Cargando…

Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance

Left Ventricular (LV) Non-compaction (LVNC), Hypertrophic Cardiomyopathy (HCM), and Dilated Cardiomyopathy (DCM) share morphological and functional traits that increase the diagnosis complexity. Additional clinical information, besides imaging data such as cardiovascular magnetic resonance (CMR), is...

Descripción completa

Detalles Bibliográficos
Autores principales: Izquierdo, Cristian, Casas, Guillem, Martin-Isla, Carlos, Campello, Victor M., Guala, Andrea, Gkontra, Polyxeni, Rodríguez-Palomares, Jose F., Lekadir, Karim
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8586199/
https://www.ncbi.nlm.nih.gov/pubmed/34778415
http://dx.doi.org/10.3389/fcvm.2021.764312
_version_ 1784597844272873472
author Izquierdo, Cristian
Casas, Guillem
Martin-Isla, Carlos
Campello, Victor M.
Guala, Andrea
Gkontra, Polyxeni
Rodríguez-Palomares, Jose F.
Lekadir, Karim
author_facet Izquierdo, Cristian
Casas, Guillem
Martin-Isla, Carlos
Campello, Victor M.
Guala, Andrea
Gkontra, Polyxeni
Rodríguez-Palomares, Jose F.
Lekadir, Karim
author_sort Izquierdo, Cristian
collection PubMed
description Left Ventricular (LV) Non-compaction (LVNC), Hypertrophic Cardiomyopathy (HCM), and Dilated Cardiomyopathy (DCM) share morphological and functional traits that increase the diagnosis complexity. Additional clinical information, besides imaging data such as cardiovascular magnetic resonance (CMR), is usually required to reach a definitive diagnosis, including electrocardiography (ECG), family history, and genetics. Alternatively, indices of hypertrabeculation have been introduced, but they require tedious and time-consuming delineations of the trabeculae on the CMR images. In this paper, we propose a radiomics approach to automatically encode differences in the underlying shape, gray-scale and textural information in the myocardium and its trabeculae, which may enhance the capacity to differentiate between these overlapping conditions. A total of 118 subjects, including 35 patients with LVNC, 25 with HCM, 37 with DCM, as well as 21 healthy volunteers (NOR), underwent CMR imaging. A comprehensive radiomics characterization was applied to LV short-axis images to quantify shape, first-order, co-occurrence matrix, run-length matrix, and local binary patterns. Conventional CMR indices (LV volumes, mass, wall thickness, LV ejection fraction—LVEF—), as well as hypertrabeculation indices by Petersen and Jacquier, were also analyzed. State-of-the-art Machine Learning (ML) models (one-vs.-rest Support Vector Machine—SVM—, Logistic Regression—LR—, and Random Forest Classifier—RF—) were used for one-vs.-rest classification tasks. The use of radiomics models for the automated diagnosis of LVNC, HCM, and DCM resulted in excellent one-vs.-rest ROC-AUC values of 0.95 while generating these results without the need for the delineation of the trabeculae. First-order and texture features resulted to be among the most discriminative features in the obtained radiomics signatures, indicating their added value for quantifying relevant tissue patterns in cardiomyopathy differential diagnosis.
format Online
Article
Text
id pubmed-8586199
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-85861992021-11-13 Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance Izquierdo, Cristian Casas, Guillem Martin-Isla, Carlos Campello, Victor M. Guala, Andrea Gkontra, Polyxeni Rodríguez-Palomares, Jose F. Lekadir, Karim Front Cardiovasc Med Cardiovascular Medicine Left Ventricular (LV) Non-compaction (LVNC), Hypertrophic Cardiomyopathy (HCM), and Dilated Cardiomyopathy (DCM) share morphological and functional traits that increase the diagnosis complexity. Additional clinical information, besides imaging data such as cardiovascular magnetic resonance (CMR), is usually required to reach a definitive diagnosis, including electrocardiography (ECG), family history, and genetics. Alternatively, indices of hypertrabeculation have been introduced, but they require tedious and time-consuming delineations of the trabeculae on the CMR images. In this paper, we propose a radiomics approach to automatically encode differences in the underlying shape, gray-scale and textural information in the myocardium and its trabeculae, which may enhance the capacity to differentiate between these overlapping conditions. A total of 118 subjects, including 35 patients with LVNC, 25 with HCM, 37 with DCM, as well as 21 healthy volunteers (NOR), underwent CMR imaging. A comprehensive radiomics characterization was applied to LV short-axis images to quantify shape, first-order, co-occurrence matrix, run-length matrix, and local binary patterns. Conventional CMR indices (LV volumes, mass, wall thickness, LV ejection fraction—LVEF—), as well as hypertrabeculation indices by Petersen and Jacquier, were also analyzed. State-of-the-art Machine Learning (ML) models (one-vs.-rest Support Vector Machine—SVM—, Logistic Regression—LR—, and Random Forest Classifier—RF—) were used for one-vs.-rest classification tasks. The use of radiomics models for the automated diagnosis of LVNC, HCM, and DCM resulted in excellent one-vs.-rest ROC-AUC values of 0.95 while generating these results without the need for the delineation of the trabeculae. First-order and texture features resulted to be among the most discriminative features in the obtained radiomics signatures, indicating their added value for quantifying relevant tissue patterns in cardiomyopathy differential diagnosis. Frontiers Media S.A. 2021-10-29 /pmc/articles/PMC8586199/ /pubmed/34778415 http://dx.doi.org/10.3389/fcvm.2021.764312 Text en Copyright © 2021 Izquierdo, Casas, Martin-Isla, Campello, Guala, Gkontra, Rodríguez-Palomares and Lekadir. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Cardiovascular Medicine
Izquierdo, Cristian
Casas, Guillem
Martin-Isla, Carlos
Campello, Victor M.
Guala, Andrea
Gkontra, Polyxeni
Rodríguez-Palomares, Jose F.
Lekadir, Karim
Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance
title Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance
title_full Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance
title_fullStr Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance
title_full_unstemmed Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance
title_short Radiomics-Based Classification of Left Ventricular Non-compaction, Hypertrophic Cardiomyopathy, and Dilated Cardiomyopathy in Cardiovascular Magnetic Resonance
title_sort radiomics-based classification of left ventricular non-compaction, hypertrophic cardiomyopathy, and dilated cardiomyopathy in cardiovascular magnetic resonance
topic Cardiovascular Medicine
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8586199/
https://www.ncbi.nlm.nih.gov/pubmed/34778415
http://dx.doi.org/10.3389/fcvm.2021.764312
work_keys_str_mv AT izquierdocristian radiomicsbasedclassificationofleftventricularnoncompactionhypertrophiccardiomyopathyanddilatedcardiomyopathyincardiovascularmagneticresonance
AT casasguillem radiomicsbasedclassificationofleftventricularnoncompactionhypertrophiccardiomyopathyanddilatedcardiomyopathyincardiovascularmagneticresonance
AT martinislacarlos radiomicsbasedclassificationofleftventricularnoncompactionhypertrophiccardiomyopathyanddilatedcardiomyopathyincardiovascularmagneticresonance
AT campellovictorm radiomicsbasedclassificationofleftventricularnoncompactionhypertrophiccardiomyopathyanddilatedcardiomyopathyincardiovascularmagneticresonance
AT gualaandrea radiomicsbasedclassificationofleftventricularnoncompactionhypertrophiccardiomyopathyanddilatedcardiomyopathyincardiovascularmagneticresonance
AT gkontrapolyxeni radiomicsbasedclassificationofleftventricularnoncompactionhypertrophiccardiomyopathyanddilatedcardiomyopathyincardiovascularmagneticresonance
AT rodriguezpalomaresjosef radiomicsbasedclassificationofleftventricularnoncompactionhypertrophiccardiomyopathyanddilatedcardiomyopathyincardiovascularmagneticresonance
AT lekadirkarim radiomicsbasedclassificationofleftventricularnoncompactionhypertrophiccardiomyopathyanddilatedcardiomyopathyincardiovascularmagneticresonance