Prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with Takotsubo syndrome: a machine learning based proof-of-principle approach
Abstract Cardiac magnetic resonance (CMR) imaging has become an important technique for non-invasive diagnosis of takotsubo syndrome (TTS). The long-term prognostic value of CMR imaging in TTS has not been fully elucidated yet. This study sought to evaluate the prognostic value of texture analysis (...
Main Authors: | , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2020-11-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-020-76432-4 |
id |
doaj-8b9558fcbb414f078925eee1ae9987cc |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Manoj Mannil Ken Kato Robert Manka Jochen von Spiczak Benjamin Peters Victoria L. Cammann Christoph Kaiser Stefan Osswald Thanh Ha Nguyen John D. Horowitz Hugo A. Katus Frank Ruschitzka Jelena R. Ghadri Hatem Alkadhi Christian Templin |
spellingShingle |
Manoj Mannil Ken Kato Robert Manka Jochen von Spiczak Benjamin Peters Victoria L. Cammann Christoph Kaiser Stefan Osswald Thanh Ha Nguyen John D. Horowitz Hugo A. Katus Frank Ruschitzka Jelena R. Ghadri Hatem Alkadhi Christian Templin Prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with Takotsubo syndrome: a machine learning based proof-of-principle approach Scientific Reports |
author_facet |
Manoj Mannil Ken Kato Robert Manka Jochen von Spiczak Benjamin Peters Victoria L. Cammann Christoph Kaiser Stefan Osswald Thanh Ha Nguyen John D. Horowitz Hugo A. Katus Frank Ruschitzka Jelena R. Ghadri Hatem Alkadhi Christian Templin |
author_sort |
Manoj Mannil |
title |
Prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with Takotsubo syndrome: a machine learning based proof-of-principle approach |
title_short |
Prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with Takotsubo syndrome: a machine learning based proof-of-principle approach |
title_full |
Prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with Takotsubo syndrome: a machine learning based proof-of-principle approach |
title_fullStr |
Prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with Takotsubo syndrome: a machine learning based proof-of-principle approach |
title_full_unstemmed |
Prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with Takotsubo syndrome: a machine learning based proof-of-principle approach |
title_sort |
prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with takotsubo syndrome: a machine learning based proof-of-principle approach |
publisher |
Nature Publishing Group |
series |
Scientific Reports |
issn |
2045-2322 |
publishDate |
2020-11-01 |
description |
Abstract Cardiac magnetic resonance (CMR) imaging has become an important technique for non-invasive diagnosis of takotsubo syndrome (TTS). The long-term prognostic value of CMR imaging in TTS has not been fully elucidated yet. This study sought to evaluate the prognostic value of texture analysis (TA) based on CMR images in patients with TTS using machine learning. In this multicenter study (InterTAK Registry), we investigated CMR imaging data of 58 patients (56 women, mean age 68 ± 12 years) with TTS. CMR imaging was performed in the acute to subacute phase (median time after symptom onset 4 days) of TTS. TA of the left ventricle was performed using free-hand regions-of-interest in short axis late gadolinium-enhanced and on T2-weighted (T2w) images. A total of 608 TA features adding the parameters age, gender, and body mass index were included. Dimension reduction was performed removing TA features with poor intra-class correlation coefficients (ICC ≤ 0.6) and those being redundant (correlation matrix with Pearson correlation coefficient r > 0.8). Five common machine-learning classifiers (artificial neural network Multilayer Perceptron, decision tree J48, NaïveBayes, RandomForest, and Sequential Minimal Optimization) with tenfold cross-validation were applied to assess 5-year outcome including major adverse cardiac and cerebrovascular events (MACCE). Dimension reduction yielded 10 TA features carrying prognostic information, which were all based on T2w images. The NaïveBayes machine learning classifier showed overall best performance with a sensitivity of 82.9% (confidence interval (CI) 80–86.2), specificity of 83.7% (CI 75.7–92), and an area-under-the receiver operating characteristics curve of 0.88 (CI 0.83–0.92). This proof-of-principle study is the first to identify unique T2w-derived TA features that predict long-term outcome in patients with TTS. These features might serve as imaging prognostic biomarkers in TTS patients. |
url |
https://doi.org/10.1038/s41598-020-76432-4 |
work_keys_str_mv |
AT manojmannil prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT kenkato prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT robertmanka prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT jochenvonspiczak prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT benjaminpeters prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT victorialcammann prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT christophkaiser prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT stefanosswald prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT thanhhanguyen prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT johndhorowitz prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT hugoakatus prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT frankruschitzka prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT jelenarghadri prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT hatemalkadhi prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach AT christiantemplin prognosticvalueoftextureanalysisfromcardiacmagneticresonanceimaginginpatientswithtakotsubosyndromeamachinelearningbasedproofofprincipleapproach |
_version_ |
1724389731262791680 |
spelling |
doaj-8b9558fcbb414f078925eee1ae9987cc2020-12-08T11:18:40ZengNature Publishing GroupScientific Reports2045-23222020-11-011011910.1038/s41598-020-76432-4Prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with Takotsubo syndrome: a machine learning based proof-of-principle approachManoj Mannil0Ken Kato1Robert Manka2Jochen von Spiczak3Benjamin Peters4Victoria L. Cammann5Christoph Kaiser6Stefan Osswald7Thanh Ha Nguyen8John D. Horowitz9Hugo A. Katus10Frank Ruschitzka11Jelena R. Ghadri12Hatem Alkadhi13Christian Templin14Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of ZurichAcute Cardiac Care, Andreas Grüntzig Heart Catheterization Laboratories, Department of Cardiology, University Heart Center, University Hospital Zurich, University of ZurichInstitute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of ZurichInstitute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of ZurichInstitute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of ZurichAcute Cardiac Care, Andreas Grüntzig Heart Catheterization Laboratories, Department of Cardiology, University Heart Center, University Hospital Zurich, University of ZurichDepartment of Cardiology, University Hospital BaselDepartment of Cardiology, University Hospital BaselDepartment of Cardiology, Basil Hetzel Institute, Queen Elizabeth Hospital, University of AdelaideDepartment of Cardiology, Basil Hetzel Institute, Queen Elizabeth Hospital, University of AdelaideDepartment of Cardiology, Heidelberg University HospitalAcute Cardiac Care, Andreas Grüntzig Heart Catheterization Laboratories, Department of Cardiology, University Heart Center, University Hospital Zurich, University of ZurichAcute Cardiac Care, Andreas Grüntzig Heart Catheterization Laboratories, Department of Cardiology, University Heart Center, University Hospital Zurich, University of ZurichInstitute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of ZurichAcute Cardiac Care, Andreas Grüntzig Heart Catheterization Laboratories, Department of Cardiology, University Heart Center, University Hospital Zurich, University of ZurichAbstract Cardiac magnetic resonance (CMR) imaging has become an important technique for non-invasive diagnosis of takotsubo syndrome (TTS). The long-term prognostic value of CMR imaging in TTS has not been fully elucidated yet. This study sought to evaluate the prognostic value of texture analysis (TA) based on CMR images in patients with TTS using machine learning. In this multicenter study (InterTAK Registry), we investigated CMR imaging data of 58 patients (56 women, mean age 68 ± 12 years) with TTS. CMR imaging was performed in the acute to subacute phase (median time after symptom onset 4 days) of TTS. TA of the left ventricle was performed using free-hand regions-of-interest in short axis late gadolinium-enhanced and on T2-weighted (T2w) images. A total of 608 TA features adding the parameters age, gender, and body mass index were included. Dimension reduction was performed removing TA features with poor intra-class correlation coefficients (ICC ≤ 0.6) and those being redundant (correlation matrix with Pearson correlation coefficient r > 0.8). Five common machine-learning classifiers (artificial neural network Multilayer Perceptron, decision tree J48, NaïveBayes, RandomForest, and Sequential Minimal Optimization) with tenfold cross-validation were applied to assess 5-year outcome including major adverse cardiac and cerebrovascular events (MACCE). Dimension reduction yielded 10 TA features carrying prognostic information, which were all based on T2w images. The NaïveBayes machine learning classifier showed overall best performance with a sensitivity of 82.9% (confidence interval (CI) 80–86.2), specificity of 83.7% (CI 75.7–92), and an area-under-the receiver operating characteristics curve of 0.88 (CI 0.83–0.92). This proof-of-principle study is the first to identify unique T2w-derived TA features that predict long-term outcome in patients with TTS. These features might serve as imaging prognostic biomarkers in TTS patients.https://doi.org/10.1038/s41598-020-76432-4 |