arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.09575cs.CVeess.IV
收藏

i3PosNet:颞骨手术中基于X线的器械位姿估计

i3PosNet: Instrument Pose Estimation from X-Ray in temporal bone surgery

German Center for Neuro-degenerative Diseases(德国神经退行性疾病中心);Technischer Universität Darmstadt(达姆施塔特工业大学);University Düsseldorf(杜塞尔多夫大学)

David Kügler, Jannik Sehring, Andrei Stefanov, Igor Stenin, Julia Kristin, Thomas Klenzner, Jörg Schipper, Anirban Mukhopadhyay

摘要:

目的:精确估计手术器械的位置和方向(姿态)对于精细的微创颞骨手术至关重要。目前的技术缺乏准确性和/或视线限制(常规跟踪系统)或使患者暴露于禁止的电离辐射(术中CT)。一种可能的解决方案是用C形臂以不规则的间隔捕获仪器,并从图像中恢复姿态。方法:i3 PosNet使用姿态估计网络从图像中推断仪器的位置和方向。所述框架考虑局部补丁并输出伪地标。通过几何考虑从伪地标重建姿态。结果:我们显示i3 PosNet的误差小于0.05 mm。它优于传统的基于图像配准的方法,将平均误差和最大误差减少了至少三分之二。在合成图像上训练的i3 PosNet可以推广到真实的X射线,而无需任何进一步的调整。结论:将基于深度学习的方法转化为外科手术应用是困难的,因为无法获得用于训练和测试的大型代表性数据集。这项工作经验性地示出了仅基于合成训练数据训练的亚毫米姿态估计。

英文摘要:

Purpose: Accurate estimation of the position and orientation (pose) of surgical instruments is crucial for delicate minimally invasive temporal bone surgery. Current techniques lack in accuracy and/or line-of-sight constraints (conventional tracking systems) or expose the patient to prohibitive ionizing radiation (intra-operative CT). A possible solution is to capture the instrument with a c-arm at irregular intervals and recover the pose from the image. Methods: i3PosNet infers the position and orientation of instruments from images using a pose estimation network. Said framework considers localized patches and outputs pseudo-landmarks. The pose is reconstructed from pseudo-landmarks by geometric considerations. Results: We show i3PosNet reaches errors less than 0.05mm. It outperforms conventional image registration-based approaches reducing average and maximum errors by at least two thirds. i3PosNet trained on synthetic images generalizes to real x-rays without any further adaptation. Conclusion: The translation of Deep Learning based methods to surgical applications is difficult, because large representative datasets for training and testing are not available. This work empirically shows sub-millimeter pose estimation trained solely based on synthetic training data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑