ISMRM 25th Annual Meeting & Exhibition • 22-27 April 2017 • Honolulu, HI, USA

Educational Session: Junior Fellows Symposium: Machine Learning in Imaging

Educational Course

ORGANIZERS: Jakob Assländer, Ph.D., Steven H. Baete, Ph.D., Adrienne E. Campbell-Washburn, Ph.D., Thijs Dhollander, Ph.D. & Signe Johanna Vannesjö, Ph.D.

Wednesday, 26 April 2017
Room 313BC  13:45 - 15:45 Moderators:  Jakob Assländer, Steven Baete

Skill Level: Intermediate

Slack Channel: #E_CrossCutting
Session Number: W04

This symposium will provide an introduction to neural network and how they may be used for MRI reconstruction and computer aided-diagnosis. This symposium will include three educational talks and a panel discussion with clinicians and technical experts on the future of these methods in the field of MRI.

Target Audience
MR physicists and engineers, reconstruction specialists who want to learn how to apply deep learning techniques to MRI applications. Clinicians who want to learn about novel reconstruction methods and computer aided diagnosis that may one day help them read MR-images.

Educational Objectives
Upon completion of this course, participants should be able to:
-Explain the basics of deep learning and neural networks;
-Illustrate the application of deep learning to reconstruction; and
-Recognize the potential value of computer-aided diagnosis.


Machine Learning & Opportunities in MRI
Daniel Alexander
The talk will give an introduction to machine learning and explore opportunities to exploit the technology in MRI development and application.

Insights into Learning-Based MRI Reconstruction
Kerstin Hammernik
In this educational, we give an overview of the current developments in deep learning-based MRI reconstruction of undersampled k-space data. We show the advantages of deep learning-based approaches over compressed sensing approaches in terms of improved image quality and suppressed artifacts. We will also discuss several challenges that are encountered during learning covering the design of a training database, deep network architectures and image quality measures.

Computer Aided Diagnosis
Dinggang Shen
Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. In this talk, I will introduce the fundamentals of deep learning methods and their applications in computer-aided diagnosis for Alzheimer's Disease (AD), breast cancer, lung cancer, and brain tumors.

Introduction by Discussion Leaders - video not available
Adrienne Campbell-Washburn
A panel discussion regarding the role of machine learning in clinical MRI
Introduction by Discussion Leaders - video not available
Thijs Dhollander
A panel discussion on the challenges and opportunities for machine learning in daily clinical practice.
Radiologist vs. Computer: Panel Discussion - video not available
Vikas Gulani
Radiologist vs. Computer: Panel Discussion - video not available
Tim Leiner
Radiologist vs. Computer: Panel Discussion - video not available
Susie Huang
Panel discussion on machine learning
Adjournment & Meet the Teachers



The International Society for Magnetic Resonance in Medicine is accredited by the Accreditation Council for
Continuing Medical Education to provide continuing medical education for physicians.