Artificial intelligence fully automated myocardial strain quantification for risk stratification following acute myocardial infarction

Feasibility of automated volume-derived cardiac functional evaluation has successfully been demonstrated using cardiovascular magnetic resonance (CMR) imaging. Notwithstanding, strain assessment has proven incremental value for cardiovascular risk stratification. Since introduction of deformation im...

Descripción completa

Detalles Bibliográficos
Autores principales: Backhaus, Sören J., Aldehayat, Haneen, Kowallick, Johannes T., Evertz, Ruben, Lange, Torben, Kutty, Shelby, Bigalke, Boris, Gutberlet, Matthias, Hasenfuß, Gerd, Thiele, Holger, Stiermaier, Thomas, Eitel, Ingo, Schuster, Andreas
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9293901/
https://www.ncbi.nlm.nih.gov/pubmed/35851282
http://dx.doi.org/10.1038/s41598-022-16228-w
Descripción
Sumario:Feasibility of automated volume-derived cardiac functional evaluation has successfully been demonstrated using cardiovascular magnetic resonance (CMR) imaging. Notwithstanding, strain assessment has proven incremental value for cardiovascular risk stratification. Since introduction of deformation imaging to clinical practice has been complicated by time-consuming post-processing, we sought to investigate automation respectively. CMR data (n = 1095 patients) from two prospectively recruited acute myocardial infarction (AMI) populations with ST-elevation (STEMI) (AIDA STEMI n = 759) and non-STEMI (TATORT-NSTEMI n = 336) were analysed fully automated and manually on conventional cine sequences. LV function assessment included global longitudinal, circumferential, and radial strains (GLS/GCS/GRS). Agreements were assessed between automated and manual strain assessments. The former were assessed for major adverse cardiac event (MACE) prediction within 12 months following AMI. Manually and automated derived GLS showed the best and excellent agreement with an intraclass correlation coefficient (ICC) of 0.81. Agreement was good for GCS and poor for GRS. Amongst automated analyses, GLS (HR 1.12, 95% CI 1.08–1.16, p < 0.001) and GCS (HR 1.07, 95% CI 1.05–1.10, p < 0.001) best predicted MACE with similar diagnostic accuracy compared to manual analyses; area under the curve (AUC) for GLS (auto 0.691 vs. manual 0.693, p = 0.801) and GCS (auto 0.668 vs. manual 0.686, p = 0.425). Amongst automated functional analyses, GLS was the only independent predictor of MACE in multivariate analyses (HR 1.10, 95% CI 1.04–1.15, p < 0.001). Considering high agreement of automated GLS and equally high accuracy for risk prediction compared to the reference standard of manual analyses, automation may improve efficiency and aid in clinical routine implementation. Trial registration: ClinicalTrials.gov, NCT00712101 and NCT01612312.

Ejemplares similares