Hyun Jik Song
Yonsei University · 医学
研究室紹介
Professor Hyun Jik Song's research lab specializes in clinical artificial intelligence and medical image analysis, focusing on leveraging deep learning to improve diagnostic accuracy in gastrointestinal diseases. The lab investigates AI applications in capsule endoscopy for detecting small bowel lesions such as erosions, ulcers, and angiodysplasia, aiming to enhance early diagnosis and reduce diagnostic variability. Additionally, the lab explores age-related clinical patterns in infectious diseases like Clostridium difficile infection, integrating clinical data with machine learning to uncover demographic-specific disease presentations. Their work bridges clinical gastroenterology with advanced computational methods to support precision medicine.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
5Aims Since the introduction of computer vision technology using Deep-learning, various acceptable results have been reported for the recognition of small bowel pathologies in capsule endoscopy. However, the results are limitedly dealt with lesions such as erosions, ulcers, and angioectasia, which are easy to apply machine learning technologies. We classified capsule endoscopy images into those with and without significant lesions, and studied whether artificial intelligence, which learned the im
Advancing age is a well-known risk factor for Clostridium difficile infection (CDI). However, age-specific clinical differences in CDI are uncertain. A retrospective comparative analysis was performed based on age in 1367 patients with CDI in Korea. Most clinical features were similar in the two age groups studied, however malignancy was more common in the older group (age ≥ 65 y) (p < 0.001), while chemotherapy and transplantation were more common in the younger group (age < 65 y) (p < 0.001).