1.Two Cases of Paratesticular Rhabdomyosarcoma.
Kwang Jai KIM ; In Gi SEOUNG ; Jeng Gi KANG ; Bo Hyun HAN
Korean Journal of Urology 1986;27(6):963-966
Rhabdomyosarcoma is the most frequent cancer involving the trigone of the bladder, the proximal urethra, vagina and paratesticular tissue in children, and 15 percent of rhabdomyosarcoma in children arise in the urogenital tract. Rhabdomyosarcoma is highly malignant neoplasm with a tendency toward early infiltration of adjacent structures and metastases to regional lymphnodes and distant organs. We report tow cases of paratesticular rhabdomyosarcoma with brief review of literatures.
Child
;
Humans
;
Neoplasm Metastasis
;
Rhabdomyosarcoma*
;
Testis
;
Urethra
;
Urinary Bladder
;
Vagina
2.Correction: Methods of Hematoxylin and Eosin Image Information Acquisition and Optimization in Confocal Microscopy.
Woong Bae YOON ; Hyunjin KIM ; Kwang Gi KIM ; Yongdoo CHOI ; Hee Jin CHANG ; Dae Kyung SOHN
Healthcare Informatics Research 2016;22(4):355-355
In the article, Methods of Hematoxylin and Erosin Image Information Acquisition and Optimization in Confocal Microscopy, there was a typographical error in the title.
3.Video Archiving and Communication System (VACS): A Progressive Approach, Design, Implementation, and Benefits for Surgical Videos
Deokseok KIM ; Woojoong HWANG ; Joonseong BAE ; Hyeyeon PARK ; Kwang Gi KIM
Healthcare Informatics Research 2021;27(2):162-167
Objectives:
As endoscopic, laparoscopic, and robotic surgical procedures become more common, surgical videos are increasingly being treated as records and serving as important data sources for education, research, and developing new solutions with recent advances in artificial intelligence (AI). However, most hospitals do not have a system that can store and manage such videos systematically. This study aimed to develop a system to help doctors manage surgical videos and turn them into content and data.
Methods:
We developed a video archiving and communication system (VACS) to systematically process surgical videos. The VACS consists of a video capture device called SurgBox and a video archiving system called SurgStory. SurgBox automatically transfers surgical videos recorded in the operating room to SurgStory. SurgStory then analyzes the surgical videos and indexes important sections or video frames to provide AI reports. It allows doctors to annotate classified indexing frames, “data-ize” surgical information, create educational content, and communicate with team members.
Results:
The VACS collects surgical and procedural videos, and helps users manage archived videos. The accuracy of a convolutional neural network learning model trained to detect the top five surgical instruments reached 96%.
Conclusions
With the advent of the VACS, the informational value of medical videos has increased. It is possible to improve the efficiency of doctors’ continuing education by making video-based online learning more active and supporting research using data from medical videos. The VACS is expected to promote the development of new AI-based products and services in surgical and procedural fields.
4.Development of an Optimized Deep Learning Model for Medical Imaging
Journal of the Korean Radiological Society 2020;81(6):1274-1289
Deep learning has recently become one of the most actively researched technologies in the field of medical imaging. The availability of sufficient data and the latest advances in algorithms are important factors that influence the development of deep learning models. However, several other factors should be considered in developing an optimal generalized deep learning model. All the steps, including data collection, labeling, and pre-processing and model training, validation, and complexity can affect the performance of deep learning models. Therefore, appropriate optimization methods should be considered for each step during the development of a deep learning model. In this review, we discuss the important factors to be considered for the optimal development of deep learning models.
5.Video Archiving and Communication System (VACS): A Progressive Approach, Design, Implementation, and Benefits for Surgical Videos
Deokseok KIM ; Woojoong HWANG ; Joonseong BAE ; Hyeyeon PARK ; Kwang Gi KIM
Healthcare Informatics Research 2021;27(2):162-167
Objectives:
As endoscopic, laparoscopic, and robotic surgical procedures become more common, surgical videos are increasingly being treated as records and serving as important data sources for education, research, and developing new solutions with recent advances in artificial intelligence (AI). However, most hospitals do not have a system that can store and manage such videos systematically. This study aimed to develop a system to help doctors manage surgical videos and turn them into content and data.
Methods:
We developed a video archiving and communication system (VACS) to systematically process surgical videos. The VACS consists of a video capture device called SurgBox and a video archiving system called SurgStory. SurgBox automatically transfers surgical videos recorded in the operating room to SurgStory. SurgStory then analyzes the surgical videos and indexes important sections or video frames to provide AI reports. It allows doctors to annotate classified indexing frames, “data-ize” surgical information, create educational content, and communicate with team members.
Results:
The VACS collects surgical and procedural videos, and helps users manage archived videos. The accuracy of a convolutional neural network learning model trained to detect the top five surgical instruments reached 96%.
Conclusions
With the advent of the VACS, the informational value of medical videos has increased. It is possible to improve the efficiency of doctors’ continuing education by making video-based online learning more active and supporting research using data from medical videos. The VACS is expected to promote the development of new AI-based products and services in surgical and procedural fields.
6.Development of an Optimized Deep Learning Model for Medical Imaging
Journal of the Korean Radiological Society 2020;81(6):1274-1289
Deep learning has recently become one of the most actively researched technologies in the field of medical imaging. The availability of sufficient data and the latest advances in algorithms are important factors that influence the development of deep learning models. However, several other factors should be considered in developing an optimal generalized deep learning model. All the steps, including data collection, labeling, and pre-processing and model training, validation, and complexity can affect the performance of deep learning models. Therefore, appropriate optimization methods should be considered for each step during the development of a deep learning model. In this review, we discuss the important factors to be considered for the optimal development of deep learning models.
7.A Study on the Interpupillary Distance and the Distance Between Optical Centers in Spectacles Wearers.
Journal of the Korean Ophthalmological Society 1988;29(2):405-410
The authors analysed the interpupillary distance and the distance between optical centers in 200 spectacles wearers. The results were as follows; 1. Among the 200 glasses wearers, the cases of hospital prescriptions were 44 persons and the cases of optical shops prescriptions were 156 persons. 2. Hyperopic glasses wearers were 26 persons and myopic glasses wearers were 174 persons. 3. The distance between optical centers was coincided to the interpupillary distance in 26 persons and discrepant in 174 persons. 4. In 115 eyes the prismatic effects were more than 0.5 prism diopter, and maximal prismatic effect was 5.78 prism diopters. 5. The evaluation of the induced horizontal phoria showed that 119 persons had the induced esophoria and 55 persons had the induced exophoria. In 58 persons induced phoria were more than 1 prism diopter. Maximal induced esophoria was 11.55 prism diopters and maximal induced exophoria was 4.30 prism diopters.
Esotropia
;
Exotropia
;
Eyeglasses*
;
Glass
;
Humans
;
Prescriptions
;
Strabismus
8.Two Cases of Kayser-Fleischer Rings.
Doo Suck LEE ; Gi Gen ON ; Jae Duck KIM
Journal of the Korean Ophthalmological Society 1987;28(1):177-183
The Kayser-Fleischer ring, a characteristic finding in Wilson's disease, occurs in the corneal periphery and is usually yellow-brown but may by red, blue, green, ormixture of any these colors. The Kayser-Fleischer ring, copper deposition at the level of the posterior position of Descemet's membrane, is about 1 to 3mm in width and extends to the limbus without a lucid interval. In addition to involvement of Descemet's membrane, one may find anterior subcapsular sunflower cataract in Wilson's disease. The authors have recently experienced two cases of Wilson's disease. One case, a 17-year-old boy, has Kayser-Fleischer rings and anterior subcapsular sunflower cataracts in both eyes and the other, a 17-year-old aldolescent male, has dense yellow-green colored Kayser-Fleischer rings in both eyes. Both cases have been treated with penicillamine(1gr/day) and low copper diet. After treatment, clinical manifestations have been improved markedly but the Kayer-Fleischer rings have not disappeared yet.
Adolescent
;
Cataract
;
Copper
;
Descemet Membrane
;
Diet
;
Helianthus
;
Hepatolenticular Degeneration
;
Humans
;
Male
9.Differences in the Determination of Cause and Manner of 127 Natural Death Cases by Postmortem Inspection and Autopsy.
Gi Yeong HUH ; Kwang Hoon KIM ; Gam Rae JO ; Sang Yong LEE
Korean Journal of Legal Medicine 2013;37(1):9-13
Medico-legal investigations in Korea depend mostly on postmortem inspection without autopsy. Both untrained physicians and experienced forensic pathologists may not be able to determine the cause and manner of death only by postmortem inspection. The aim of our study was to show the limitations of postmortem inspection by evaluating the discrepancy between the results of postmortem inspection and autopsy after natural death. The manner of death by postmortem inspection changed to unnatural death in 9.4% of the cases (12 cases/127 cases) after autopsy. The cause of death in most cases was consumption of alcohol, agricultural chemicals, and antipsychotic intoxication. The cause of death by postmortem inspection changed in 24.3% of the cases (26 cases/107 cases) among cases of confirmed natural death after autopsy. The positive predictive value of cause of death by postmortem inspection was higher for cardiovascular disease (79.0%) and lower for chronic alcoholism and/or chronic liver disease (28.6%). This study shows that forensic pathologists could make considerable errors in determining the cause and manner of death without autopsy and emphasizes the necessity to refine medico-legal investigations in Korea by introducing the limited autopsy with toxicologic study and supportive postmortem imaging.
Agrochemicals
;
Alcoholism
;
Autopsy
;
Cardiovascular Diseases
;
Cause of Death
;
Korea
;
Liver Diseases
10.A clinical study on the ectopic pregnancy following laparoscopic tubal sterilization.
Sang Kyung KIM ; Kwang Yeol LEE ; Young Oh TARK ; Ki Hak LEE ; Gi Sang KWON
Korean Journal of Obstetrics and Gynecology 1992;35(4):480-488
No abstract available.
Female
;
Pregnancy
;
Pregnancy, Ectopic*
;
Sterilization, Tubal*