Machine learning of three-dimensional right ventricular motion enables outcome prediction in pulmonary hypertension: a cardiac MR imaging study
File(s)radiol.2016161315.pdf (1.7 MB)
Published version
Author(s)
Type
Journal Article
Abstract
Purpose: To determine if patient survival and mechanisms of right ventricular (RV) failure in pulmonary hypertension (PH) could be predicted usin g supervised machine learning of three dimensional patterns of systolic cardiac motion. Materials and methods: The study was approved by a research ethics committ ee and participants gave written informed consent. 256 patients (143 females, mean a ge 63 ± 17) with newly diagnosed PH underwent cardiac MR imaging, right heart catheteri zation (RHC) and six minute walk testing (6MWT) with a median follow up of 4.0 years . Semi automated segmentation of short axis cine images was used to create a three dimensi onal model of right ventricular motion. Supervised principal components analysis identified patterns of systolic motion which were most strongly predictive of survival. Survival pred iction was assessed by the difference in median survival time and the area under the curve ( AUC) using time dependent receiver operator characteristic for one year survival. Results: At the end of follow up 33% (93/256) died and one u nderwent lung transplantation. Poor outcome was predicted by a loss of effective contra ction in the septum and freewall coupled with reduced basal longitudinal motion. When added to conventional imaging, hemodynamic, functional and clinical markers, three dimensional cardiac motion improved survival prediction (area under the curve 0.73 vs 0.60, p<0. 001) and provided greater differentiation by difference in median survival time between high and low risk groups (13.8 vs 10.7 years, p<0.001). Conclusion: Three dimensional motion modeling with machine lear ning approaches reveal the adaptations in function that occur early in right heart failure and independently predict outcomes in newly diagnosed PH patients.
Date Issued
2017-05-01
Online Publication Date
2017-05-01
Date Acceptance
2016-11-16
ISSN
1527-1315
Publisher
Radiological Society of North America (RSNA)
Start Page
381
End Page
390
Journal / Book Title
Radiology
Volume
283
Issue
2
Source Database
manual-entry
Sponsor
British Heart Foundation
GlaxoSmithKline Services Unlimited
National Institute for Health Research
Engineering & Physical Science Research Council (EPSRC)
British Heart Foundation
British Heart Foundation
Wellcome Trust
Grant Number
PG/12/27/29489
COL011953
RDB02 79560
EP/K030523/1
SP/10/10/28431
FS/15/59/31839
Subjects
Science & Technology
Life Sciences & Biomedicine
Radiology, Nuclear Medicine & Medical Imaging
SURVIVAL
HEART
SEGMENTATION
MECHANICS
ATLASES
IMAGES
SHAPE
Aged
Female
Heart Ventricles
Humans
Hypertension, Pulmonary
Image Interpretation, Computer-Assisted
Imaging, Three-Dimensional
Machine Learning
Magnetic Resonance Imaging, Cine
Male
Middle Aged
Pattern Recognition, Automated
Reproducibility of Results
Sensitivity and Specificity
Stroke Volume
Ventricular Dysfunction, Right
Heart Ventricles
Humans
Hypertension, Pulmonary
Ventricular Dysfunction, Right
Image Interpretation, Computer-Assisted
Imaging, Three-Dimensional
Magnetic Resonance Imaging, Cine
Stroke Volume
Sensitivity and Specificity
Reproducibility of Results
Pattern Recognition, Automated
Aged
Middle Aged
Female
Male
Machine Learning
11 Medical and Health Sciences
Nuclear Medicine & Medical Imaging
Publication Status
Published
Date Publish Online
2017-01-16