Self-supervised and unsupervised learning using diffusion models in medical imaging: from theory to applications
Recently, deep learning approaches have become the main research frontier for image reconstruction and enhancement problems thanks to their high performance, along with their ultra-fast inference times. However, due to the difficulty of obtaining matched reference data for supervised learning, there has been increasing interest in unsupervised learning approaches that do not need paired reference data. In particular, self-supervised learning and generative models have been successfully used for various inverse problem applications. In this talk, we overview recent approaches using score-function, the gradient of loglikelihood function from the data, which address the lack of supervised training data set. In particular, one-step score-based denoising approaches called Noise2Score are reviewed as a unified framework for self-supervised denoising without reference data set. Then, a recent score-based diffusion model is discussed as a powerful iterative approach that can be utilized for various image reconstruction problems beyond the denoising problems. Finally, we will explain a geometric aspect of score-based approaches from high-dimensional geometry.
Jong Chul Ye is a Professor at the Kim Jaechul Graduate School of Artificial Intelligence (AI) of Korea Advanced Institute of Science and Technology (KAIST), Korea. He received his B.Sc. and M.Sc. degrees from Seoul National University, Korea, and a Ph.D. from Purdue University, West Lafayette. Before joining KAIST, he worked at Philips Research and GE Global Research in New York. He has served as an associate editor of IEEE Trans. on Image Processing, and an editorial board member for Magnetic Resonance in Medicine. He is currently an associate editor for IEEE Trans. on Medical Imaging and a Senior Editor of IEEE Signal Processing Magazine. He is an IEEE Fellow and was the Chair of IEEE SPS Computational Imaging TC and IEEE EMBS Distinguished Lecturer in 2020-2021. He was a General Cochair (with Mathews Jacob) for IEEE Symp. On Biomedical Imaging (ISBI) 2020. His research interest is in machine learning for biomedical imaging and computer vision.