A Comparative Study on Left and Right Endocardium Segmentation using Gradient Vector Field and Adaptive Diffusion Flow Algorithms

The cardiac Magnetic Resonance Imaging (MRI) provides high resolution images of the heart without radiation exposure. It is an excellent noninvasive test used by radiologist for proper detection of heart diseases. The manual segmentation of left ventricle in cine short axis MRI sequences takes an ample amount of time as compared to semi-automated segmentation. In Gradient Vector Flow (GVF) model certain barriers hinder the performance such as weak edge detection, high computational time, limited capture range and its ambiguity with other parameters. In this paper segmentation of Endocardium is carried out on multistage MRI frames Using Adaptive Diffusion flow (ADF) model. This deformable model was tested on large scale number of Cardiac MRI images. We replace the smoothening energy term in GVF with active hyper-surface harmonic minimal function in order to avoid possible leakage at weak edges. The use of harmonic maps is adjusted in accordance with image characteristics. We also assimilate infinite Laplace function to move active contours into narrow concave sections. Experimental results and collation with GVF are presented in this paper which reveals several good results based on extraction of endocardium tissue from left and right ventricle, including less computational time, noise robustness and weak edge preserving on Cardiac MR Images.