A Novel Method for Echocardiogram Boundary Detection Using Adaptive Neuro -Fuzzy Systems

Extracting left ventricular contour by MVN_CNN, UBN_CNN and region based level set method

“…Manual outlining of these borders is slow, time consuming and tedious task. Moreover, the resulting outlines vary between different observers and suffer from a subjective bias [4]. Hence, there is a clinical need for automatically detecting the heart boundaries over the cardiac cycle.…”

“…Amongst the other medical imaging modalities, (2D) echocardiography is valuable for patients with heart diseases. It is non-invasive, non radioactive, portable, real time, easy to use in clinical environment and non expensive when compared to other modalities [4].…”

Left Ventricular Endocardium Tracking by Fusion of Biomechanical and Deformable Models

“…Manual outlining of these borders is slow, time consuming, and tedious task. Moreover, the resulting outlines vary between different observers and suffer from a subjective bias [ 3 ].…”

“…Echocardiography has a poor image quality and resolution with various image artifacts like speckle, shadowing, and side lobes [ 3 ]. The images of echocardiography suffer from signal dropout.…”

“…The images of echocardiography suffer from signal dropout. This dropout in the echocardiography signal makes part of the LV invisible which yields an open contour [ 3 ]. Moreover, the relation between the physical property of the monitored tissue and the intensity of the pixels cannot be described in a simple way [ 4 ].…”