Pranav Bhagirath

60 Chapter 3 On the porcine LGE CMR scans segmentations from the algorithms and fixed-model approaches were compared in a similar way to the patient dataset. The Dice overlap metric is plotted in figure 4 for each submitted algorithm and fixed model. The Dice overlaps were determined, as above, on ROIs enclosing each region of infarction labeled in the consensus. The medians of these individual Dice overlaps were as follows: AIT = 86, KCL = 80, MCG = 73, MV = 33, and UPF = 73. Standard methods using fixed models were also compared with the consensus ground-truth and the median Dice overlaps were: 2-SD = 64, 3-SD = 65, 4-SD = 67, 5-SD = 74, 6- SD = 76, FWHM = 69. An example of a single slice from the porcine dataset is given in figure 6 . Figure 6. Example segmentation from the porcine dataset. Clockwise from top-left: original LGE CMR, consensus segmentation, FWHM, 5-SD, 6-SD, AIT, KCL, MCG, MV, UPF. Abbreviations: LV - left ventricle, RV - right ventricle, ANT - anterior, INF - inferior, INF-SEP - infero-septal, INF-LAT - infero-lateral, ANT-LAT - antero-lateral. The Dice scores, reported above, were evaluated within ROIs enclosing scar in the consensus segmentation. These areas can often be large sections within the image, especially if the scar is continuous and extends to several slices. This provided for a more objective evaluation. The algorithm’s false positive outside the ROI is not accountable. To counteract this issue, segmentations were also compared by quantifying volume differences. This was determined by measuring the difference in total volume of scar between the consensus and algorithm segmentation. An algorithm could be deemed as accurate only when it yielded a good Dice together with a small volume difference. Table 4 lists the mean volume differences and variance (as milliliters) over the entire image database for patient and porcine datasets.