Key result
The centerline depth-based reinforcement learning algorithm localized the left atrial appendage orifice with an average error of 2.547 mm, outperforming other methods.
Why the study?
Accurate LAA orifice localization in preoperative CT angiography is difficult due to anatomic variation and small orifice size relative to the CT image, causing deep localization models to yield high error.
Does a centerline depth-based reinforcement learning method improve LAA orifice localization accuracy in CT images of patients undergoing LAA closure?
Does a centerline depth-based reinforcement learning method improve LAA orifice localization accuracy in CT images of patients undergoing LAA closure?
A novel reinforcement learning-based method for LAA orifice localization in CT images significantly improves accuracy and speed, potentially aiding preoperative planning for LAA closure.
Answers are grounded in this paper and cite their sources.
Supports RL-based LAA localization in imaging; hypothesis-generating and requires prospective clinical validation.
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.
No takes yet. Share an insight, caveat, or question.
Al et al. (2019) studied Non-valvular atrial fibrillation (LAA orifice localization) (n=98). Centerline depth-based reinforcement learning (RL) algorithm vs. Rule-based and CNN-based localization methods was evaluated on Orifice localization error (center difference in mm) (p=<0.02). The centerline depth-based reinforcement learning algorithm localized the left atrial appendage orifice with an average error of 2.547 mm, outperforming other methods.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: