IEEE 2021 NSS MIC

Please note! All times in the online program are given in New York - America (GMT -04:00) times!

New York - America ()
Jan 26, 2022, 2:47:59 PM
Your time ()
n/a
Tokyo - Asia ()
Jan 27, 2022, 4:47:59 AM
Our exhibitors and sponsors – click on name to visit booth:

To search for a specific ID please enter the hash sign followed by the ID number (e.g. #123).

Medical image reconstruction using deep learning

Session chair: Qi , Jinyi (University of California, Davis, Department of Biomedical Engineering, Davis, USA); Reader , Andrew J. (King's College London, School of Biomedical Engineering and Imaging Sciences, London, UK)
 
Shortcut: SC-05
Date: Monday, 18 October, 2021, 8:00 AM - 11:15 AM
Room: SC-01
Session type: Short Course

Medical imaging reconstruction has progressed from analytic reconstruction methods, model-based iterative reconstruction, to the latest learning-based and learning-enhanced reconstruction methods. This course starts from key fundamentals in tomographic image reconstruction and then covers a range of approaches of applying artificial intelligence (AI) and deep learning (DL) methods to image reconstruction. We will use positron emission tomography (PET) as the primary example, but the basic principles are applicable to other imaging modalities.

Contents

Click on an contribution to preview the abstract content.

8:00 AM SC-05-01

Medical image reconstruction using deep learning (#1475)

J. Qi1, A. Reader2

1 University of California, Davis, Department of Biomedical Engineering, Davis, California, United States of America
2 King’s College London, London, United Kingdom

Abstract

Course Outline:

  1. Introduction to deep learning
  2. Basics of tomographic mage reconstruction and direct inversion networks
  3. Iterative reconstruction (IR) and IR-inspired DL methods
    • Unrolled deep network
    • Deep network based regularization
  4. Deep learning in quantitative corrections
    • Deep learning for attenuation correction
    • Deep learning for scatter correction
    • Deep learning for motion correction
Biographies:

Jinyi Qi is a professor of biomedical engineering at the University of California – Davis (UC Davis), USA. He received his Ph.D. in electrical engineering from the University of Southern California in 1998. Prior to joining the faculty of UC Davis in 2004, he was a Research Scientist in the Department of Functional Imaging at the Lawrence Berkeley National Laboratory. Dr. Qi served as the Interim Chair of the Department of Biomedical Engineering at UC Davis from 2015 to 2016. He is an Associate Editor of IEEE TMI and IEEE TRPMS, and is an elected Fellow of AIMBE and IEEE. His main research interests concern the development of advanced image formation and processing tools to push the boundary of molecular imaging using positron emission tomography (PET)/computed tomography (CT).

Andrew Reader is a professor of imaging sciences at King’s College London, United Kingdom. He received his Ph.D. in medical physics from the University of London in 1999 on the subject of PET image reconstruction. Prior to joining the School of Biomedical Engineering and Imaging Sciences at King’s College London in 2014, he was a Canada Research Chair at McGill University and the Montreal Neurological institute for 6 years. He is an Associate Editor of IEEE TRPMS and has co-authored over 200 scientific outputs. His main research interests include PET-MR, multi-modal image reconstruction and medical image analysis, all now with a primary emphasis on exploiting deep learning.

Keywords: Short Course
9:15 AM SC-05-02

Break

9:30 AM SC-05-03

Medical image reconstruction using deep learning (Part II) (#1585)

J. Qi1, A. Reader2

1 University of California, Davis, Department of Biomedical Engineering, Davis, California, United States of America
2 King's College, London, London, United Kingdom

10:45 AM SC-05-04

Q&A


Our exhibitors and sponsors – click on name to visit booth: