Automated and semiautomated techniques for left ventricular scar quantification from CMR-LGE images provided accurate and reproducible results comparable to manual tracing.
Observational (n=20)
Do automated and semiautomated segmentation techniques provide comparable accuracy to manual tracing for quantifying left ventricular nonviable tissue on CMR-LGE images in patients with ischemic cardiomyopathy?
Automated and semiautomated segmentation techniques offer accurate and reproducible quantification of left ventricular scar on CMR-LGE images, comparable to manual tracing, while potentially minimizing user interaction and computational time.
PURPOSE: The aim of this study was to compare the performance of quantitative methods, either semiautomated or automated, for left ventricular (LV) nonviable tissue analysis from cardiac magnetic resonance late gadolinium enhancement (CMR-LGE) images. MATERIALS AND METHODS: The investigated segmentation techniques were: (i) n-standard deviations thresholding; (ii) full width at half maximum thresholding; (iii) Gaussian mixture model classification; and (iv) fuzzy c-means clustering. These algorithms were applied either in each short axis slice (single-slice approach) or globally considering the entire short-axis stack covering the LV (global approach). CMR-LGE images from 20 patients with ischemic cardiomyopathy were retrospectively selected, and results from each technique were assessed against manual tracing. RESULTS: All methods provided comparable performance in terms of accuracy in scar detection, computation of local transmurality, and high correlation in scar mass compared with the manual technique. In general, no significant difference between single-slice and global approach was noted. The reproducibility of manual and investigated techniques was confirmed in all cases with slightly lower results for the nSD approach. CONCLUSIONS: Automated techniques resulted in accurate and reproducible evaluation of LV scars from CMR-LGE in ischemic patients with performance similar to the manual technique. Their application could minimize user interaction and computational time, even when compared with semiautomated approaches.
Carminati et al. (Tue,) conducted a observational in Ischemic cardiomyopathy (n=20). Automated and semiautomated quantitative methods (n-SD, FWHM, GMM, FCM) vs. Manual tracing was evaluated on Accuracy in scar detection, computation of local transmurality, and correlation in scar mass. Automated and semiautomated techniques for left ventricular scar quantification from CMR-LGE images provided accurate and reproducible results comparable to manual tracing.