Automated Classification of Left Ventricular Hypertrophy on Cardiac MRI

Left ventricular hypertrophy is an independent predictor of coronary artery disease, stroke, and heart failure. Our aim was to detect LVH cardiac magnetic resonance (CMR) scans with automatic methods. We developed an ensemble model based on a three-dimensional version of ResNet. The input of the net...

Full description

Bibliographic Details
Main Authors: Adam Budai, Ferenc Imre Suhai, Kristof Csorba, Zsofia Dohy, Liliana Szabo, Bela Merkely, Hajnalka Vago
Format: Article
Language:English
Published: MDPI AG 2022-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/12/9/4151
_version_ 1827673359310127104
author Adam Budai
Ferenc Imre Suhai
Kristof Csorba
Zsofia Dohy
Liliana Szabo
Bela Merkely
Hajnalka Vago
author_facet Adam Budai
Ferenc Imre Suhai
Kristof Csorba
Zsofia Dohy
Liliana Szabo
Bela Merkely
Hajnalka Vago
author_sort Adam Budai
collection DOAJ
description Left ventricular hypertrophy is an independent predictor of coronary artery disease, stroke, and heart failure. Our aim was to detect LVH cardiac magnetic resonance (CMR) scans with automatic methods. We developed an ensemble model based on a three-dimensional version of ResNet. The input of the network included short-axis and long-axis images. We also introduced a standardization methodology to unify the input images for noise reduction. The output of the network is the decision whether the patient has hypertrophy or not. We included 428 patients (mean age: 49 ± 18 years, 262 males) with LVH (346 hypertrophic cardiomyopathy, 45 cardiac amyloidosis, 11 Anderson–Fabry disease, 16 endomyocardial fibrosis, 10 aortic stenosis). Our control group consisted of 234 healthy subjects (mean age: 35 ± 15 years; 126 males) without any known cardiovascular diseases. The developed machine-learning-based model achieved a 92% F1-score and 97% recall on the hold-out dataset, which is comparable to the medical experts. Experiments showed that the standardization method was able to significantly boost the performance of the algorithm. The algorithm could improve the diagnostic accuracy, and it could open a new door to AI applications in CMR.
first_indexed 2024-03-10T04:22:44Z
format Article
id doaj.art-4a2f93e2bd4e4e48b8e6947b3f9ffb12
institution Directory Open Access Journal
issn 2076-3417
language English
last_indexed 2024-03-10T04:22:44Z
publishDate 2022-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj.art-4a2f93e2bd4e4e48b8e6947b3f9ffb122023-11-23T07:44:57ZengMDPI AGApplied Sciences2076-34172022-04-01129415110.3390/app12094151Automated Classification of Left Ventricular Hypertrophy on Cardiac MRIAdam Budai0Ferenc Imre Suhai1Kristof Csorba2Zsofia Dohy3Liliana Szabo4Bela Merkely5Hajnalka Vago6Department of Automation and Applied Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, H-1111 Budapest, HungaryHeart and Vascular Center, Semmelweis University, H-1122 Budapest, HungaryDepartment of Automation and Applied Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, H-1111 Budapest, HungaryHeart and Vascular Center, Semmelweis University, H-1122 Budapest, HungaryHeart and Vascular Center, Semmelweis University, H-1122 Budapest, HungaryHeart and Vascular Center, Semmelweis University, H-1122 Budapest, HungaryHeart and Vascular Center, Semmelweis University, H-1122 Budapest, HungaryLeft ventricular hypertrophy is an independent predictor of coronary artery disease, stroke, and heart failure. Our aim was to detect LVH cardiac magnetic resonance (CMR) scans with automatic methods. We developed an ensemble model based on a three-dimensional version of ResNet. The input of the network included short-axis and long-axis images. We also introduced a standardization methodology to unify the input images for noise reduction. The output of the network is the decision whether the patient has hypertrophy or not. We included 428 patients (mean age: 49 ± 18 years, 262 males) with LVH (346 hypertrophic cardiomyopathy, 45 cardiac amyloidosis, 11 Anderson–Fabry disease, 16 endomyocardial fibrosis, 10 aortic stenosis). Our control group consisted of 234 healthy subjects (mean age: 35 ± 15 years; 126 males) without any known cardiovascular diseases. The developed machine-learning-based model achieved a 92% F1-score and 97% recall on the hold-out dataset, which is comparable to the medical experts. Experiments showed that the standardization method was able to significantly boost the performance of the algorithm. The algorithm could improve the diagnostic accuracy, and it could open a new door to AI applications in CMR.https://www.mdpi.com/2076-3417/12/9/4151classificationleft ventricular hypertrophyCMRmachine learning
spellingShingle Adam Budai
Ferenc Imre Suhai
Kristof Csorba
Zsofia Dohy
Liliana Szabo
Bela Merkely
Hajnalka Vago
Automated Classification of Left Ventricular Hypertrophy on Cardiac MRI
Applied Sciences
classification
left ventricular hypertrophy
CMR
machine learning
title Automated Classification of Left Ventricular Hypertrophy on Cardiac MRI
title_full Automated Classification of Left Ventricular Hypertrophy on Cardiac MRI
title_fullStr Automated Classification of Left Ventricular Hypertrophy on Cardiac MRI
title_full_unstemmed Automated Classification of Left Ventricular Hypertrophy on Cardiac MRI
title_short Automated Classification of Left Ventricular Hypertrophy on Cardiac MRI
title_sort automated classification of left ventricular hypertrophy on cardiac mri
topic classification
left ventricular hypertrophy
CMR
machine learning
url https://www.mdpi.com/2076-3417/12/9/4151
work_keys_str_mv AT adambudai automatedclassificationofleftventricularhypertrophyoncardiacmri
AT ferencimresuhai automatedclassificationofleftventricularhypertrophyoncardiacmri
AT kristofcsorba automatedclassificationofleftventricularhypertrophyoncardiacmri
AT zsofiadohy automatedclassificationofleftventricularhypertrophyoncardiacmri
AT lilianaszabo automatedclassificationofleftventricularhypertrophyoncardiacmri
AT belamerkely automatedclassificationofleftventricularhypertrophyoncardiacmri
AT hajnalkavago automatedclassificationofleftventricularhypertrophyoncardiacmri