Convexity and connectivity principles applied for Left Ventricle segmentation
We present results of an unsupervised method for MRI image segmentation
on the Test dataset of MICCAI 2018 Left Ventricle Full Quantification Challenge.
The segmentation is based on pixel labeling using image analysis, connectivity constraints
and near convex region requirements for the LV cavity and the epicardium.
At first the LV cavity is approximately localized based
on the strong intensity contrast in the septal myocardium region.
The requirement of a near convex connected component is then applied.
The image intensity statistical parameters are extracted for three classes: LV cavity, myocardium and chest space.
Even if the whole background is completely inhomogeneous, the application of topological,
connectivity and shape constraints permits to extract step-by-step the LV cavity and the myocardium.
The poster presented in MICCAI 2018 STACOM Workshop is here.
Click on the thumbnail to view an animation of the segmentation result on the whole cardiac cycle
