Artificial Intelligence for Limited Labels and Domain Differences in Medical Images
Artificial intelligence (AI) is revolutionizing the field of medicine by providing advanced tools and techniques for medical imaging analysis. However, developing AI models for medical images with limited labels and domain differences remains a challenging task. Despite the availability of advanced medical imaging technologies, making annotations in medical imaging remains a difficult task due to the complexity and variability of anatomical structures, variations in imaging modalities, and the need for high accuracy and consistency. In this presentation, I will present cutting-edge artificial intelligence techniques, including weakly-supervised learning, few-shot learning, debiasing, and federated learning, that aim to address these challenges and improve the effectiveness of medical image analysis.
Dr. Sang Hyun Park is an Associate Professor in the Department of Robotics and Mechatronics and AI major at DGIST. He completed his Ph.D. in the Department of Electrical and Computer Engineering from the Seoul National University in Feb. 2014 under the supervision of Prof. Sang Uk Lee, and a B.S. from the Yonsei University in Feb. 2008. He spent a year as a Postdoctoral Fellow at SRI International working with Prof. Kilian Pohl (3/2016-2/2017) and two years as a Postdoctoral Fellow in the Biomedical Research Imaging Center at the University of North Carolina working with Prof. Dinggang Shen (3/2014-2/2016). To learn more about Prof. Park’s research projects, visit his website: https://mispl.dgist.ac.kr/