Deformable 3D-2D registration for high-precision guidance and verification of neuroelectrode placement.
Deformable 3D-2D registration for high-precision guidance and verification of neuroelectrode placement.
复制标题
可变形 3D-2D 配准，用于神经电极放置的高精度引导和验证。
DOI：
10.1088/1361-6560/ac2f89
复制
发表时间：
2021
影响因子：
3.5
通讯作者：
Siewerdsen,JH
中科院分区：
文献类型：
--
作者：
Uneri,A;Wu,P;Jones,CK;Vagdargi,P;Han,R;Helm,PA;Luciano,MG;Anderson,WS;Siewerdsen,JH
目的准确的神经电极放置是有效监测或刺激神经外科靶点的关键。本研究提出并评估了一种结合深度学习和基于模型的可变形3D-2D配准的方法，该方法使用术中成像来指导和验证神经电极放置。以及（3）根据物理设备模型的神经电极的可变形3D-2D配准。在体模、尸体、和临床研究的（a）神经电极配准的准确性和（B）锥形束CT（CBCT）中金属伪影减少（MAR）的质量，其中将可变形配准的神经电极模型作为MAR的输入。2D配准方法在尸体研究中达到0.2±0.1 mm的准确度，在临床研究中达到0.6±0.3 mm的准确度。检测网络和3D对应关系提供了2 mm内3D-2D配准的初始化，这有助于在10 s内实现端到端配准运行时间。金属伪影，量化为标准偏差的体素值在邻近神经电极的组织，减少了72%，在幻影研究和60%，在第一次临床studies.ConclusionsThe方法结合了深度学习的速度和普遍性（初始化）与基于物理模型的配准的精度和可靠性，以实现准确的可变形3D-2D配准和MAR在功能神经外科。荧光透视的准确3D-2D引导可以克服传统导航中与变形相关的局限性，改进的MAR可以改善CBCT对神经电极放置的验证。
PurposeAccurate neuroelectrode placement is essential to effective monitoring or stimulation of neurosurgery targets. This work presents and evaluates a method that combines deep learning and model-based deformable 3D-2D registration to guide and verify neuroelectrode placement using intraoperative imaging.MethodsThe registration method consists of three stages:(1) detection of neuroelectrodes in a pair of fluoroscopy images using a deep learning approach;(2) determination of correspondence and initial 3D localization among neuroelectrode detections in the two projection images; and (3) deformable 3D-2D registration of neuroelectrodes according to a physical device model. The method was evaluated in phantom, cadaver, and clinical studies in terms of (a) the accuracy of neuroelectrode registration and (b) the quality of metal artifact reduction (MAR) in cone-beam CT (CBCT) in which the deformably registered neuroelectrode models are taken as input to the MAR.ResultsThe combined deep learning and model-based deformable 3D-2D registration approach achieved 0.2±0.1 mm accuracy in cadaver studies and 0.6±0.3 mm accuracy in clinical studies. The detection network and 3D correspondence provided initialization of 3D-2D registration within 2 mm, which facilitated end-to-end registration runtime within 10 s. Metal artifacts, quantified as the standard deviation in voxel values in tissue adjacent to neuroelectrodes, were reduced by 72% in phantom studies and by 60% in first clinical studies.ConclusionsThe method combines the speed and generalizability of deep learning (for initialization) with the precision and reliability of physical model-based registration to achieve accurate deformable 3D-2D registration and MAR in functional neurosurgery. Accurate 3D-2D guidance from fluoroscopy could overcome limitations associated with deformation in conventional navigation, and improved MAR could improve CBCT verification of neuroelectrode placement.