Reproducibility of late gadolinium enhancement quantification techniques in ischemic and non-ischemic heart diseases (ReLate study)

Abstract

Background: Late gadolinium enhancement (LGE) assessed by cardiovascular magnetic resonance (CMR) is an established metric for risk stratification and therapeutic guidance. However, consensus on the optimal technique for quantifying left ventricular (LV) LGE extent remains lacking. This study aimed to identify the most reliable method for quantifying LGE in chronic myocardial infarction (CMI), hypertrophic cardiomyopathy (HCM), and inflammatory heart disease (IHD).

Methods: A retrospective analysis was conducted on 285 prospectively enrolled patients (CMI: n = 98; HCM: n = 91; IHD: n = 96). LV LGE images in short-axis orientation were analyzed twice by the same reader. The most reliable LGE quantification technique was defined as the one achieving the highest intra-observer reproducibility. A two-step study design was implemented: in the pilot phase (n = 90), three quantification methods were compared: full width at half maximum (FWHM), signal threshold vs. reference mean using 2-6 standard deviations (n-SD), and manual thresholding. Techniques demonstrating the lowest variability were then applied in a validation cohort (n = 195). A mixed model for repeated measures was used to estimate mean differences. Equivalence was confirmed if the 95% confidence interval (CI) for the mean difference remained within predefined margins.

Results: In CMI, FWHM demonstrated the highest reproducibility, with a mean difference of 0.47% (95% CI: -0.40 to 1.35). In HCM, both the 5-SD and 6-SD techniques showed the highest reproducibility, with mean differences of 0.06% (95% CI: -1.28 to 1.39) and -0.16% (95% CI: -1.50 to 1.17), respectively. In IHD, the 5-SD and 6-SD techniques achieved the highest reproducibility, with mean differences of -0.72% (95% CI: -1.54 to 0.11) and -0.71% (95% CI: -1.54 to 0.11).

Conclusion: The distribution and pattern of LGE influence the reproducibility of its quantification. FWHM provided the highest intra-observer reproducibility for sharply demarcated scars, as seen in CMI. For more diffuse fibrosis patterns, such as in HCM and IHD, both the 5-SD and 6-SD techniques offered similarly reproducible performance.

Keywords: cardiovascular magnetic resonance; fibrosis; hypertrophic cardiomyopathy; inflammatory heart disease; ischemic heart disease; late gadolinium enhancement; myocardial scar; quantification technique.

Figure 1

Study protocol. Intra-observer analysis followed a two-step approach. In the first step (pilot study, n = 90), intra-observer variability and sample size estimates were derived. LGE was quantified using seven techniques per entity: FWHM, n-SD with 2–6 standard deviations from remote normal myocardium, and manual thresholding. In the second step (validation study, n = 195), techniques with the lowest variability were applied in separate patient cohorts (CMI: FWHM, 6-SD, manual thresholding; HCM: FWHM, 5-SD, 6-SD; IHD: 5-SD, 6-SD). Final statistical analysis (mixed model for repeated measures) identified the techniques with the highest intra-observer reproducibility, based on results from the pilot, validation, and pooled cohorts (overall analysis). CMI, chronic myocardial infarction; HCM, hypertrophic cardiomyopathy; IHD, inflammatory heart disease; LGE, late gadolinium enhancement; FWHM, full width at half maximum; n-SD, signal threshold at n standard deviations from remote myocardium. 5-SD, signal threshold at 5 standard deviations from remote myocardium. 6-SD, signal threshold at 6 standard deviations from remote myocardium. *During the pilot study, all cases were analyzed using 2-, 3-, 4-, 5-, and 6-SD techniques.

Figure 2

Representative LGE images and annotations. Representative cases of CMI (a–f), HCM: (g–l) and IHD: (m–r) with disease-typical LGE distribution: Sharply demarcated subendocardial LGE distribution in CMI cases, patchy intramural pattern in HCM cases and subepicardial pattern in IHD cases. Horizontal rows display reader annotations in the same patient for the first and second image analysis. Vertical columns indicate LGE quantification technique applied: FWHM (a,g,m,d,j,p), 6-SD (b,h,n,e,k,q), and manual thresholding (c,i,o,f,l,r). Endo- (red line) and epicardial (green line) borders were annotated. For FWHM the reference ROI (pink contour) was drawn around the visually brightest myocardial area, covering the most signal intense voxel. For the n-SD technique, the remote ROI (blue contour) was drawn in remote myocardium. Yellow marking indicates hyper-enhanced myocardium. CMI, chronic myocardial infarction; HCM, hypertrophic cardiomyopathy; IHD, inflammatory heart disease; LGE, late gadolinium enhancement; FWHM, full width at half maximum. 5-SD, signal threshold at 5 standard deviations from remote myocardium. 6-SD, signal threshold at 6 standard deviations from remote myocardium. ROI, region of interest.

Figure 3

Bland–Altman plots of agreement between first and second read LGE extent in percent for all cases per quantification technique and disease entity. CMI, chronic myocardial infarction; HCM, hypertrophic cardiomyopathy; IHD, inflammatory heart disease; LGE, late gadolinium enhancement; FWHM, full width at half maximum. 5-SD, signal threshold vs. reference mean at 5 standard deviations from remote myocardium. 6-SD, signal threshold vs. reference mean at 6 standard deviations from remote myocardium.

Figure 4

Boxplot figures of LGE extent expressed in median [%] with interquartile range (25th to 75th percentile) during first and second read per LGE quantification technique per disease entity. Whiskers depict 1.5 times interquartile range. CMI: chronic myocardial infarction. HCM, hypertrophic cardiomyopathy; IHD, inflammatory heart disease; LGE, late gadolinium enhancement; FWHM, full width at half maximum. 5-SD, signal threshold vs. reference mean at 5 standard deviations from remote myocardium. 6-SD, signal threshold vs. reference mean at 6 SD from remote myocardium.

Figure 5

Most reliable LGE quantification techniques per entity across pilot (n = 90) and validation study (n = 195). Data are expressed as PE along with 95% CI for the overall analysis (n = 285). CMI, chronic myocardial infarction; HCM, hypertrophic cardiomyopathy; IHD, inflammatory heart disease; LGE, late gadolinium enhancement; PE, point estimate; CI, confidence interval; FWHM, full width at half maximum. 5-SD: signal threshold vs. reference mean at 5 standard deviations from remote myocardium. 6-SD: signal threshold vs. reference mean at 6 standard deviations from remote myocardium.

Figure 6

Decision tree for the first step of visual inspection. After establishing sufficient image quality, visual inspection of LGE distribution and myocardial fibrosis is the primary step. In cases with CMI, HCM and IHD LGE distribution and scar pattern can present either with sharp demarcation (CMI) or no sharp demarcation (HCM, IHD). In cases of fibrosis with sharp demarcation, that are often observed in CMI patients, FWHM is the technique with the highest intra-observer reproducibility to quantify LGE extent. In cases with focal fibrosis with not sharp demarcation as associated with HCM and IHD, 5-SD and 6-SD are equally well suited to quantify LGE extent. CMI, chronic myocardial infarction; HCM, hypertrophic cardiomyopathy; IHD, inflammatory heart disease; LGE, late gadolinium enhancement; FWHM, full width at half maximum. 5-SD: signal threshold vs. reference mean at 5 standard deviations from remote myocardium. 6-SD: signal threshold vs. reference mean at 6 standard deviations from remote myocardium.