• Korean Journal of Radiology
• /
• v.21 no.5
• /
• pp.629-631
• /
• 2020

• Imaging Science in Dentistry
• /
• v.50 no.3
• /
• pp.261-263
• /
• 2020

• Korean Journal of Radiology
• /
• v.22 no.4
• /
• pp.547-558
• /
• 2021

The perihepatic space is frequently involved in a spectrum of diseases, including intrahepatic lesions extending to the liver capsule and disease conditions involving adjacent organs extending to the perihepatic space or spreading thanks to the communication from intraperitoneal or extraperitoneal sites through the hepatic ligaments. Lesions resulting from the dissemination of peritoneal processes may also affect the perihepatic space. Here we discuss how to assess the perihepatic origin of a lesion and describe the magnetic resonance imaging (MRI) features of normal structures and fluids that may be abnormally located in the perihepatic space. We then review and illustrate the MRI findings present in cases of perihepatic infectious, tumor-related, and miscellaneous conditions. Finally, we highlight the value of MRI over computed tomography.

• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1061-1080
• /
• 2023

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.

• 대한핵의학회:학술대회논문집
• /
• 1988.05a
• /
• pp.124.2-124.2
• /
• 1988

• 대한핵의학회:학술대회논문집
• /
• 1988.05a
• /
• pp.137.1-137.1
• /
• 1988

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 1999.11a
• /
• pp.409-411
• /
• 1999

• Proceedings of the KSMRM Conference
• /
• 2006.11a
• /
• pp.42-42
• /
• 2006

• Korean Journal of Radiology
• /
• v.24 no.12
• /
• pp.1173-1175
• /
• 2023

• Investigative Magnetic Resonance Imaging
• /
• v.22 no.3
• /
• pp.182-186
• /
• 2018

Dynamic enhanced magnetic resonance lymphangiography can be used to provide anatomic and dynamic information for various lymphatic diseases, including thoracic duct injury, and can also help to guide the thoracic duct embolization procedure. We present a case of postoperative chylothorax demonstrated by dynamic enhanced MR lymphangiography. In this case, the chyle leakage site and location of cisterna chyli were clearly visualized by dynamic enhanced MR lymphangiography, thus allowing for management with thoracic duct embolization.