Right Ventricle MRI Image Segmentation of Heart

Accurate segmentation of right ventricle (RV) is essential for the cardiac function analysis. However, it is labor intensive and time consuming for radiologists to delineate RV boundary manually. In this paper, we propose a fully automatic approach for segmentation of right ventricular (RV) cavities from cardiac Magnetic Resonance (MR) images. Standard Models of CNN are not efficient to provide more accurate mask. That's why higher variants of CNN are introduced. In this we propose a approach "dilated densers" which outperforms the result of Standard models U-Net, Dilated Denesenets and Dilated U-net).