Factors Affecting the Level Set Segmentation of the Heart Ventricles in Short Axis Cardiac Perfusion MRI Images

Abstract

This paper studies the effect of the registration and initialization of the level set segmentation on the performance of the extracting the heart ventricles for perfusion MRI images. Through the registration experiments, the translational transformation was studied based on both the spatial and frequency domain. The frequency domain based registration is mainly established on the phase correlation methodology. As for the segmentation experiments, the level set initialization, was done through extracting the ventricles’ real shape from each slice, using threshold and a combination of morphological operations. Though, the final contour of any frame was used as the initial contour for the next frame. This proposed strategy differs from conventional ones in using the real shape of the ventricles as an initial contour than assuming it as circle or ellipse as in the literature. The second initialization strategy was based on defining the initial contour for each frame using the polar representation of the image. Two short axis view datasets of cardiac magnetic resonance (CMR) perfusion imaging were used in testing the proposed methods. Dice  coefficient, sensitivity, specificity  and  Hausdorff  distance have  been  used  to  evaluate  and  validate  the  segmentation results. The segmentation accuracy for left and right ventricles improved from 72% to 77% and from 70 % to 81% using the spatial domain based registration algorithm. The   polar based initialization strategy improves the segmentation accuracy from 77 % to 81% and from 81% to 82% for the left and right ventricles respectively.