Weekend Educational Session
Machine Learning: Everything You Want to Know
Back to Program-at-a-Glance
Session Topic: Machine Learning: Everything You Want to Know
Session Sub-Topic: Machine Learning: Everything You Want to Know
Weekend Course
ORGANIZERS: Demian Wassermann, Florian Knoll, Daniel Rueckert
| Saturday Parallel 2 Live Q&A | Saturday, 8 August 2020, 16:00 - 16:30 UTC | Moderators: Florian Knoll & Jakob Meineke |
Skill Level: Basic to Advanced
Session Number: WE-08
Overview
In this session, we will cover the theoretical foundation of machine learning, provide practical guidelines how to get started, and then cover specific applications in MR imaging both from a technical and clinical point of view.
Target Audience
Researchers and clinicians interested in learning more about what machine learning is, how it works, how to get started, and what it can and (at least currently) cannot do.
Educational Objectives
As a result of attending this course, participants should be able to:
- Define the theoretical foundations of machine learning;
- Choose the appropriate (deep) model for their particular research question;
- Describe example applications in MRI where machine learning can be used;
- Recognize limitations and challenges of using machine learning in emerging applications; and
- Discuss the potential clinical impact of machine learning on field of MRI.
 |
Basic Introduction to Machine Learning
Jo Schlemper
In this talk, we will discuss the basics of machine learning: a supervised learning framework and neural networks. In particular, we will cover the following topics, focussing on the intuition behind them: (1) Types of machine learning (2) Neural networks, from perceptron, MLP to deep neural networks (3) Training, overfitting and regularization (4) Practical considerations for applying ML (5) Challenges of deep learning. |
|
| When Does It Work, When Does It Break Down? Analyzing the Theoretical Properties of Machine Learning
Thomas Pock
|
||
| Which Deep Learning Model Will Work for Me? Practical Considerations & Getting Started
Matthew Muckley
|
||
| Applications of Machine Learning: Image Processing & Interpretation
Henkjan Huisman
|
||
| Applications of Machine Learning: Data Acquisition & Image Reconstruction
Shanshan Wang, Xin Liu, Hairong Zheng
Machine learning, especially deep learning, has shown great potential in accelerating MR imaging lately. To accelerate MR imaging with deep learning, the sampling trajectories can be Cartesian or Non-Cartesian subsampling patterns. While the reconstruction methods can be roughly categorized into end-to-end data-driven learning reconstruction methods and model based unrolled iterative learning reconstruction methods. This educational lecture will briefly go through these methods and provide a starting point for researchers interested in this field.
|
||
| Killer Applications: Where Will Machine Learning Make a Substantial Clinical Impact?
Greg Zaharchuk
|
Watch the Video
Back to Top