Nonlinear Ill-Posed Inverse Problem in Low-Dose Computed Tomography

Abstract

This talk describes the mathematical structure of the ill-posed nonlinear inverse problem of low-dose dental cone-beam computed tomography (CBCT). Despite this severe ill-posedness, the demand for dental CBCT systems is rapidly growing because of their cost competitiveness and low radiation dose. The speaker will explain the underlying reasons why dental CBCT is more ill-posed than standard computed tomography. He will also describe the limitations of existing methods in the accurate restoration of the morphological structures of teeth using dental CBCT data severely damaged by metal implants. He will then explain the advantages of a deep learning-based approach to the reconstruction of computed tomography images over conventional regularization methods. Finally, he would like to explain future research directions in this field.

About the Speaker

Prof. Jin Keun SEO received his PhD in Mathematics from the University of Minnesota in 1991. Since 1995, he has been a Professor at Yonsei University where he has served as the Founding Director of the Department of Computational Science and Engineering in 2008-2013. He is currently a Professor of Mathematics and Computing (Computational Science and Engineering) there.

Prof. Seo’s research interests include machine learning for medical image analysis, inverse problems, mathematical modeling, partial differential equations and harmonic analysis. Recently, he wrote books entitled Nonlinear Inverse Problems in Imaging and Electro-Magnetic Tissue Properties MRI that provide the diverse knowledge and skills needed to deal effectively with nonlinear inverse problems.

Prof. Seo received the DI Prize for Mathematicians from the Korean Mathematical Society (KMS) in 2013 and the Samil Prize (Science) from the Samil Foundation in 2016. He was elected a Member of KMS in 2019.

For Attendees' Attention

This talk will be held online via Zoom. To attend, please join the Zoom meeting at https://hkust.zoom.us/j/96502041732 (Meeting ID: 965 0204 1732 / Passcode: iasip2023).

About the Program

For more information, please refer to the program website at https://iasprogram.hkust.edu.hk/inverseproblems/.