• The Journal of KAIRB
• /
• v.2 no.1
• /
• pp.6-22
• /
• 2020

Purpose: Clinical studies require institutional review board (IRB) approval based on the ethical principle and regulations. While the number of clinical studies has been increased and diversified, duplicated IRB review for multi-center studies has become a major issue. Therefore, single IRB system has been suggested in revised Common Rule. This study aimed to identify and assess the current status of single IRB in Korea and the anticipated needs of single IRB from researchers and IRB member or administrators. Methods: We developed 14 questions including perceived advantages and disadvantages of single IRB, and anticipated problems. The online survey collected opinions on single IRB from researchers, IRB members and IRB administrators. We also interviewed five IRB administrators who have an experience of single IRB. Results: A total of 80 responses were analyzed in this study. Although efficiencies were suggested for the advantages of single IRB in terms of reducing burden of duplicated review, respondents also perceived that the different review criteria between single IRB and each IRB would be a major hurdle for adopting single IRB system. Therefore, the standardization of standard of procedures (SOP) and the standardization of IRB submission materials should be preceded. According to the small group experiences of single IRB in Korea, we also observed the similar anticipated problems of single IRB. Conclusion: Single IRB system has many advantages for conducting multi-center trial. However, many specialists still have a lot of concerns about introducing a single IRB system in Korea. Therefore, a gradual, step-by-step process for conducting a single IRB system in Korea will be needed. Many studies for improving currently suggested single IRB system and the improvement of awareness about the essential of single IRB system would be needed.

• Therapeutic Science for Rehabilitation
• /
• v.11 no.1
• /
• pp.35-47
• /
• 2022

Objective : In this study, we conducted a questionnaire survey of occupational therapists to examine their perceptions on and willingness to provide telerehabilitation dementia prevention education. Methods : From March 13 to 19, 2021, a questionnaire survey targeting occupational therapists in Busan, Ulsan, and Gyeongnam was conducted. 100 questionnaires were distributed but only 70 were collected. The collected data were subjected to frequency analysis and descriptive statistics using the statistical program SPSS version 23.0. Results : The average scores by region were as follows. The average compatibility score was highest at 3.92 score, intention to providing education, doctors 3.89 score, community-centric rehabilitation awareness 3.81 score, cost saving 3.78 score, perceiver usefulness 3.75 score, accessibility 3.62 score, the quality of telerehabilitation service was in order of 3.49 score. Conclusion : All items asking whether occupational therapists participate in community-centered rehabilitation and non-face-to-face dementia prevention education programs showed high scores, indicating the willingness to participate actively. In the future, in addition to follow-up research on the implementation of telerehabilitation dementia prevention education, measures for improving accessibility within the local and national government should be discussed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.331-337
• /
• 2023

In this paper, we propose a deep learning model to detect lumbar 3 (L3) CT images to determine the occurrence and degree of sarcopenia. In addition, we would like to propose an optimization technique that uses oversampling ratio and class weight as design parameters to address the problem of performance degradation due to data imbalance between L3 level and non-L3 level portions of CT data. In order to train and test the model, a total of 150 whole-body CT images of 104 prostate cancer patients and 46 bladder cancer patients who visited Gangneung Asan Medical Center were used. The deep learning model used ResNet50, and the design parameters of the optimization technique were selected as six types of model hyperparameters, data augmentation ratio, and class weight. It was confirmed that the proposed optimization-based L3 level extraction model reduced the median L3 error by about 1.0 slices compared to the control model (a model that optimized only 5 types of hyperparameters). Through the results of this study, accurate L3 slice detection was possible, and additionally, we were able to present the possibility of effectively solving the data imbalance problem through oversampling through data augmentation and class weight adjustment.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.260-268
• /
• 2024

Cervical cancer is the fourth most common cancer in women worldwide, and more than 604,000 new cases were reported in 2020 alone, resulting in approximately 341,831 deaths. The Cox regression model is a major model widely adopted in cancer research, but considering the existence of nonlinear associations, it faces limitations due to linear assumptions. To address this problem, this paper proposes ResSurvNet, a new model that improves the accuracy of cervical cancer mortality prediction using ResNet's residual learning framework. This model showed accuracy that outperforms the DNN, CPH, CoxLasso, Cox Gradient Boost, and RSF models compared in this study. As this model showed accuracy that outperformed the DNN, CPH, CoxLasso, Cox Gradient Boost, and RSF models compared in this study, this excellent predictive performance demonstrates great value in early diagnosis and treatment strategy establishment in the management of cervical cancer patients and represents significant progress in the field of survival analysis.

• Journal of the Korean Society of Radiology
• /
• v.18 no.1
• /
• pp.53-63
• /
• 2024

The purpose of this study was to analyze radiological technologists' (RT) task perceptions of intravenous injection behavior of contrast medium and use it as basic data for future workforce response plans. We surveyed a total of 172 RT using questionnaire terms consisting of demographic characteristics, job priorities, and RT' task perceptions of intravenous injection behavior. Statistical analysis was performed using descriptive statistics, frequency analysis, independent samples T-test, and ANOVA analysis. As a result, first, current clinical RT were highly aware of the need for intravenous injection behavior as a response to the future workforce of them, and the workload burden resulting from this was evaluated as low. Second, the fear of intravenous injection behavior was found to be significant, so it is judged to be useful to perform them as selective job actions rather than all RT' task. Third, the need for training courses and certification for RT' intravenous injection behavior is being raised, and additional specific research on this is required. Last, RT' positive perception of intravenous injection behavior could be expected as a foundation for improving national medical services, strengthening RT expertise, and expanding tasks.

• Industry Promotion Research
• /
• v.9 no.1
• /
• pp.39-45
• /
• 2024

Dangerous tasks that occur every day at industrial site manufacturing plants, which have recently been making rapid changes, were classified by type, and the effect of mobile circuit television (CCTV) on safety accidents among daily safety management methods was analyzed. The subject of the study is about 3,000 workers who manage the infrastructure facility sector to supply utilities such as gas, water, and electricity to the display manufacturing process located in Asan City, and the study was conducted based on the daily dangerous work from 2019 to 2022, and during this study period, many construction works such as new investment and expansion of construction and manufacturing processes were occurring at the site. As a result, the rate of safety accidents and exposure to risks are expanding, and most of the safety accidents occurred because the sectors that did not follow the basics and the safety measures on the site were not implemented. In this paper, it was confirmed that there is an accident reduction effect according to the relationship between the dangerous work classified according to the work importance and the mobile CCTV shooting rate. Considering the characteristics of the manufacturing plant site, it can be used to play the role of basic data for preventing safety accidents based on the expansion of the introduction of a new safety management culture in the future.

• Journal of the Korean Society of Radiology
• /
• v.83 no.2
• /
• pp.265-283
• /
• 2022

To develop Korean coronavirus disease (COVID-19) chest imaging justification guidelines, eight key questions were selected and the following recommendations were made with the evidence-based clinical imaging guideline adaptation methodology. It is appropriate not to use chest imaging tests (chest radiograph or CT) for the diagnosis of COVID-19 in asymptomatic patients. If reverse transcription-polymerase chain reaction testing is not available or if results are delayed or are initially negative in the presence of symptoms suggestive of COVID-19, chest imaging tests may be considered. In addition to clinical evaluations and laboratory tests, chest imaging may be contemplated to determine hospital admission for asymptomatic or mildly symptomatic un-hospitalized patients with confirmed COVID-19. In hospitalized patients with confirmed COVID-19, chest imaging may be advised to determine or modify treatment alternatives. CT angiography may be considered if hemoptysis or pulmonary embolism is clinically suspected in a patient with confirmed COVID-19. For COVID-19 patients with improved symptoms, chest imaging is not recommended to make decisions regarding hospital discharge. For patients with functional impairment after recovery from COVID-19, chest imaging may be considered to distinguish a potentially treatable disease.

• Journal of the Korean Society of Radiology
• /
• v.81 no.2
• /
• pp.272-289
• /
• 2020

Current advances in CT techniques allow thorough evaluation of the beating heart. The strengths of cardiac CT relative to echocardiography and magnetic resonance imaging are its high availability in most institutions, rapid production of high-quality images, and outstanding delineation of the anatomy. For many normal variants and pathologic conditions, such as thrombi, masses, and congenital abnormalities of the left atrium, CT findings are sufficient to make a presumptive diagnosis. Assessments of the left atrium and left atrial appendage are particularly important for the management of atrial fibrillation, as various catheter-based procedures are aimed at the mechanical and electrical isolation of these structures. CT offers information crucial to a successful catheter-based procedure or surgery. Therefore, a comprehensive review of the geometry (shape, size, and relative position), along with various CT imaging features of pathologic states, should be provided in radiology reports to be of clinical value.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1124-1139
• /
• 2021

The objective assessment of atrophy and the measurement of brain volume is important in the early diagnosis of dementia and neurodegenerative diseases. Recently, several MR-based volumetry software have been developed. For their clinical application, several issues arise, including the standardization of image acquisition and their validation of software. Additionally, it is important to highlight the diagnostic performance of the volumetry software based on expert opinions. We instituted a task force within the Korean Society of Neuroradiology to develop guidelines for the clinical use of MR-based brain volumetry software. In this review, we introduce the commercially available software and compare their diagnostic performances. We suggest the need for a standard protocol for image acquisition, the validation of the software, and evaluations of the limitations of the software related to clinical practice. We present recommendations for the clinical applications of commercially available software for volumetry based on the expert opinions of the Korean Society of Neuroradiology.

• Journal of the Korean Society of Radiology
• /
• v.81 no.6
• /
• pp.1397-1411
• /
• 2020

Purpose To survey the perception, knowledge, wishes, and expectations of Korean radiology residents regarding artificial intelligence (AI) in radiology. Materials and Methods From June 4th to 7th, 2019, questionnaires comprising 19 questions related to AI were distributed to 113 radiology residents. Results were analyzed based on factors such as the year of residency and location and number of beds of the hospital. Results A total of 101 (89.4%) residents filled out the questionnaire. Fifty (49.5%) respondents had studied AI harder than the average while 68 (67.3%) had a similar or higher understanding of AI than the average. In addition, the self-evaluation and knowledge level of AI were significantly higher for radiology residents at hospitals located in Seoul and Gyeonggi-do compared to radiology residents at hospitals located in other regions. Furthermore, the self-evaluation and knowledge level of AI were significantly lower in junior residents than in residents in the 4th year of training. Of the 101 respondents, only 16 (15.8%) had experiences in AI-related study while 91 (90%) were willing to participate in AI-related study in the future. Conclusion Organizational efforts through a radiology society would be needed to meet the need of radiology trainees for AI education and to promote the role of radiologists more adequately in the era of medical AI.