DEep LearnIng-based QuaNtification of epicardial adipose tissue predicts MACE in patients undergoing stress CMR

Marco Guglielmo; Marco Penso; Maria Ludovica Carerj; Carlo Maria Giacari; Alessandra Volpe; Laura Fusini; Andrea Baggiano; Saima Mushtaq; Andrea Annoni; Francesco Cannata; Francesco Cilia; Alberico Del Torto; Fabio Fazzari; Alberto Formenti; Antonio Frappampina; Paola Gripari; Daniele Junod; Maria Elisabetta Mancini; Valentina Mantegazza; Riccardo Maragna; Francesca Marchetti; Giorgio Mastroiacovo; Sergio Pirola; Luigi Tassetti; Francesca Baessato; Valentina Corino; Andrea Igoren Guaricci; Mark G Rabbat; Alexia Rossi; Chiara Rovera; Pietro Costantini; Ivo van der Bilt; Pim van der Harst; Marianna Fontana; Enrico G Caiani; Mauro Pepi; Gianluca Pontone

doi:10.1016/j.atherosclerosis.2024.117549

DEep LearnIng-based QuaNtification of epicardial adipose tissue predicts MACE in patients undergoing stress CMR

Atherosclerosis. 2024 Apr 18:117549. doi: 10.1016/j.atherosclerosis.2024.117549. Online ahead of print.

Authors

Marco Guglielmo¹, Marco Penso², Maria Ludovica Carerj³, Carlo Maria Giacari⁴, Alessandra Volpe⁵, Laura Fusini⁶, Andrea Baggiano⁷, Saima Mushtaq⁵, Andrea Annoni⁵, Francesco Cannata⁵, Francesco Cilia⁵, Alberico Del Torto⁵, Fabio Fazzari⁵, Alberto Formenti⁵, Antonio Frappampina⁵, Paola Gripari⁵, Daniele Junod⁵, Maria Elisabetta Mancini⁵, Valentina Mantegazza⁷, Riccardo Maragna⁵, Francesca Marchetti⁵, Giorgio Mastroiacovo⁵, Sergio Pirola⁵, Luigi Tassetti⁵, Francesca Baessato⁸, Valentina Corino⁶, Andrea Igoren Guaricci⁹, Mark G Rabbat¹⁰, Alexia Rossi¹¹, Chiara Rovera¹², Pietro Costantini¹³, Ivo van der Bilt¹, Pim van der Harst¹⁴, Marianna Fontana¹⁵, Enrico G Caiani¹⁶, Mauro Pepi⁵, Gianluca Pontone¹⁷

Affiliations

¹ Department of Cardiology, Division of Heart and Lungs, Utrecht University, Utrecht University Medical Center, Utrecht, the Netherlands; Department of Cardiology, Haga Teaching Hospital, The Hague, the Netherlands.
² Istituto Auxologico Italiano IRCCS, San Luca Hospital, Milano, Italy.
³ Department of Perioperative Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Biomedical Sciences and Morphological and Functional Imaging, "G. Martino" University Hospital Messina, Messina, Italy.
⁴ Department of Valvular and Structural Interventional Cardiology, Centro Cardiologico, Monzino IRCCS, Milan, Italy.
⁵ Department of Perioperative Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy.
⁶ Department of Perioperative Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Electronics, Information and Biomedical Engineering, Politecnico di Milano, Milan, Italy.
⁷ Department of Perioperative Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Clinical Sciences and Community Health, Cardiovascular Section, University of Milan, Italy.
⁸ Department of Cardiology, San Maurizio Regional Hospital, Bolzano, Italy.
⁹ Department of Interdisciplinary Medicine Cardiology University Unit, University Hospital Polyclinic of Bari, Bari, Italy.
¹⁰ Loyola University of Chicago, Chicago, IL, USA; Edward Hines Jr. VA Hospital, Hines, IL, USA.
¹¹ Department of Nuclear Medicine, University Hospital, Zurich, Switzerland; Center for Molecular Cardiology, University of Zurich, Zurich, Switzerland.
¹² Ospedale di Chivasso, Turin, Italy.
¹³ Radiology Department, Ospedale Maggiore Della Carita' University Hospital, Novara, Italy.
¹⁴ Department of Cardiology, Division of Heart and Lungs, Utrecht University, Utrecht University Medical Center, Utrecht, the Netherlands.
¹⁵ National Amyloidosis Centre, University College London, Royal Free Hospital, London, UK.
¹⁶ Istituto Auxologico Italiano IRCCS, San Luca Hospital, Milano, Italy; Department of Electronics, Information and Biomedical Engineering, Politecnico di Milano, Milan, Italy.
¹⁷ Department of Perioperative Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy. Electronic address: gianluca.pontone@cardiologicomonzino.it.

PMID: 38679562
DOI: 10.1016/j.atherosclerosis.2024.117549

Abstract

Background and aims: This study investigated the additional prognostic value of epicardial adipose tissue (EAT) volume for major adverse cardiovascular events (MACE) in patients undergoing stress cardiac magnetic resonance (CMR) imaging.

Methods: 730 consecutive patients [mean age: 63 ± 10 years; 616 men] who underwent stress CMR for known or suspected coronary artery disease were randomly divided into derivation (n = 365) and validation (n = 365) cohorts. MACE was defined as non-fatal myocardial infarction and cardiac deaths. A deep learning algorithm was developed and trained to quantify EAT volume from CMR. EAT volume was adjusted for height (EAT volume index). A composite CMR-based risk score by Cox analysis of the risk of MACE was created.

Results: In the derivation cohort, 32 patients (8.7 %) developed MACE during a follow-up of 2103 days. Left ventricular ejection fraction (LVEF) < 35 % (HR 4.407 [95 % CI 1.903-10.202]; p<0.001), stress perfusion defect (HR 3.550 [95 % CI 1.765-7.138]; p<0.001), late gadolinium enhancement (LGE) (HR 4.428 [95%CI 1.822-10.759]; p = 0.001) and EAT volume index (HR 1.082 [95 % CI 1.045-1.120]; p<0.001) were independent predictors of MACE. In a multivariate Cox regression analysis, adding EAT volume index to a composite risk score including LVEF, stress perfusion defect and LGE provided additional value in MACE prediction, with a net reclassification improvement of 0.683 (95%CI, 0.336-1.03; p<0.001). The combined evaluation of risk score and EAT volume index showed a higher Harrel C statistic as compared to risk score (0.85 vs. 0.76; p<0.001) and EAT volume index alone (0.85 vs.0.74; p<0.001). These findings were confirmed in the validation cohort.

Conclusions: In patients with clinically indicated stress CMR, fully automated EAT volume measured by deep learning can provide additional prognostic information on top of standard clinical and imaging parameters.

Keywords: Cardiac magnetic resonance; Cardiac segmentation; Coronary artery disease; Deep learning; Epicardial adipose tissue; Epicardial fat; Outcome.