ABSTRACT
BACKGROUND: The gastroscopic examination is a preferred method for the detection of upper gastrointestinal lesions. However, gastroscopic examination has high requirements for doctors, especially for the strict position and quantity of the archived images. These requirements are challenging for the education and training of junior doctors. OBJECTIVE: The purpose of this study is to use deep learning to develop automatic position recognition technology for gastroscopic examination. METHODS: A total of 17182 gastroscopic images in eight anatomical position categories are collected. Convolutional neural network model MogaNet is used to identify all the anatomical positions of the stomach for gastroscopic examination The performance of four models is evaluated by sensitivity, precision, and F1 score. RESULTS: The average sensitivity of the method proposed is 0.963, which is 0.074, 0.066 and 0.065 higher than ResNet, GoogleNet and SqueezeNet, respectively. The average precision of the method proposed is 0.964, which is 0.072, 0.067 and 0.068 higher than ResNet, GoogleNet, and SqueezeNet, respectively. And the average F1-Score of the method proposed is 0.964, which is 0.074, 0.067 and 0.067 higher than ResNet, GoogleNet, and SqueezeNet, respectively. The results of the t-test show that the method proposed is significantly different from other methods (p< 0.05). CONCLUSION: The method proposed exhibits the best performance for anatomical positions recognition. And the method proposed can help junior doctors meet the requirements of completeness of gastroscopic examination and the number and position of archived images quickly.
Subject(s)
Deep Learning , Gastroscopy , Humans , Gastroscopy/methods , Gastroscopy/education , Stomach/anatomy & histology , Stomach/diagnostic imaging , Neural Networks, ComputerABSTRACT
The development of modern technologies and the use of social networks create an environment for the exchange of information, interactive communication, learning, and optimization of various processes. The study describes the results of the effectiveness of using various social media tools to increase the level of physical activity in people of different ages (12-35 years old). Effective tools for increasing the level of physical activity that can be used on social media have been considered. A survey created in Google forms was conducted to select research participants and group them; the pedagogical experiment is the introduction of social media tools to encourage users to do sports. The experiment involved 148 people of different age groups: adolescents, students, adults. After the experiment with the experimental group, there were 59.20% of participants with an average level of physical activity and 22.37% of participants with a high level of physical activity; in the control group, 31.58% of participants had a low level of physical activity, 48.70%-average, 10.53%-high. Most participants of all ages (88.16%) refrained from posting videos of their achievements on social media, while nine participants (5 pupils and 4 students) posted their achievements in the form of short video exercises or screenshots, and reports of exercises in mobile applications in their groups. The research results are applicable to various social groups and can be used to create private groups on social media to encourage physical activity. The data obtained can be used for further development of specialized training programs using digital technology and social networks.
ABSTRACT
Purpose: To evaluate the long-term effect of vibration therapy with holistic and local intervention in treating muscle fatigue in elite athletes during their intensive training season. Methods: Study participants included five male athletes from a provincial Greco-Roman wrestling team who were qualified for the finals of China's national games. During the study, conventional therapeutic intervention was applied during the initial three weeks of the study, and an instrument intervention was adopted in the following three weeks. A surface electromyography (sEMG) was used to measure muscle fatigue of latissimus dorsi, both before and after each intervention session. Specifically, the pre-intervention measurement was conducted right after the daily training completion; and the post-intervention measurement occurred in the following morning. The data analyses were to compare the differences in the muscle fatigue data between the two modes of interventions, conventional and instrument therapy. Results: The conventional intervention showed no significant difference in the sEMG indexes before and after the intervention; while for the instrument intervention, the pre- and post- intervention sEMG indexes differed significantly (p < 0.05). Conclusion: The long-term effects of instrument vibration therapy on muscle fatigue recovery were studied based on observational data from elite athletes. The results indicate that the vibration therapy with holistic and local consideration demonstrated an effective reduction of muscle fatigue and/or fatigue accumulation in elite athletes during their intensive training season.