http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김해구 ( Hae Koo Kim ),김성은 ( Sung Eun Kim ),박무인 ( Moo In Park ),박선자 ( Seun Ja Park ),문원 ( Won Moon ),김재현 ( Jae Hyun Kim ),정경원 ( Kyoungwon Jung ),남용진 ( Yong Jin Nam ) 대한소화기학회 2017 대한소화기학회지 Vol.69 No.5
The peritoneum is one of the common extrapulmonary sites of tuberculosis infection. Patients with underlying end-stage renal or liver disease are frequently complicated by tuberculous peritonitis; however, the diagnosis of the tuberculous peritonitis is difficult due to its insidious nature, well as its variability in presentation and limitation of available diagnostic tests. Once diagnosed, the preferred treatment is usually antituberculous therapy in uncomplicated cases. However, surgical treatment may also be required for complicated cases, such as small bowel obstruction or perforation. An 85-year-old woman was referred our hospital for abdominal pain with ileus. Despite medical therapy, prolonged ileus and progression to sepsis were shown, she underwent surgery to confirm the diagnosis and relief of mechanical ileus. Intraoperative peritoneal biopsy and macroscopic findings confirmed tuberculous peritonitis. Therefore, physicians should consider the possibility of tuberculous peritonitis in patients with unexplained small bowel obstruction. (Korean J Gastroenterol 2017;69:308-311)
권용우(Yong Woo Kwon),한정훈(Jeong Hoon Han),김지훈(Ji Hoon Kim),김해문(Hae Moon Kim),문영식(Young Shik Moon) 대한전자공학회 2020 대한전자공학회 학술대회 Vol.2020 No.11
The deep learning method requires a lot of data to achieve good performance, but suffers from insufficient of data. This problem is particularly remarkable in the medical image processing. To solve this problem, a method of weakly supervised learning using pseudo-label is widely used. In this paper, we propose a method of segmenting the vertebral body by augmentation the data using the weakly supervised method in the lateral X-ray image of infants. The proposed method is designed based on U-Net network, which is widely used in medical image segmentation problems, and consists of one encoder and two decoders. Experimentally, the result shows that the performance of our method has been improved by 1.05 % over the previous method.
박경리(Kyung Ri Park),권용우(Yong Woo Kwon),김지훈(Ji Hoon Kim),김해문(Hae Moon Kim),서지원(Ji Won Suh),강경원(Kyung Won Kang),문영식(Young Shik Moon) 대한전자공학회 2021 대한전자공학회 학술대회 Vol.2021 No.6
Skin lesions have a high misdiagnosis rate due to a wide variety of forms. Recently, a deep learning based skin lesion classification method is difficult to classify due to hair and fuzzy boundaries of skin lesions. In this paper, we propose a network for classifying skin lesions and segmenting skin lesion regions using a multitask learning method. Experimentally, the result shows that the performance of our method has been improved by 2.48 % over the previous method.