Centerline Depth World Reinforcement Learning-based Left Atrial Appendage Orifice Localization

Abstract: Left atrial appendage (LAA) closure (LAAC) is a minimally invasive implant-based method to prevent cardiovascular stroke in patients with non-valvular atrial fibrillation. Assessing the LAA orifice in preoperative CT angiography plays a crucial role in choosing an appropriate LAAC implant size and a proper C-arm angulation. However, accurate orifice localization is hard because of the high anatomic variation of LAA, and unclear position and orientation of the orifice in available CT views. Deep localization models also yield high error in localizing the orifice in CT image because of the tiny structure of orifice compared to the vastness of CT image. In this paper, we propose a centerline depth-based reinforcement learning (RL) world for effective orifice localization in a small search space. In our scheme, an RL agent observes the centerline-to-surface distance and navigates through the LAA centerline to localize the orifice. Thus, the search space is significantly reduced facilitating improved localization. The proposed formulation could result in high localization accuracy comparing to the expert-annotations in 98 CT images. Moreover, the localization process takes about 8 seconds which is 18 times more efficient than the existing method. Therefore, this can be a useful aid to physicians during the preprocedural planning of LAAC.