Machine learning methods and applications have proliferated in recent years and with this expansion has come a range of powerful software platforms enabling users to rapidly prototype solutions for problems in their field. These software platforms have now developed to the point where they can be used rather like a ‘black box’, with relatively little understanding of the underlying principles, the importance of various parameters (of which there are many), model design choices, and the meaning of the output.…
The main goal of this lunchtime tutorial is to introduce the key concepts, principles and nomenclature of machine learning for those who are new to it and for those who ‘dabble’ in it but would like to gain a more thorough foundation. A secondary goal is to demonstrate how machine learning intersects with the medical imaging field as a computational approach to problem solving. This will be illustrated using case studies, with time allocated for discussion of some of the exciting opportunities that exist going forward and Q&A. We highly recommend this tutorial as a ‘primer’ to enhance your appreciation of the many machine learning approaches presented in the poster and oral sessions of the Medical Imaging Conference.
Organizers:
Steven Meikle, University of Sydney, Australia
Andre Kyme, University of Sydney, Australia
Speaker:
Dr Jingya Wang, University of Sydney, Australia
latest news
Dec 29 - Winners of the $200 Amazon Gift Vouchers
1. Martin Nikl, Institute of Physics, Academy of Sciences of the Czech Republic
2. Laura Stonehill, Los Alamos National Laboratory
Oct 01, 2019 - Conference Records are available
Oct 25 - Conference app is now available
Oct 24 - Conference Record upload is now available
Oct 23 - Presentation upload is now available
Sept 19 - Exhibit Guide Book published
Sept 13 - Guide to Conference Records
Sept 10 - All Grants are now announced
Aug 09 - Notes for Exhibitors
Aug 03 - Online Program available
Jul 05 - Registration is open
Exhibit Guide Book Download (3.2 MB)
Conference Poster Low-Res (0.5 MB) High-Res (15.5 MB)