Protection from Particulate Matter and Infection: Thermal Imaging and Deep Learning-based Fit-checking of Quasi-drug Masks

Abstract Background Particulate matter and infectious diseases confer serious health risks, particularly in healthcare workers who experience occupational exposure risk. Masks can provide effective protection against such risks, although their efficacy is only as good as their fit. Therefore, a fit test is performed to ensure correct fit of the mask. In this study, we aimed to develop an artificial intelligence system to quickly and easily determine correct mask-wearing in real time using thermal videos that ascertained temperature changes caused by air trapped inside the mask. Methods We investigated the effectiveness of deep learning-based identification of the correct way to wear a mask based on thermal videos with five types of masks, which were approved as quasi-drugs by the Korean Ministry of Food and Drug Safety, and four ways of wearing these masks including one proper way and three improper ways. The same conditions were repeated five times, with a total of 100 videos per participant, and 5000 videos were obtained in this study. We used a 3D Convolutional Neural Network (3DCNN) and Convolutional Long Short-Term Memory (ConvLSTM) for data analysis. Both models performed binary and multi-classification to categorize mask-wearing. Results 3DCNN performed better than ConvLSTM by achieving higher scores in both binary and multi-classification tasks. The AUROC value for multi-classification using 3DCNN was the highest at 0.986 whereas the remaining parameters of accuracy, precision, recall, specificity, and F1-score were all better with the binary classification. All mask types showed AUROC values > 0.9, with KF-AD being the best classified. Conclusion This novel approach uses thermal imaging and deep learning techniques to effectively monitor correct mask-wearing and could be useful in high-risk environments, including in healthcare settings. This method can be applied to various mask types, which enables easy generalizability and advantages in public and occupational health and healthcare. Furthermore, integrating this novel technology into other screening methods can improve the safety and well-being of people, including healthcare workers, in various situations.