Deep learning algorithms for classification and detection of recurrent aphthous ulcerations using oral clinical photographic images.

Background/purpose: The application of artificial intelligence diagnosis based on deep learning in the medical field has been widely accepted. We aimed to evaluate convolutional neural networks (CNNs) for automated classification and detection of recurrent aphthous ulcerations (RAU), normal oral mucosa, and other common oral mucosal diseases in clinical oral photographs. Materials and methods: The study included 785 clinical oral photographs, which was divided into 251 images of RAU, 271 images of the normal oral mucosa, and 263 images of other common oral mucosal diseases. Four and three CNN models were used for the classification and detection tasks, respectively. 628 images were randomly selected as training data. In addition, 78 and 79 images were assigned as validating and testing data. Main outcome measures included precision, recall, F1, specificity, sensitivity and area under the receiver operating characteristics curve (AUC). Results: In the classification task, the Pretrained ResNet50 model had the best performance with a precision of 92.86%, a recall of 91.84%, an F1 score of 92.24%, a specificity of 96.41%, a sensitivity of 91.84% and an AUC of 98.95%. In the detection task, the Pretrained YOLOV5 model had the best performance with a precision of 98.70%, a recall of 79.51%, an F1 score of 88.07% and an AUC of Precision-Recall curve 90.89%. Conclusion: The Pretrained ResNet50 and the Pretrained YOLOV5 algorithms were shown to have superior performance and acceptable potential in the classification and detection of RAU lesions based on non-invasive oral images, which may prove useful in clinical practice.

Modulation of tropoelastin and fibrillin-1 by infrared radiation in human skin in vivo.

BACKGROUND: The heat produced by exposure to infrared radiation (IR) has been demonstrated to modulate the expression of tropoelastin and fibrillin-1, the two main components of elastic fibers in human skin in vivo. However, the effect of IR range of radiations on tropoelastin and fibrillin-1 expression has not been thoroughly investigated. METHODS: Eighteen volunteers were enrolled in this study involving three trials. Time-dependent, dose-dependent and cumulative effects of IR were investigated, respectively. Tropoelastin and fibrillin-1 expression was measured by immunohistochemical staining on skin biopsy samples from volunteers. In addition, we also measured tropoelastin mRNA expression by a real-time RT-polymerase chain reaction. RESULTS: A single dose of IR (2 minimal heating dose) induced a time-dependent increase in tropoelastin expression at the protein level. An inverse correlation was found between the alterations of tropoelastin and fibrillin-1. Furthermore, IR was found to increase tropoelastin expression in a dose-dependent manner at both the mRNA and the protein level. Repeated low doses of IR increased tropoelastin expression and decreased fibrillin-1 expression at the protein level in the dermis. Meanwhile, the number of both fibers along the dermal-epidermal junction was increased. CONCLUSION: IR can alter the expression of tropoelastin and fibrillin-1, which may result in abnormal elastic fiber formation.

[Study and investigation of mechanism of atrial fibrillation--(II). Atrial fibrillation animal model and data analysis method].

The first thorny problem in the study of atrial fibrillation (AF) is the establishment of reliable animal models. This paper presents how to create a canine sterile pericarditis model. A new data analysis method, Fast Fourier Transform is introduced. The data from canine sterile pericarditis model was analyzed using FFT. The results demonstrate that canine sterile pericarditis model is a reliable animal model for studying AF and that FFT is a rapid and effective method for analyzing AF data.

[Study and investigation of mechanism of atrial fibrillation--(I) High resolution cardiac mapping system].

This paper introduces the history and background of studies on the mechanism of atrial fibrillation. The necessary equipment to study atrial fibrillation--a high-resolution cardiac mapping system is presented. This equipment has provided a strong basis for the future study to acquire a precise understanding of the mechanism of atrial fibrillation.

[A novel method for automated detection of activation time].

In the study of cardiac activity, manual determination of local activation times is a time-consuming process that precludes the application of cardiac activity during a clinical procedure or an electrophysiologic experiment. Based on former bipolar algorithm and unipolar algorithm, this paper presents a novel method. Using unipolar electrograms and bipolar electrograms simultaneously, this method determines the activation times with good accuracy.