http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
정우경 ( Woo Kyoung Jeong ) 대한소화기학회 2021 대한소화기학회지 Vol.78 No.5
간세포암종은 바이러스성 간염 외에도 다양한 원인에 의해 발생하며, 다른 암종과는 달리 영상의학적 진단만을 거쳐 치료 계획을 수립하는 경우가 많다. LI-RADS는 미국 영상의학회에서 간 영상 소견에 대한 확실한 의사소통과 표준화된 보고서 작성을 목적으로 만든 진단 시스템이며, 최근 미국간학회 가이드라인에 진단 기준으로 포함되었다. 이외에도 gadoxetic acid MRI의 활용이 보편화됨에 따라 간세포암종의 진단뿐만 아니라 간세포암종의 치료 후 예후 예측을 가능하게 하는 영상 소견들이 연구되고 있어, 앞으로 간세포암종의 영상의학 발달이 더욱 기대된다. There are various causes of hepatocellular carcinoma, including viral hepatitis, and treatment strategies are often established based on the radiology diagnosis, unlike other carcinomas. The liver imaging reporting and data system (LI-RADS) is a diagnostic system developed by the American College of Radiologists for clear communication and standardized reports of the liver imaging findings. It was recently included in the clinical guidance of the American Association for the Study of Liver Diseases. In addition, the radiologic findings of hepatocellular carcinoma (HCC) enable a prediction of the prognosis after treatment and a diagnosis of diseases because the use of gadoxetic acid MRI has become more common. Thus, the role of radiology for the diagnosis and treatment of HCC is expected to be developed further. (Korean J Gastroenterol 2021;78:261-267)
Unsupervised Liver Segmentation using Domain Adaptation in MRI
Jiwon Jung(정지원),Ehwa Yang(양이화),Woo Kyoung Jeong(정우경),Kyoung Doo Song(송경두),Jae-Hun Kim(김재훈) 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
Liver segmentation is an essential procedure in Computer-Aided Diagnosis (CAD), surgery, and volume measurement for radiotherapy. But it is still a challenging task to extract liver tissue parenchyma due to nearby organs with similar intensities. When we segment the liver using supervised deep learning, fully-annotated datasets are needed. However, it is hard to obtain well-annotated labels because of their diverse appearances such as size and shape. Also, it takes expensive costs for labeling. In this paper, we performed unsupervised liver segmentation in unlabeled Magnetic Resonance Imaging (MRI) datasets using deep learning. To generate labels of MRI, the domain adaptation technique is applied with CT images containing well-annotated labels. We trained the segmentation model with the MRI dataset which is transferred from CT images and evaluated the model on real MRI datasets. The performance of our model shows 88% dice similarity coefficient accuracy. This study could be one of the solutions to handle the difficulty to train deep learning models with unlabeled datasets.
최솔지(Sol Ji Choi),정승은(Seung Eun Jung),정우경(Woo Kyoung Jeong),최미영(Mi young Choi),백정환(Jung Hwan Baek) 한국보건의료연구원 2016 근거와 가치 Vol.2 No.3
Objectives: This study aims to establish collaboration system for trustworthy clinical practice guideline. Evidence- based Korean Clinical Imaging development was led by the Korean Society of Radiology (KSR) and the National Evidence-based Healthcare Collaborating Agency (NECA). Methods: Collaboration framework is consisted of internal collaboration and external collaboration. Guideline development committee and working groups co-worked as internal collaboration. As extra collaboration, expected end-users were involved in consensus group who are clinical experts related to guidelines. Protocol for guideline development and education was performed. Consensus group consulted during developing process and contributed to panel survey. Results: Collaborating works for trustworthy clinical practice guideline, a protocol was developed to reflect the process of developing diagnostic guidelines in Korea, which differs from traditional interventional treatment. Conclusion: Collaboration framework was effective for developing evidence-based clinical imaging guideline. Moreover, this framework will be continued and revised respond to the needs for trustworthy guidelines.
이준행 ( Jun Haeng Lee ),김재규 ( Jae G Kim ),정혜경 ( Hye Kyung Jung ),김정훈 ( Jung Hoon Kim ),정우경 ( Woo Kyoung Jeong ),전태주 ( Tae Joo Jeon ),김준미 ( Joon Mee Kim ),김용일 ( Young Il Kim ),류근원 ( Keun Won Ryu ),공성호 ( 대한소화기학회 2014 대한소화기학회지 Vol.63 No.2
Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Department of Medicine, Chung-Ang University College of Medicine, Seoul1, Department of Internal Medicine, Ewha Medical Research Institute, Ewha Womans University School of Medicine, Seoul2, Department of Radiology and Institute of Radiation Medicine, Seoul National University College of Medicine, Seoul3, Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul4, Department of Nuclear Medicine, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul5, Department of Pathology, Inha University School of Medicine, Incheon6, Department of Surgery, Ewha Womans University School of Medicine, Seoul7, Center for Gastric Cancer, National Cancer Center, Goyang8, Department of Surgery, Seoul National University Hospital, Seoul9, Department of Surgery, Yonsei University College of Medicine, Seoul10, Department of Internal Medicine, Asan Medical Center, Ulsan University College of Medicine, Seoul11, Department of Internal Medicine, Korea University College of Medicine, Seoul12, Department of Internal Medicine, Hallym University Medical Center, Hallym University College of Medicine, Anyang13, Department of Medical Oncology, Yonsei University College of Medicine, Seoul14, Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul15, Department of Radiation Oncology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul16, Department of Pathology, Seoul St. Mary`s Hospital, The Catholic University of Korea, Seoul17, Department of Preventive Medicine, Korea University Medical College, Seoul18, Korea Although, gastric cancer is quite common in Korea, the treatment outcome is relatively favorable compared to that of Western countries. However, there is no Korean multidisciplinary guideline for gastric cancer and thus, a guideline adequate for domestic circumstances is required. Experts from related societies developed 22 recommendation statements for the diagnosis (n=9) and treatment (n=13) based on relevant key questions. Evidence levels based on systematic review of literatures were classified as five levels from A to E, and recommendation grades were classified as either strong or weak. The topics of this guideline cover diagnostic modalities (endoscopy, endoscopic ultrasound, radiologic diagnosis), treatment modalities (surgery, therapeutic endoscopy, chemotherapy, radiotherapy) and pathologic evaluation. External review of the guideline was conducted at the finalization phase. (Korean J Gastroenterol 2014;63:66-81)