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.

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.

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.

PURPOSE: This study was carried out to describe the process and evaluation of a critical thinking class for new community health practitioners. METHODS: The case study design was used to develop and evaluate a critical thinking class for 46 participants in the community health practitioners training program. The class was held two hours a week for 8 weeks. Critical thinking disposition was tested before and after the class and critical skill was graded according to the final test score. Data analysis was performed using descriptive statistics and paired t-tests using SPSS WIN 20.0. RESULTS: Clinical critical thinking competences were identified through the literature review. The case situations with questions guiding the problem-solving process were developed and used for group discussion. Critical thinking disposition of participants was determined to have increased slightly after having taken the class. 17.4% of the participants had a competency level high enough to solve a problem and half of them stayed at the level of understanding of critical thinking. Compared with the class's satisfaction with the relevance to their jobs, the satisfaction with the learning method and instructor was high. CONCLUSION: The findings of this research will serve as the basis for developing critical thinking classes for community health nurses in order to improve their critical thinking competence.
Education ; Learning ; Mental Competency ; Nurses, Community Health ; Primary Health Care ; Problem-Based Learning ; Statistics as Topic ; Thinking*

We investigated the effect of lysophosphatidic acid (LPA) in experimental acetaminophen (APAP)-induced acute liver injury. LPA administration significantly reduced APAP-challenged acute liver injury, showing attenuated liver damage, liver cell death and aspartate aminotransferase and alanine aminotransferase levels. APAP overdose-induced mortality was also significantly decreased by LPA administration. Regarding the mechanism involved in LPA-induced protection against acute liver injury, LPA administration significantly increased the glutathione level, which was markedly decreased in APAP challenge-induced acute liver injury. LPA administration also strongly blocked the APAP challenge-elicited phosphorylation of JNK, ERK and GSK3β, which are involved in the pathogenesis of acute liver injury. Furthermore, LPA administration decreased the production of TNF-α and IL-1β in an experimental drug-induced liver injury animal model. Mouse primary hepatocytes express LPA₁(,)₃–₆, and injection of the LPA receptor antagonist KI16425 (an LPA₁(,)₃-selective inhibitor) or H2L 5765834 (an LPA₁(,)₃(,)₅-selective inhibitor) did not reverse the LPA-induced protective effects against acute liver injury. The therapeutic administration of LPA also blocked APAP-induced liver damage, leading to an increased survival rate. Collectively, these results indicate that the well-known bioactive lipid LPA can block the pathogenesis of APAP-induced acute liver injury by increasing the glutathione level but decreasing inflammatory cytokines in an LPA₁(,)₃(,)₅-independent manner. Our results suggest that LPA might be an important therapeutic agent for drug-induced liver injury.

PURPOSE: Tension pneumothorax is a life threatening condition. As an emergency treatment, needle thoracostomy with 50mm angiocatheter at the second intercostal space on the mid-clavicular line (2nd ICS/MCL) is recommended in the current guidelines. However, another site has been suggested in some studies. The purpose of this study was to determine whether the current procedure should be changed, by comparing the chest wall thicknesses (CWT) at the 2(nd) ICS/MCL and the 5(th) ICS/AAL (anterior axillary line) of injured patients. METHODS: A retrospective observational study was performed in an emergency center between May 2009 and December 2011. Medical records and computed tomography (CT) images of 140 included patients were reviewed. CWT at the 2(nd) ICS/MCL was compared with the 5(th) ICS/AAL. Moreover, the relationship between BMI (body mass index) and CWT was evaluated. RESULTS: CWT of the 2(nd) ICS/MCL was 31.7±8.5 mm on the right and 31.6±8.8 mm on the left, with no differences (p=0.42). CWT of the 5(th) ICS/AAL was 28.1±8.5 mm on the right and 27.8±7.7 mm on the left, also with no differences (p=0.30). CWT of the 2(nd) ICS/MCL was thicker than that of the 5(th) ICS/AAL (p<0.001). Nevertheless, CWT of all sites were not thicker than 50 mm (p<0.001). BMI was positively correlated with CWT. CONCLUSION: There was insufficient amount of evidences shown in this study to change the current guidelines of needle thoracostomy. However, in case of obvious patients, a long needle and 5(th) ICS/AAL site should be considered for needle thoracostomy, because CWT tended to increase as BMI increased.
Emergencies ; Emergency Treatment ; Humans ; Medical Records ; Needles* ; Observational Study ; Pneumothorax ; Retrospective Studies ; Thoracic Injuries ; Thoracic Wall ; Thoracostomy* ; Thorax*

In recent years, clinical applications of robotic thyroid surgery have been gradually promoted with the continuous improvement of the da Vinci robotic surgical system. Unlike traditional open surgery, robotic thyroid surgery mainly adopts remote access, which has many advantages, such as magnified high-definition 3D view and hand vibration stabilization. The rates and causes of postoperative complications differ due to different approaches, view angles, and operation sequences. This paper presents the literature on both transoral and bilateral areolar axillary approaches in robotic thyroid surgery, focusing on five common complications under both approaches, including laryngeal recurrent nerve injury and hypoparathyroidism, to provide theoretical support for the standardization of robotic thyroid surgery.