Segmentation of non-viable myocardium in delayed enhancement magnetic resonance images

Publisher Website
Google Scholar
Abstract
Purpose: To evaluate six algorithms for segmenting non-viable left ventricular (LV) myocardium in delayed enhancement (DE) magnetic resonance imaging (MRI). Methods: Twenty-three patients with known chronic ischemic heart disease underwent DE-MRI. DE images were first manually thresholded using an interactive region-filling tool to isolate non-viable myocardium. Then, six thresholding algorithms, based on the image intensity characteristics of either LV blood pool (BP), viable LV myocardium, or both, were applied to each image. For the Mean−2SDBP algorithm, thresholds were equal to the mean BP intensity minus twice its standard deviation. For the Mean+2SDSemi, Mean+3SDSemi, Mean+2SDAuto, and Mean+3SDAuto algorithms, thresholds equaled the mean intensity of viable myocardium plus twice (or thrice, as denoted by the name) the standard deviation of intensity (subscripts denote how these values were determined: automatic or semi-automatic). For the Minimum Intensity algorithm, the threshold equaled the minimum intensity between the BP and LV myocardium mean intensities. Percent Scar was defined as the ratio of non-viable to total myocardial pixels in each image. Agreement between each algorithm and manual thresholding was assessed using Bland–Altman analysis. Results: Mean Percent Scar was 25 ± 16% by manual thresholding. Five of the six algorithms demonstrated mean bias within ±3% (all except Mean+2SDAuto); however, limits of agreement (LoA) were large in general (range 12–36%). The best overall agreement was demonstrated by the Mean+2SDSemi (bias, 0%; LoA, 12%) and Mean+3SDSemi(bias, −3%; LoA, 14%) algorithms. Conclusion: On average, five of the six algorithms proved satisfactory for clinical implementation; however, in some images, manual correction of automatic results was necessary.