SCMR/ISMRM Co-Provided Workshop
February 6-7, 2019
|
|
|
Claudia Prieto, PhD
King's College London Program Co-Chair |
Frederick H. Epstein, PhD
University of Virginia Program Co-Chair |
Overview
“The Emerging Role of Machine Learning in Cardiovascular Magnetic Resonance Imaging”
Cardiovascular imaging technologies such as cardiac MRI are continually developing to increase their capacity to provide richer and more quantitative diagnostic information by accelerating and simplifying image acquisition, further improving reconstruction and motion compensation techniques and processing ever larger quantities of data. Modern computational methods, developed in the field of machine learning offer new capabilities to process the growing volume of imaging data and to facilitate complex analyses, which may result in greater automation of time-consuming tasks that are commonly performed by humans. Moreover, machine learning capabilities may help to overcome some of the unique challenges particular to cardiac MRI including acquisition planning, data acquisition speed, and motion compensation. In addition, machine learning approaches employed to analyze large imaging databases including patient records may lead to new clinical insights and generate novel hypotheses to advance cardiovascular science. In summary, machine learning methods are very promising techniques that may significantly improve both scientific research and clinical workflow in the field of cardiovascular MRI.
This workshop would try to integrate a deep review on machine learning with a focus on cardiovascular MR imaging to discuss major developments in acquisition, reconstruction, post-processing and clinical applications. Possible topics of the sessions (subject to changes) could be:
1. Cardiac Motion and Mechanics
2. Experimental and Clinical Validation
3. Image Reconstruction and Accelerated Imaging
4. Population Science
5. Post-Processing and Analysis
Cardiovascular imaging technologies such as cardiac MRI are continually developing to increase their capacity to provide richer and more quantitative diagnostic information by accelerating and simplifying image acquisition, further improving reconstruction and motion compensation techniques and processing ever larger quantities of data. Modern computational methods, developed in the field of machine learning offer new capabilities to process the growing volume of imaging data and to facilitate complex analyses, which may result in greater automation of time-consuming tasks that are commonly performed by humans. Moreover, machine learning capabilities may help to overcome some of the unique challenges particular to cardiac MRI including acquisition planning, data acquisition speed, and motion compensation. In addition, machine learning approaches employed to analyze large imaging databases including patient records may lead to new clinical insights and generate novel hypotheses to advance cardiovascular science. In summary, machine learning methods are very promising techniques that may significantly improve both scientific research and clinical workflow in the field of cardiovascular MRI.
This workshop would try to integrate a deep review on machine learning with a focus on cardiovascular MR imaging to discuss major developments in acquisition, reconstruction, post-processing and clinical applications. Possible topics of the sessions (subject to changes) could be:
1. Cardiac Motion and Mechanics
2. Experimental and Clinical Validation
3. Image Reconstruction and Accelerated Imaging
4. Population Science
5. Post-Processing and Analysis
Program
The SCMR is pleased to announce the launching of a new online program here. Session and exhibitor information can be searched by a variety of methods, including date, time, presenter, booth number, and much more. Attendees can bookmark sessions and create personal plans for an integrated schedule onsite.
Registration
Online registration is now open. The SCMR Headquarters strongly encourages you to register in advance to ensure you will have an expeditious check-in when you arrive at the workshop.
If you are an ISMRM Member, please contact ISMRM at info@ismrm.org to receive the member discount code prior to registering.
If you are an ISMRM Member, please contact ISMRM at info@ismrm.org to receive the member discount code prior to registering.