Colloquiums and Conferences

Knowledge-Guided Deep Learning for Enhanced Medical Image Segmentation

Time: 2025-03-10 23:01:00

Title: Knowledge-Guided Deep Learning for Enhanced Medical Image Segmentation
Speaker: Prof. Yanwei Chen
Affiliation: Ritsumeikan University, Japan

Speaker Biography:
    Yanwei Chen graduated from Kobe University, Japan in 1985 and received his Ph.D. (Doctor of Engineering) from Osaka University in 1990. He has worked as a researcher at the Institute for Laser Technology, and as a lecturer, associate professor and professor at the University of the Ryukyus. He is a tenured professor in the College of Information Science and Engineering at Ritsumeikan University and the founder and first director of the Ritsumeikan University Research Centre for Advanced Medical and Health Informatics. In April 2024 he was elected a foreign member of the Engineering Academy of Japan. His research covers computer vision, computational anatomy and artificial intelligence, and he has published more than 200 papers in leading journals and conferences including IEEE Transactions on Image Processing, IEEE Transactions on Medical Imaging, CVPR, ICCV, IJCAI and AAAI. His distinctions include the ICPR 2013 Best Scientific Paper Award, the JAMIT Best Paper Award and the CAS Outstanding Overseas Chinese Scientist Fund. According to the Stanford/Elsevier rankings, he is among the world's top 2% of scientists for both single-year and career-long impact. As principal investigator he has led nearly 20 Japanese government-funded and international collaborative projects.

Abstract:
    Recently, Deep Learning (DL) has played an important role in various academic and industrial domains, especially in computer vision and image recognition. Although deep learning (DL) has been successfully applied to medical image analysis, achieving state-of-the-art performance, few DL applications have been successfully implemented in real clinical settings. The primary reason for this is that the specific knowledge and prior information of human anatomy possessed by doctors is not utilized or incorporated into DL applications. In this keynote address, I will present our recent advancements in knowledge-guided deep learning for enhanced medical image analysis. This will include two research topics: (1) our proposed deep atlas prior, which incorporates medical knowledge into DL models; (2) language-guided medical image segmentation, which incorporates the specific knowledge of doctors as an additional language modality into DL models.