用粒子滤波提升心肌荧光成像追踪精度，实现实时手术导航。
Robust Tracking with Particle Filtering for Fluorescent Cardiac Imaging
- 基于循环一致性检查的粒子滤波算法，增强对心脏运动的鲁棒性。
- 同时追踪117个目标，帧率达25.4fps，误差仅5.00±0.22像素。
- 适合需高精度实时成像的外科手术场景，尤其冠状动脉搭桥术。
术中荧光心脏成像可实现冠状动脉旁路移植术后质量控制。通过追踪局部特征点，可估算心肌灌注等定量指标。然而，心脏运动及血管结构增强导致的图像特性剧烈波动，限制了传统追踪方法性能。本文提出一种基于循环一致性检查的粒子滤波追踪器，用于稳定追踪采样粒子以跟随目标地标。该方法可同步追踪117个目标，实现25.4 fps的实时处理，跟踪误差为(5.00 ± 0.22 px)，显著优于深度学习追踪器(22.3 ± 1.1 px)和传统追踪器(58.1 ± 27.1 px)。
原文摘要 · Abstract (English)
Intraoperative fluorescent cardiac imaging enables quality control following coronary bypass grafting surgery. We can estimate local quantitative indicators, such as cardiac perfusion, by tracking local feature points. However, heart motion and significant fluctuations in image characteristics caused by vessel structural enrichment limit traditional tracking methods. We propose a particle filtering tracker based on cyclicconsistency checks to robustly track particles sampled to follow target landmarks. Our method tracks 117 targets simultaneously at 25.4 fps, allowing real-time estimates during interventions. It achieves a tracking error of (5.00 +/- 0.22 px) and outperforms other deep learning trackers (22.3 +/- 1.1 px) and conventional trackers (58.1 +/- 27.1 px).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。