Machine learning in cardiovascular magnetic resonance: basic concepts and applications
Abstract Machine learning (ML) is making a dramatic impact on cardiovascular magnetic resonance (CMR) in many ways. This review seeks to highlight the major areas in CMR where ML, and deep learning in particular, can assist clinicians and engineers in improving imaging efficiency, quality, image ana...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2019-10-01
|
Series: | Journal of Cardiovascular Magnetic Resonance |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12968-019-0575-y |
id |
doaj-50fded3c0a6f4833a5d28092b3bf1e51 |
---|---|
record_format |
Article |
spelling |
doaj-50fded3c0a6f4833a5d28092b3bf1e512020-11-25T04:00:45ZengBMCJournal of Cardiovascular Magnetic Resonance1532-429X2019-10-0121111410.1186/s12968-019-0575-yMachine learning in cardiovascular magnetic resonance: basic concepts and applicationsTim Leiner0Daniel Rueckert1Avan Suinesiaputra2Bettina Baeßler3Reza Nezafat4Ivana Išgum5Alistair A. Young6Department of Radiology | E.01.132, Utrecht University Medical CenterBiomedical Image Analysis Group, Department of Computing, Imperial CollegeDepartment of Anatomy and Medical Imaging, University of AucklandDepartment of Radiology, University Hospital of CologneDepartment of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Centre, Harvard Medical SchoolImage Sciences Institute, University Medical Center UtrechtDepartment of Anatomy and Medical Imaging, University of AucklandAbstract Machine learning (ML) is making a dramatic impact on cardiovascular magnetic resonance (CMR) in many ways. This review seeks to highlight the major areas in CMR where ML, and deep learning in particular, can assist clinicians and engineers in improving imaging efficiency, quality, image analysis and interpretation, as well as patient evaluation. We discuss recent developments in the field of ML relevant to CMR in the areas of image acquisition & reconstruction, image analysis, diagnostic evaluation and derivation of prognostic information. To date, the main impact of ML in CMR has been to significantly reduce the time required for image segmentation and analysis. Accurate and reproducible fully automated quantification of left and right ventricular mass and volume is now available in commercial products. Active research areas include reduction of image acquisition and reconstruction time, improving spatial and temporal resolution, and analysis of perfusion and myocardial mapping. Although large cohort studies are providing valuable data sets for ML training, care must be taken in extending applications to specific patient groups. Since ML algorithms can fail in unpredictable ways, it is important to mitigate this by open source publication of computational processes and datasets. Furthermore, controlled trials are needed to evaluate methods across multiple centers and patient groups.http://link.springer.com/article/10.1186/s12968-019-0575-yCardiovascular magnetic resonanceMachine learningDeep learningRadiomics |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tim Leiner Daniel Rueckert Avan Suinesiaputra Bettina Baeßler Reza Nezafat Ivana Išgum Alistair A. Young |
spellingShingle |
Tim Leiner Daniel Rueckert Avan Suinesiaputra Bettina Baeßler Reza Nezafat Ivana Išgum Alistair A. Young Machine learning in cardiovascular magnetic resonance: basic concepts and applications Journal of Cardiovascular Magnetic Resonance Cardiovascular magnetic resonance Machine learning Deep learning Radiomics |
author_facet |
Tim Leiner Daniel Rueckert Avan Suinesiaputra Bettina Baeßler Reza Nezafat Ivana Išgum Alistair A. Young |
author_sort |
Tim Leiner |
title |
Machine learning in cardiovascular magnetic resonance: basic concepts and applications |
title_short |
Machine learning in cardiovascular magnetic resonance: basic concepts and applications |
title_full |
Machine learning in cardiovascular magnetic resonance: basic concepts and applications |
title_fullStr |
Machine learning in cardiovascular magnetic resonance: basic concepts and applications |
title_full_unstemmed |
Machine learning in cardiovascular magnetic resonance: basic concepts and applications |
title_sort |
machine learning in cardiovascular magnetic resonance: basic concepts and applications |
publisher |
BMC |
series |
Journal of Cardiovascular Magnetic Resonance |
issn |
1532-429X |
publishDate |
2019-10-01 |
description |
Abstract Machine learning (ML) is making a dramatic impact on cardiovascular magnetic resonance (CMR) in many ways. This review seeks to highlight the major areas in CMR where ML, and deep learning in particular, can assist clinicians and engineers in improving imaging efficiency, quality, image analysis and interpretation, as well as patient evaluation. We discuss recent developments in the field of ML relevant to CMR in the areas of image acquisition & reconstruction, image analysis, diagnostic evaluation and derivation of prognostic information. To date, the main impact of ML in CMR has been to significantly reduce the time required for image segmentation and analysis. Accurate and reproducible fully automated quantification of left and right ventricular mass and volume is now available in commercial products. Active research areas include reduction of image acquisition and reconstruction time, improving spatial and temporal resolution, and analysis of perfusion and myocardial mapping. Although large cohort studies are providing valuable data sets for ML training, care must be taken in extending applications to specific patient groups. Since ML algorithms can fail in unpredictable ways, it is important to mitigate this by open source publication of computational processes and datasets. Furthermore, controlled trials are needed to evaluate methods across multiple centers and patient groups. |
topic |
Cardiovascular magnetic resonance Machine learning Deep learning Radiomics |
url |
http://link.springer.com/article/10.1186/s12968-019-0575-y |
work_keys_str_mv |
AT timleiner machinelearningincardiovascularmagneticresonancebasicconceptsandapplications AT danielrueckert machinelearningincardiovascularmagneticresonancebasicconceptsandapplications AT avansuinesiaputra machinelearningincardiovascularmagneticresonancebasicconceptsandapplications AT bettinabaeßler machinelearningincardiovascularmagneticresonancebasicconceptsandapplications AT rezanezafat machinelearningincardiovascularmagneticresonancebasicconceptsandapplications AT ivanaisgum machinelearningincardiovascularmagneticresonancebasicconceptsandapplications AT alistairayoung machinelearningincardiovascularmagneticresonancebasicconceptsandapplications |
_version_ |
1724449447691157504 |