Skip to main content
. Author manuscript; available in PMC: 2019 Aug 1.
Published in final edited form as: Magn Reson Med. 2018 Jan 3;80(2):780–791. doi: 10.1002/mrm.27068

Figure 2.

Figure 2

Pipeline for myocardial segmentation from T1-w images. Appearance model, gref, for a selected reference image, Iref, is combined with the general shape model, built in the training step, to segment Iref in the given T1-w images. One point is inserted manually at the middle of the blood pool of Iref to locate the initial LV shape of the general shape model on Iref. The extracted reference contour, cref, is used to generate the number of simulated LV contours. A new slice-specific shape model (SSSM) is built for that set of T1-w images from the simulated contours. Each of the remaining appearance models, gi, built in the training step is combined with the SSSM to segment the corresponding image, Ii, and generate new contour, ci.