Literature DB >> 26239472

Cardiac magnetic resonance image-based classification of the risk of arrhythmias in post-myocardial infarction patients.

Lasya Priya Kotu1, Kjersti Engan2, Reza Borhani3, Aggelos K Katsaggelos3, Stein Ørn4, Leik Woie4, Trygve Eftestøl5.   

Abstract

INTRODUCTION: Patients surviving myocardial infarction (MI) can be divided into high and low arrhythmic risk groups. Distinguishing between these two groups is of crucial importance since the high-risk group has been shown to benefit from implantable cardioverter defibrillator insertion; a costly surgical procedure with potential complications and no proven advantages for the low-risk group. Currently, markers such as left ventricular ejection fraction and myocardial scar size are used to evaluate arrhythmic risk.
METHODS: In this paper, we propose quantitative discriminative features extracted from late gadolinium enhanced cardiac magnetic resonance images of post-MI patients, to distinguish between 20 high-risk and 34 low-risk patients. These features include size, location, and textural information concerning the scarred myocardium. To evaluate the discriminative power of the proposed features, we used several built-in classification schemes from matrix laboratory (MATLAB) and Waikato environment for knowledge analysis (WEKA) software, including k-nearest neighbor (k-NN), support vector machine (SVM), decision tree, and random forest.
RESULTS: In Experiment 1, the leave-one-out cross-validation scheme is implemented in MATLAB to classify high- and low-risk groups with a classification accuracy of 94.44%, and an AUC of 0.965 for a feature combination that captures size, location and heterogeneity of the scar. In Experiment 2 with the help of WEKA, nested cross-validation is performed with k-NN, SVM, adjusting decision tree and random forest classifiers to differentiate high-risk and low-risk patients. SVM classifier provided average accuracy of 92.6%, and AUC of 0.921 for a feature combination capturing location and heterogeneity of the scar. Experiment 1 and Experiment 2 show that textural features from the scar are important for classification and that localization features provide an additional benefit.
CONCLUSION: These promising results suggest that the discriminative features introduced in this paper can be used by medical professionals, or in automatic decision support systems, along with the recognized risk markers, to improve arrhythmic risk stratification in post-MI patients.
Copyright © 2015 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Cardiac magnetic resonance image; High and low arrhythmic risk; Local binary pattern; Sobel filter; Support vector machine classifier; k-Nearest neighbor classifier

Mesh:

Substances:

Year:  2015        PMID: 26239472     DOI: 10.1016/j.artmed.2015.06.001

Source DB:  PubMed          Journal:  Artif Intell Med        ISSN: 0933-3657            Impact factor:   5.326


  16 in total

1.  Radiomics for Distinguishing Myocardial Infarction from Myocarditis at Late Gadolinium Enhancement at MRI: Comparison with Subjective Visual Analysis.

Authors:  Tommaso Di Noto; Jochen von Spiczak; Manoj Mannil; Elena Gantert; Paolo Soda; Robert Manka; Hatem Alkadhi
Journal:  Radiol Cardiothorac Imaging       Date:  2019-12-19

2.  Quality of science and reporting for radiomics in cardiac magnetic resonance imaging studies: a systematic review.

Authors:  Suyon Chang; Kyunghwa Han; Young Joo Suh; Byoung Wook Choi
Journal:  Eur Radiol       Date:  2022-03-01       Impact factor: 5.315

3.  Radiomic Analysis of Myocardial Native T1 Imaging Discriminates Between Hypertensive Heart Disease and Hypertrophic Cardiomyopathy.

Authors:  Ulf Neisius; Hossam El-Rewaidy; Shiro Nakamori; Jennifer Rodriguez; Warren J Manning; Reza Nezafat
Journal:  JACC Cardiovasc Imaging       Date:  2019-01-16

Review 4.  Machine learning in cardiovascular magnetic resonance: basic concepts and applications.

Authors:  Tim Leiner; Daniel Rueckert; Avan Suinesiaputra; Bettina Baeßler; Reza Nezafat; Ivana Išgum; Alistair A Young
Journal:  J Cardiovasc Magn Reson       Date:  2019-10-07       Impact factor: 5.364

Review 5.  Emerging methods for the characterization of ischemic heart disease: ultrafast Doppler angiography, micro-CT, photon-counting CT, novel MRI and PET techniques, and artificial intelligence.

Authors:  Martin J Willemink; Akos Varga-Szemes; U Joseph Schoepf; Marina Codari; Koen Nieman; Dominik Fleischmann; Domenico Mastrodicasa
Journal:  Eur Radiol Exp       Date:  2021-03-25

6.  Repeatability of Cardiac Magnetic Resonance Radiomics: A Multi-Centre Multi-Vendor Test-Retest Study.

Authors:  Zahra Raisi-Estabragh; Polyxeni Gkontra; Akshay Jaggi; Jackie Cooper; João Augusto; Anish N Bhuva; Rhodri H Davies; Charlotte H Manisty; James C Moon; Patricia B Munroe; Nicholas C Harvey; Karim Lekadir; Steffen E Petersen
Journal:  Front Cardiovasc Med       Date:  2020-12-02

Review 7.  Artificial intelligence: improving the efficiency of cardiovascular imaging.

Authors:  Andrew Lin; Márton Kolossváry; Ivana Išgum; Pál Maurovich-Horvat; Piotr J Slomka; Damini Dey
Journal:  Expert Rev Med Devices       Date:  2020-06-16       Impact factor: 3.166

8.  Cardiac magnetic resonance radiomics: basic principles and clinical perspectives.

Authors:  Zahra Raisi-Estabragh; Cristian Izquierdo; Victor M Campello; Carlos Martin-Isla; Akshay Jaggi; Nicholas C Harvey; Karim Lekadir; Steffen E Petersen
Journal:  Eur Heart J Cardiovasc Imaging       Date:  2020-04-01       Impact factor: 6.875

Review 9.  Artificial intelligence and cardiovascular imaging: A win-win combination.

Authors:  Luigi P Badano; Daria M Keller; Denisa Muraru; Camilla Torlasco; Gianfranco Parati
Journal:  Anatol J Cardiol       Date:  2020-10       Impact factor: 1.596

10.  Radiomics Analysis Derived From LGE-MRI Predict Sudden Cardiac Death in Participants With Hypertrophic Cardiomyopathy.

Authors:  Jie Wang; Laura Bravo; Jinquan Zhang; Wen Liu; Ke Wan; Jiayu Sun; Yanjie Zhu; Yuchi Han; Georgios V Gkoutos; Yucheng Chen
Journal:  Front Cardiovasc Med       Date:  2021-12-10
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.