An optical flow approach to tracking colonoscopy video
An optical flow approach to tracking colonoscopy video
复制标题
DOI：
--
复制
发表时间：
--
期刊：
影响因子：
--
通讯作者：
Jianfei Liu;K. Subramanian;T. Yoo
中科院分区：
文献类型：
--
作者：
Jianfei Liu;K. Subramanian;T. Yoo
如果我们能够持续协调相应的虚拟结肠镜检查（来自术前 X 射线 CT 检查）和光学结肠镜检查图像，我们就可以补充光学结肠镜检查程序的临床价值。在这项工作中，我们演示了一种基于光流的计算机视觉算法，用于根据实时结肠镜检查视频计算自我运动，然后用于根据 X 射线 CT 数据导航和可视化相应的患者解剖结构。该算法的关键特点在于有效结合稀疏和稠密光流场来计算扩展焦点（FOE）； FOE 允许独立计算相机平移和旋转参数，直接有助于算法的准确性和鲁棒性。我们通过结肠模型和临床结肠镜检查数据进行了广泛的评估。我们构建了两个类似结肠的模型，一个直模型和一个弯曲模型来测量实际的结肠镜检查运动；通过将估计的运动参数（速度和位移）与地面实况进行比较来定量评估跟踪精度。以 10、15 和 20 mm/s 的速度收集了 30 个直线和弯曲的模型序列（每种速度进行 5 次试验），以模拟结肠镜检查过程中的典型速度。直线和弯曲体模的速度估计平均误差均在 3 mm/s 以内。在直线和弯曲模型中，总距离为 287-288 毫米的位移误差低于 7 毫米。算法的稳健性已在来自 20 名不同患者的 27 个光学结肠镜检查图像序列上成功得到证明，并且涵盖 5 个不同的结肠段。选择其中的特定序列来说明算法对以下因素的敏感性降低：(1) 记录中断、(2) 结肠分割错误、(3) 照明伪影、(4) 液体的存在和 (5) 结肠结构的变化，例如手术过程中的变形、息肉切除和手术工具移动。
We can supplement the clinical value of an optical colonoscopy procedure if we can continuously co-align corresponding virtual colonoscopy (from preoperative X-ray CT exam) and optical colonoscopy images. In this work, we demonstrate a computer vision algorithm based on optical flow to compute egomotion from live colonoscopy video, which is then used to navigate and visualize the corresponding patient anatomy from X-ray CT data. The key feature of the algorithm lies in the effective combination of sparse and dense optical flow fields to compute the focus of expansion (FOE); FOE permits independent computation of camera translational and rotational parameters, directly contributing to the algorithm's accuracy and robustness. We performed extensive evaluation via a colon phantom and clinical colonoscopy data. We constructed two colon like phantoms, a straight phantom and a curved phantom to measure actual colonoscopy motion; tracking accuracy was quantitatively evaluated by comparing estimated motion parameters (velocity and displacement) to ground truth. Thirty straight and curved phantom sequences were collected at 10, 15 and 20 mm/s (5 trials at each speed), to simulate typical velocities during colonoscopy procedures. The average error in velocity estimation was within 3 mm/s in both straight and curved phantoms. Displacement error was under 7 mm over a total distance of 287–288 mm in the straight and curved phantoms. Algorithm robustness was successfully demonstrated on 27 optical colonoscopy image sequences from 20 different patients, and spanning 5 different colon segments. Specific sequences among these were chosen to illustrate the algorithm's decreased sensitivity to (1) recording interruptions, (2) errors in colon segmentation, (3) illumination artifacts, (4) presence of fluid, and (5) changes in colon structure, such as deformation, polyp removal, and surgical tool movement during a procedure.