Pranav Bhagirath

57 Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late Gadolinium enhancement MR images where V T is the volume of scar in the algorithm segmentation and V G is the volume of scar in the consensus segmentation. Objective evaluation In LGE CMR of the LV, hyper-enhanced areas not relating to scar are not uncommon (Turkbey et al., 2012). Unless the characteristic and geometry of these pseudo infarcts are explicitlymodeled into the technique, it is challenging for an algorithmto distinguish them. Some common sources of pseudo infarcts seen in LGE CMR of the LV are: (1) the location of the RV insertion point, (2) partial voluming in basal slices due to the outflow tract and the appendage, and (3) hyper-enhancedareas due toepi- andpericardial fat. An experienced observer selected regions containing the aforementioned enhancements. These were identified using simple techniques such as checking for continuity of scar or artifact in the adjacent slices, i.e. if it continues then it is likely to be scar. Some instances of pseudo infarcts occurring in the patient dataset are shown in figure 2 . To evaluate how the algorithms handled pseudo infarcts, each algorithm’s output was evaluated separately on these regions. The percentage of voxels detected by each method in these spurious regions was determined. Figure 2. Examples of pseudo infarct in the patient database. Arrows indicate enhancements due to the right ventricle insertion point (left) and outflow tract (right).