed to the use of Zoom, and 100% felt that online procedural education was useful. In questions regarding system effectiveness, more than 70% of trainers answered positively to all questions, and in questions about efficiency, more than 70% of trainers answered positively. Only 55% of the trainers felt that this system was easy to use, but 91% were satisfied as trainers. Conclusions: The results of the questionnaire suggest that this system has high usability for training. This online system could be a useful tool for providing feedback in situations where face-to-face education is difficult.

An attempt to construct the individual model of daily facial skin temperature using variational autoencoder.

Facial skin temperature (FST) has also gained prominence as an indicator for detecting anomalies such as fever due to the COVID-19. When FST is used for engineering applications, it is enough to be able to recognize normal. We are also focusing on research to detect some anomaly in FST. In a previous study, it was confirmed that abnormal and normal conditions could be separated based on FST by using a variational autoencoder (VAE), a deep generative model. However, the simulations so far have been a far cry from reality. In this study, normal FST with a diurnal variation component was defined as a normal state, and a model of normal FST in daily life was individually reconstructed using VAE. Using the constructed model, the anomaly detection performance was evaluated by applying the Hotelling theory. As a result, the area under the curve (AUC) value in ROC analysis was confirmed to be 0.89 to 1.00 in two subjects.