Image Reconstruction & Analysis for Clinicians
Weekday Course
ORGANIZERS: Anthony Christodoulou, Khin Tha, Takeshi Yokoo
Wednesday, 07 June 2023
701A
13:30 -
15:30
Moderators: Claudia Prieto
Skill Level: Basic
Session Number: W-04
CME Credit
Session Number: W-04
Overview
This course will be a basic review of image reconstruction and analysis techniques used in clinical practice. The presentations will focus on practical implications for clinical use. The course will cover k-space, compressed sensing, artificial intelligence denoising/enhancement, and volumetric processing/display.
Target Audience
This course is primarily designed for the clinician who will benefit from an understanding of the hows, whys, pitfalls, and practical implementation of image reconstruction and analysis techniques. While it requires no prior experience with MR, those with some familiarity and experience will also benefit. Those interested may include: radiologists and clinicians relatively new to MR imaging (including residents and fellows), experienced radiologists and clinicians wanting a refresher course in MR physics and image reconstruction, and physicists and engineers wanting an introduction to the field and understanding of what technical aspects are relevant to clinicians.
Educational Objectives
As a result of attending this course, participants should be able to:
- Explain how the MR images viewed on the console are reconstructed;
- Identify fast scan technologies; and
- Apply volumetric processing techniques.
13:30 | | From k-Space to Image Space Susie Huang |
14:00 | | Compressed Sensing in the Clinic Shreyas Vasanawala Keywords: Image acquisition: Reconstruction, Image acquisition: Fast imaging Sparsity, ubiquitous in medical images, can enable faster scans. Here, the concepts of sparsity and compressibility are reviewed. This is followed by an overview of how these concepts can be leveraged to scan faster, and conditions under which imaging speed can be pushed further. |
14:30 | | AI Image Enhancement & Denoising Mika Kitajima Keywords: Neuro: Brain Deep learning (DL)-based denoising and image
enhancement techniques reduce scan time while improving SNR and maintaining
spatial resolution. Combining DL-based denoising with other rapid imaging techniques
including parallel imaging and compressed sensing further reduces scan time. DL-based
denoising techniques may be particularly beneficial for potentially low SNR
images and/or time-consuming sequences such as DWI with high b-value and large
number of MPG directions, and it may improve image quality of quantitative
maps. DL-based resolution enhancement such as super-resolution model is
superior to conventional methods. To establish clinically useful DL-based
denoising and image enhancement techniques, prospective multi-site studies are
required. |
15:00 | | Volumetric Processing: How to Do 3D MPR/MIP/minIP Taro Takahara |