Mitral valve regurgitation (MR) is a heart valvular disease involving blood backflow from left ventricle to left atrium. Evaluating the severity of MR is one of the most significant aspects in treating MR, since MR with different severity requires different treatments. In clinical settings, an overestimation of MR can occur under many circustances, such as when MR is not holosystolic. Therefore, techniques to avoid overestimation and underestimation of the severity of MR are valuable to the treatment of MR. In this project, we aim to develop a deep neural network to support an accurate MR severity estimation. Our network will use two-dimensional color-flow echocardiography and the PISA method to estimate the flow rate through the regurgitant orifice. We will detect PISA area and find the center of the regurgitant origice and the flow rate. Thus estiamte the severity of MR.
