Automatic Detection and Quantification of Mitral Regurgitation on TTE with Application to Assist Mitral Clip Planning and Evaluation

摘要

Mitral regurgitation (MR), characterized by reverse blood flow during systole, is one of the most common valvular heart diseases. It typically requires treatment via surgical (mitral valve replacement or repair) or percutaneous approaches (e.g., MitraClip). To assist clinical diagnosis and assessment, we propose a learning-based framework to automatically detect and quantify mitral regurgitation from transthoracic echocardiography (TTE), which is usually the initial method to evaluate the cardiac and valve function. Our method leverages both anatomical (B-Mode) and hemodynamical (Color Doppler) information by extracting 3D features on multiple channels and selecting the most relevant ones by a boosting-based approach. Furthermore, the proposed framework provides an automatic modeling of mitral valve structures, such as the location of the regurgitant orifice, the mitral annulus, and the mitral valve closure line, which can be used to assist medical treatment or interventions. To demonstrate the performance of our method, we evaluate the system on a clinical dataset acquired from MR patients. Preliminary results agree well with clinical measurements in a quantitative manner.