发表机构
University of Leeds（利兹大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PICO提出端到端多任务学习模型，通过投影损失和点对点损失增强几何一致性，在SurgRIPE数据集上实现鲁棒的6DoF手术器械姿态估计，尤其在遮挡场景下表现优异。
AI 中文摘要
目的：准确估计手术器械的6自由度（6DoF）姿态对于自动化、机器人本体感知以及与手术组织的安全交互至关重要。基于运动学的方法由于机器人手臂的线缆驱动特性而遭受累积误差，而基于视觉的方法通常依赖外部标记或跟踪器。尽管近期提出了更先进的基于视觉的方法，但这些两阶段姿态估计方法往往因累积误差和计算开销而缺乏实时鲁棒性。方法：我们提出了一种新颖的端到端可训练模型PICO。该模型采用多任务学习架构，在回归平移和旋转参数的同时，预测分割图和深度图。我们定义了两个代理任务，以在2D和3D空间中强制几何一致性，从而提高准确性和鲁棒性。为此，我们提出了投影损失和点对点损失。结果：我们在SurgRIPE数据集上评估了我们的方法，使用标准的6DoF姿态估计指标，将其性能与最先进的方法进行了基准比较。我们的结果表明，在所有四个子集上均表现出一致的强劲性能，特别是在旋转方面，即使在遮挡情况下也排名第二。同时，它在平移方面也表现出可比的性能，保持竞争力，尤其是在遮挡情况下。结论：PICO证明了多任务学习和几何感知代理任务在鲁棒可靠的手术器械姿态估计中的有效性，尤其是在遮挡场景中，突显了未来应用的潜力。
英文摘要
Purpose: Accurate 6 DoF pose estimation of surgical tools is critical for automa- tion, robotic proprioception, and safe interaction with the tissue operated on. Kinematics-based approaches suffer from accumulated errors due to the cable- driven nature of robotic arms, while vision-based methods often rely on external markers or trackers. Although more recent vision-based advances have been pro- posed, these two-stage pose estimation methods often lack real-time robustness due to accumulated errors and computational overhead. Methods: We propose a novel end-to-end trainable model, PICO. Our model employs a multi-task learning architecture to predict segmentation and depth maps, alongside regression of translation and rotation parameters. We define two proxy tasks that enforce geometric consistency in both 2D and 3D spaces, improving accuracy and robustness. For this, we propose a projection loss, and a point-to-point loss. Results: We evaluate our method on the SurgRIPE dataset, benchmarking its performance against state-of-the-art approaches using standard 6DoF pose esti- mation metrics. Our results demonstrate consistently strong performance across all four subsets, specifically in rotation, ranking second even under occlusion. It also demonstrates comparable translational performance, remaining competitive, especially in occluded cases. Conclusion: PICO demonstrates the effectiveness of multi-task learning and geometry-aware proxy tasks for robust and reliable surgical tool pose estimation, especially in occluded scenarios, highlighting potential for future applications.
Journal refInternational Journal of Computer Assisted Radiology and Surgery (2026)
DOI：10.1007/s11548-026-03802-0
