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

Abstract

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.

Figure 1

Flow chart of study data. AIDA STEMI, Abciximab i.v. versus i.c. in ST-elevation Myocardial Infarction; CMR, cardiac magnetic resonance; FU, follow-up; MACE, major adverse cardiac events; NSTEMI, non-ST-segment–elevation myocardial infarction; STEMI, ST-segment–elevation myocardial infarction; and TATORT NSTEMI, Thrombus Aspiration in Thrombus Containing Culprit Lesions in Non-ST-Elevation Myocardial Infarction.

Figure 2

Cardioavascular magnetic resonance LAX images with automated contouring at end systole (top) and end diastole (bottom); 4CV (left) and 2CV (right). 2CV, 2 chamber view; 4CV, 4 chamber view; LAX, long axis.

Figure 3

SAX image slices with automated contouring starting from the apical view and ending with the outflow tract of the LV. LV, left ventricle; SAX, short axis.

Figure 4

Bland-Altmann plots for agreement of manual and automated strain; GLS, GCS 3 slices and GCS all slices. Agreement between manual and automated strain values represented by Bland-Altmann plot, y axis represents the difference (manual-automated) and x axis is the mean of manual and automated values. GCS, global circumferential strain; GLS, global longitudinal strain.

Figure 5

Kaplan–Meier curves assessing survival for manual and automated GLS and GCS. All values dichotomized by their respective medians, time to event represents time to MACE. GCS, global circumferential strain; GLS, global longitudinal strain; MACE, major adverse cardiac events.