X线片椎骨语义边缘引导的2D/3D配准方法  

Semantic edge-guided 2D/3D registration for vertebrae in radiographs

作　　者：沈傲 沈燕进[2] 蒋俊锋[1] 陈正鸣[1] 黄瑞[1] 何坤金[1] 陈杰[2] Shen Ao;Shen Yanjin;Jiang Junfeng;Chen Zhengming;Huang Rui;He Kunjin;Chen Jie(Key Laboratory of Maritime Intelligent Cyberspace Technology of Ministry of Education,Hohai University,Changzhou 213200,China;The First People’s Hospital of Changzhou,Changzhou 213003,China)

机构地区：[1]河海大学海上智能网信技术教育部重点实验室,常州213200 [2]常州市第一人民医院,常州213003

出　　处：《中国图象图形学报》2025年第2期601-614,共14页Journal of Image and Graphics

基　　金：河海大学海上智能网信技术教育部重点实验室中央高校业务费项目(B240203012);江苏省重点研发计划资助(BE2022718)。

摘　　要：目的基于影像引导的脊柱手术机器人系统中,2D/3D配准指的是将术前计算机断层扫描影像与术中X线片配准,用于实现手术机器人对于人体组织的精准空间定位。常见做法是先用标志点进行粗配准,再用灰度法修正位姿。标志点配准问题在于标志点识别精度不高且识别效率较低,灰度法的捕获范围小且对初始位姿敏感。由于脊柱关节边缘重叠且术中X线片图像质量较低,故利用物理边缘作为特征进行2D/3D配准精度不高。因此,提出一种基于语义边缘提取的2D/3D配准方法。方法首先,提取X线片中成像清晰的椎弓根边缘和椎体两侧边缘作为语义特征进行2D/3D配准;同时,面向边缘提取任务,研究一种间距约束的高效“U”形变形器网络,该深度学习网络提高分割效率的同时,保持了边缘分割的准确性,并加入了椎骨间距约束损失的先验信息,进一步提升了多椎骨语义边缘提取的精度。结果模拟数据与真实数据上评估结果表明,本文方法在配准精度与效率方面均优于现有方法;位姿修正后,本文方法平移误差小于1 mm,旋转误差小于0.1°,配准耗时在5 s左右,能较好满足实际临床需求。结论本文提出的基于椎骨语义边缘的2D/3D粗配准方法有效缩小了后续精配准过程的搜索空间,从而提高了配准精度。在边缘提取方面,将哈达玛乘积代替卷积操作的方式以及加入椎骨间距约束损失,提高了语义边缘的提取效率和精度。因此,本文方法能够较好满足2D/3D配准的精度与实时性需求。Objective In image-guided spine surgery-based robotic systems,2D/3D registration refers to aligning preopera⁃tive 3D computed tomography(CT)images with intraoperative 2D X-rays to achieve precise spatial localization of the surgi⁃cal robot for human tissues.The prevalent approach involves the use of landmark points for initial coarse registration and subsequently applying the intensity-based method to rectify the position.However,the landmark-based registration method typically uses a heatmap regression method,which can be GPU intensive.Simultaneously,the random field of view during intraoperative X-rays and the overlapping of human tissues on X-rays can result in the loss of tissue information.This loss can cause incorrect predictions or predictions with a considerable deviation of landmark points.The intensity-based method is considered the most accurate and efficient approach because it utilizes the entire image information.However,intensity-based methods usually have problems such as a small capture range and sensitivity to the initial pose.The accuracy of 2D/3D registration when physical edges are used as features is low because of the overlap of spinal joint edges and the low qual⁃ity of intraoperative radiographs.Here,a 2D/3D registration method based on semantic edge extraction is proposed.Method The semantic edge-based 2D/3D registration method uses noverlapping pedicle edges and edges on both sides of the vertebra in the X-ray as semantic features for 2D/3D registration.The real-time detection Transformer model is first used to predict the bounding boxes of the vertebrae to be registered in intraoperative X-rays.The CT images of the vertebrae to be registered are then extracted from the known vertebrae masks.The semantic edges of the vertebrae from the intraop⁃erative X-rays and the digitally reconstructed radiological images from the CT image projection are extracted by spacing con⁃strained and efficient UNet Transformers(SCE-UNETR).Finally,the pose is updated iteratively by minimizing the re

关 键 词：2D/3D配准 脊柱手术机器人 椎骨 语义边缘提取 视觉变形器网络(ViT) 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] R687.1[自动化与计算机技术—控制科学与工程]