SCoPE-Reg：基于状态空间关联与闭式位姿估计的高效刚性超声切片-体积配准方法
SCoPE-Reg: Efficient Rigid Ultrasound Slice-to-Volume Registration via State-Space Correlation and Closed-Form Pose Estimation
- Institute for AI in Medicine (IKIM), University Hospital Essen（埃森大学医院医学人工智能研究所（IKIM））
- RACOON Study Group, Site Essen（RACOON研究组埃森站点）
- Department of Physics, Technical University Dortmund（多特蒙德工业大学物理系）
- German Cancer Consortium (DKTK), Partner Site Essen（德国癌症联盟（DKTK）埃森合作站点）
- Medical Faculty and Faculty of Computer Science, University of Duisburg-Essen（杜伊斯堡-埃森大学医学院与计算机科学学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
SCoPE-Reg结合状态空间交互等技术提升刚性超声切片-体积配准精度、降低误差、保持高帧率，在相关数据集上优于现有最优方法，可用于超声引导介入操作。
AI中文摘要：
超声引导的介入操作常需要在三维解剖参考图中定位未被追踪的二维帧，刚性切片-体积配准（SVR）用于估计该六自由度位姿，但受限于解剖上下文有限、声学伪影和视角相关外观，仍具挑战性。现有方法常采用密集交叉注意力，其成本随切片与体积令牌数的乘积缩放，或采用无显式对应约束的直接位姿回归。本文提出SCoPE-Reg，结合状态空间切片-体积交互、密集三维坐标预测与无参数加权Kabsch估计。在CAMUS和μ-RegPro的SVR任务上，SCoPE-Reg的平均目标配准误差分别为0.73mm和2.27mm，而现有最优方法（SOTA）对应为1.24mm和2.63mm；在CAMUS上其峰值误差较SOTA降低56%（从12.5mm降至5.5mm），且分别有100%和80%的帧在3mm内完成配准。在128²分辨率的CAMUS上，随位姿扰动幅度增大，SCoPE-Reg仍保持最低误差。其参数量为6.49M，与分辨率无关，在512²分辨率下帧率达51 FPS。SCoPE-Reg在刚性超声SVR中达到最优性能：通过结合基于对应关系的精度、有界最坏情况误差与分辨率无关的成本，可在介入操作的原生采集分辨率下应用，而现有方法需在精度、可靠性或帧率间权衡。补充代码已提供，将在论文接收后开源。
英文摘要：
Ultrasound-guided interventions can require localization of an untracked 2D frame within a 3D anatomical reference. Rigid slice-to-volume registration (SVR) estimates this six-degree-of-freedom pose but remains challenging because of limited anatomical context, acoustic artifacts, and view-dependent appearance. Existing methods often use dense cross-attention, whose cost scales with the product of slice and volume token counts, or direct pose regression without explicit correspondence constraints. We introduce SCoPE-Reg, combining state-space slice--volume interaction, dense 3D coordinate prediction, and parameter-free weighted Kabsch estimation. On SVR tasks from CAMUS and $μ$-RegPro, SCoPE-Reg yields mean target registration errors of $0.73$ mm and $2.27$ mm against $1.24$ mm and $2.63$ mm for the state of the art (SOTA), reduces peak error on CAMUS by 56% below SOTA ($12.5\!\to\!5.5$ mm), and registers $100\%$ and $80\%$ of frames within $3$ mm. On CAMUS at $128^2$ it retains the lowest error at increasing pose-perturbation magnitude. It holds $6.49$ M parameters independent of resolution, sustaining $51$ FPS at $512^2$. SCoPE-Reg establishes a SOTA in rigid ultrasound SVR: by coupling correspondence-based accuracy with bounded worst-case error and resolution-independent cost, it becomes viable at native acquisition resolution during intervention, where prior methods trade accuracy, reliability, or frame rate against one another. Supplementary code provided and will be open-sourced upon acceptance.
