Radiomics Detection of Pulmonary Hypertension via Texture-Based Assessments of Cardiac MRI: A Machine-Learning Model Comparison-Cardiac MRI Radiomics in Pulmonary Hypertension

Sarv Priya; Tanya Aggarwal; Caitlin Ward; Girish Bathla; Mathews Jacob; Alicia Gerke; Eric A Hoffman; Prashant Nagpal

doi:10.3390/jcm10091921

Back

Radiomics Detection of Pulmonary Hypertension via Texture-Based Assessments of Cardiac MRI: A Machine-Learning Model Comparison-Cardiac MRI Radiomics in Pulmonary Hypertension

Journal article

Open access

Peer reviewed

Radiomics Detection of Pulmonary Hypertension via Texture-Based Assessments of Cardiac MRI: A Machine-Learning Model Comparison-Cardiac MRI Radiomics in Pulmonary Hypertension

Sarv Priya, Tanya Aggarwal, Caitlin Ward, Girish Bathla, Mathews Jacob, Alicia Gerke, Eric A Hoffman and Prashant Nagpal

Journal of clinical medicine, Vol.10(9), p.1921

04/28/2021

DOI: 10.3390/jcm10091921

PMCID: PMC8125238

PMID: 33925262

Files and links (1)

url

https://doi.org/10.3390/jcm10091921View

Published (Version of record) Open Access

Abstract

The role of reliable, non-invasive imaging-based recognition of pulmonary hypertension (PH) remains a diagnostic challenge. The aim of the current pilot radiomics study was to assess the diagnostic performance of cardiac MRI (cMRI)-based texture features to accurately predict PH. The study involved IRB-approved retrospective analysis of cMRIs from 72 patients (42 PH and 30 healthy controls) for the primary analysis. A subgroup analysis was performed including patients from the PH group with left ventricle ejection fraction ≥ 50%. Texture features were generated from mid-left ventricle myocardium using balanced steady-state free precession (bSSFP) cine short-axis imaging. Forty-five different combinations of classifier models and feature selection techniques were evaluated. Model performance was assessed using receiver operating characteristic curves. A multilayer perceptron model fitting using full feature sets was the best classifier model for both the primary analysis (AUC 0.862, accuracy 78%) and the subgroup analysis (AUC 0.918, accuracy 80%). Model performance demonstrated considerable variation between the models (AUC 0.523-0.918) based on the chosen model-feature selection combination. Cardiac MRI-based radiomics recognition of PH using texture features is feasible, even with preserved left ventricular ejection fractions.

Machine Learning

radiomics

cardiac MRI

pulmonary hypertension

texture

Details

Title: Subtitle: Radiomics Detection of Pulmonary Hypertension via Texture-Based Assessments of Cardiac MRI: A Machine-Learning Model Comparison-Cardiac MRI Radiomics in Pulmonary Hypertension
Creators: Sarv Priya - Department of Radiology, University of Iowa Carver College of Medicine, Iowa City, IA 52242, USA
Tanya Aggarwal - Department of Family Medicine, University of Iowa Carver College of Medicine, Iowa City, IA 52242, USA
Caitlin Ward - Department of Biostatistics, University of Iowa College of Public Health, Iowa City, IA 52242, USA
Girish Bathla - Department of Radiology, University of Iowa Carver College of Medicine, Iowa City, IA 52242, USA
Mathews Jacob - Department of Electrical Engineering, University of Iowa College of Engineering, Iowa City, IA 52242, USA
Alicia Gerke - Department of Pulmonary Medicine, University of Iowa Carver College of Medicine, Iowa City, IA 52242, USA
Eric A Hoffman - Roy J. Carver Department of Biomedical Engineering, University of Iowa College of Engineering, Iowa City, IA 52242, USA
Prashant Nagpal - Department of Radiology, University of Iowa Carver College of Medicine, Iowa City, IA 52242, USA
Resource Type: Journal article
Publication Details: Journal of clinical medicine, Vol.10(9), p.1921
DOI: 10.3390/jcm10091921
PMID: 33925262
PMCID: PMC8125238
NLM abbreviation: J Clin Med
ISSN: 2077-0383
eISSN: 2077-0383
Publisher: Switzerland
Grant note: (Grant/program #: 53380630; Fund: 243) / University of Iowa-Carver College of Medicine Small Grant Program
Language: English
Date published: 04/28/2021
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Pulmonary, Critical Care, and Occupational Medicine; Iowa Neuroscience Institute; Radiation Oncology; Nursing; Internal Medicine
Record Identifier: 9984071613802771

Metrics

13 Record Views

9 Times Cited - Web of Science