ABSTRACT
Objective@#The purpose of this study is to report the activities of Disaster Medical Assistance Team and national emergency medical center in the fire at a women’s hospital on December 14, 2019, and to suggest an improvement plan for the special disastrous situation. @*Methods@#We reviewed the transfer records of national emergency medical center, medical records of regional emergency medical center, and records of each patient’s prognosis of the women’s hospital, retrospectively. Triage of casualties was conducted according to SALT (Sort, Assess, Lifesaving Interventions, Treatment/Transport) method. @*Results@#The fire was extinguished early and there was no victim with significant carbon monoxide intoxication. Among 228 casualties, there were 143 patients of the women’s hospital. Two patients were classified as immediate, 55 patients including pregnant women, newborns, and mothers were classified as delayed, and 171 casualties including newborns and mothers were classified as minimal. Among 66 newborns, 40 newborns were transferred to the regional Emergency Medical Center, and a second triage was conducted by doctors there. @*Conclusion@#Although there was no significant victim, physically and socially susceptible people such as pregnant women, newborns, and mothers were included in this accident. We recommend establishing a standard of disaster response for special population and improving our capability at a national level.
ABSTRACT
Medical image analyses have been widely used to differentiate normal and abnormal cases, detect lesions, segment organs, etc. Recently, owing to many breakthroughs in artificial intelligence techniques, medical image analyses based on deep learning have been actively studied. However, sufficient medical data are difficult to obtain, and data imbalance between classes hinder the improvement of deep learning performance. To resolve these issues, various studies have been performed, and data augmentation has been found to be a solution. In this review, we introduce data augmentation techniques, including image processing, such as rotation, shift, and intensity variation methods, generative adversarial network-based method, and image property mixing methods. Subsequently, we examine various deep learning studies based on data augmentation techniques. Finally, we discuss the necessity and future directions of data augmentation.
ABSTRACT
Medical image analyses have been widely used to differentiate normal and abnormal cases, detect lesions, segment organs, etc. Recently, owing to many breakthroughs in artificial intelligence techniques, medical image analyses based on deep learning have been actively studied. However, sufficient medical data are difficult to obtain, and data imbalance between classes hinder the improvement of deep learning performance. To resolve these issues, various studies have been performed, and data augmentation has been found to be a solution. In this review, we introduce data augmentation techniques, including image processing, such as rotation, shift, and intensity variation methods, generative adversarial network-based method, and image property mixing methods. Subsequently, we examine various deep learning studies based on data augmentation techniques. Finally, we discuss the necessity and future directions of data augmentation.