1. AI Cardiac MRI Scar Analysis Aids Prediction of Major Arrhythmic Events in the Multicenter DERIVATE Registry
- Author
-
Fahime Ghanbari, Thomas Joyce, Valentina Lorenzoni, Andrea I. Guaricci, Anna-Giulia Pavon, Laura Fusini, Daniele Andreini, Mark G. Rabbat, Giovanni Donato Aquaro, Raffaele Abete, Jan Bogaert, Giovanni Camastra, Samuela Carigi, Nazario Carrabba, Grazia Casavecchia, Stefano Censi, Gloria Cicala, Carlo N. De Cecco, Manuel De Lazzari, Gabriella Di Giovine, Mauro Di Roma, Marta Focardi, Nicola Gaibazzi, Annalaura Gismondi, Matteo Gravina, Chiara Lanzillo, Massimo Lombardi, Jordi Lozano-Torres, Ambra Masi, Claudio Moro, Giuseppe Muscogiuri, Alberto Nese, Silvia Pradella, Stefano Sbarbati, U. Joseph Schoepf, Adele Valentini, Gérard Crelier, Pier Giorgio Masci, Gianluca Pontone, Sebastian Kozerke, Juerg Schwitter, Institut Català de la Salut, [Ghanbari F] Cardiovascular Department, CMR Center, University Hospital Lausanne–CHUV, Lausanne, Switzerland. Faculty of Biology and Medicine, Lausanne University, UniL, Lausanne, Switzerland. [Joyce T] Institute for Biomedical Engineering, University and ETH Zurich, Zurich, Switzerland. [Lorenzoni V] Institute of Management, Scuola Superiore Sant’Anna, Pisa, Italy. [Guaricci AI] Institute of Cardiovascular Disease, Department of Emergency and Organ Transplantation, University Hospital Policlinico of Bari, Bari, Italy. [Pavon AG] Cardiovascular Department, CMR Center, University Hospital Lausanne–CHUV, Lausanne, Switzerland. [Fusini L] Centro Cardiologico Monzino IRCCS, Milan, Italy. Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy. [Lozano-Torres J] Servei de Cardiologia, Vall d’Hebron Hospital Universitari, Barcelona, Spain. Vall d’Hebron Institut de Recerca (VHIR), Barcelona, Spain. Universitat Autònoma de Barcelona, Bellaterra, Spain. Centro de Investigación Biomédica en Red-CV, CIBER CV, Madrid, Spain, and Vall d'Hebron Barcelona Hospital Campus
- Subjects
conceptos matemáticos::algoritmos::inteligencia artificial [FENÓMENOS Y PROCESOS] ,Male ,Intel·ligència artificial ,enfermedades cardiovasculares::enfermedades cardíacas::arritmias cardíacas [ENFERMEDADES] ,Mathematical Concepts::Algorithms::Artificial Intelligence [PHENOMENA AND PROCESSES] ,Arrítmia ,Contrast Media ,Magnetic Resonance Imaging, Cine ,Stroke Volume ,Gadolinium ,Magnetic Resonance Imaging ,Ventricular Function, Left ,Cicatrix ,Artificial Intelligence ,Predictive Value of Tests ,Diagnosis::Diagnostic Techniques and Procedures::Diagnostic Imaging::Tomography::Magnetic Resonance Imaging [ANALYTICAL, DIAGNOSTIC AND THERAPEUTIC TECHNIQUES, AND EQUIPMENT] ,Imatgeria per ressonància magnètica ,Humans ,diagnóstico::técnicas y procedimientos diagnósticos::diagnóstico por imagen::tomografía::imagen por resonancia magnética [TÉCNICAS Y EQUIPOS ANALÍTICOS, DIAGNÓSTICOS Y TERAPÉUTICOS] ,Radiology, Nuclear Medicine and imaging ,Registries ,Cardiovascular Diseases::Heart Diseases::Arrhythmias, Cardiac [DISEASES] ,Aged ,Retrospective Studies - Abstract
Background Scar burden with late gadolinium enhancement (LGE) cardiac MRI (CMR) predicts arrhythmic events in patients with postinfarction in single-center studies. However, LGE analysis requires experienced human observers, is time consuming, and introduces variability. Purpose To test whether postinfarct scar with LGE CMR can be quantified fully automatically by machines and to compare the ability of LGE CMR scar analyzed by humans and machines to predict arrhythmic events. Materials and Methods This study is a retrospective analysis of the multicenter, multivendor CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy (DERIVATE) registry. Patients with chronic heart failure, echocardiographic left ventricular ejection fraction (LVEF) of less than 50%, and LGE CMR were recruited (from January 2015 through December 2020). In the current study, only patients with ischemic cardiomyopathy were included. Quantification of total, dense, and nondense scars was carried out by two experienced readers or a Ternaus network, trained and tested with LGE images of 515 and 246 patients, respectively. Univariable and multivariable Cox analyses were used to assess patient and cardiac characteristics associated with a major adverse cardiac event (MACE). Area under the receiver operating characteristic curve (AUC) was used to compare model performances. Results In 761 patients (mean age, 65 years ± 11, 671 men), 83 MACEs occurred. With use of the testing group, univariable Cox-analysis found New York Heart Association class, left ventricle volume and/or function parameters (by echocardiography or CMR), guideline criterion (LVEF of ≤35% and New York Heart Association class II or III), and LGE scar analyzed by humans or the machine-learning algorithm as predictors of MACE. Machine-based dense or total scar conferred incremental value over the guideline criterion for the association with MACE (AUC: 0.68 vs 0.63, P = .02 and AUC: 0.67 vs 0.63, P = .01, respectively). Modeling with competing risks yielded for dense and total scar (AUC: 0.67 vs 0.61, P = .01 and AUC: 0.66 vs 0.61, P = .005, respectively). Conclusion In this analysis of the multicenter CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy (DERIVATE) registry, fully automatic machine learning-based late gadolinium enhancement analysis reliably quantifies myocardial scar mass and improves the current prediction model that uses guideline-based risk criteria for implantable cardioverter defibrillator implantation. ClinicalTrials.gov registration no.: NCT03352648 Published under a CC BY 4.0 license. Supplemental material is available for this article. ispartof: Radiology vol:307 issue:3 pages:e222239- ispartof: location:United States status: published
- Published
- 2023