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

Cardiac magnetic resonance Cardiac segmentation Coronary artery disease Deep learning Epicardial adipose tissue Epicardial fat Outcome

Journal

Atherosclerosis

ISSN: 1879-1484

Titre abrégé: Atherosclerosis

Pays: Ireland

ID NLM: 0242543

Informations de publication

Date de publication:
18 Apr 2024

Historique:

received: 19 01 2024

revised: 18 03 2024

accepted: 10 04 2024

medline: 29 4 2024

pubmed: 29 4 2024

entrez: 28 4 2024

Statut: aheadofprint

Résumé

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. 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. 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. 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.

Sections du résumé

BACKGROUND AND AIMS OBJECTIVE

METHODS 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 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 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.

Identifiants

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

pubmed: 38679562

pii: S0021-9150(24)00109-6

doi: 10.1016/j.atherosclerosis.2024.117549

pii:

doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

Pagination

117549

Informations de copyright

Déclaration de conflit d'intérêts

Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Gianluca Pontone reports a relationship with G.E. Healthcare, Bracco, Heartflow, Boheringher that includes: funding grants and speaking and lecture fees. The other authors have nothing to disclose.