Following the successful application of the U-Net to medical images, there\nhave been different encoder-decoder models proposed as an improvement to the\noriginal U-Net for segmenting echocardiographic images. This study aims to\nexamine the performance of the state-of-the-art proposed models as well as the\noriginal U-Net model by applying them to segment the endocardium of the Left\nVentricle in 2D automatically. The prediction outputs of the models are used to\nevaluate the performance of the models by comparing the automated results\nagainst the expert annotations (gold standard). Our results reveal that the\nU-Net model outperforms other models by achieving an average Dice coefficient\nof 0.92$ \\pm 0.05$, and Hausdorff distance of 3.97$ \\pm 0.82$.\n