Suppr超能文献

基于超声B模式图像的手术基准分割与跟踪以进行姿态估计

Surgical fiducial segmentation and tracking for pose estimation based on ultrasound B-mode images.

作者信息

Kuo Nathanael, Aalamifar Fereshteh, Narrow David, Coon Devin, Prince Jerry, Boctor Emad M

出版信息

Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:1244-1247. doi: 10.1109/EMBC.2016.7590931.

Abstract

Doppler ultrasound is a non-invasive diagnostic tool for the quantitative measurement of blood flow. However, given that it provides velocity data that is dependent on the location and angle of measurement, repeat measurements to detect problems over time may require an expert to return to the same location. We therefore developed an image-guidance system based on ultrasound B-mode images that enables an inexperienced user to position the ultrasound probe at the same site repeatedly in order to acquire a comparable time series of Doppler readings. The system utilizes a bioresorbable fiducial and complementing software composed of the fiducial detection, key points tracking, probe pose estimation, and graphical user interface (GUI) modules. The fiducial is an echogenic marker that is implanted at the surgical site and can be detected and tracked during ultrasound B-mode screening. The key points on the marker can next be used to determine the pose of the ultrasound probe with respect to the marker. The 3D representation of the probe with its position and orientation are then displayed in the GUI for the user guidance. The fiducial detection has been tested on the data sets collected from three animal studies. The pose estimation algorithm was validated by five data sets collected by a UR5 robot. We tested the system on a plastisol phantom and showed that it can detect and track the fiducial marker while displaying the probe pose in real-time.

摘要

多普勒超声是一种用于定量测量血流的非侵入性诊断工具。然而,由于它提供的速度数据取决于测量位置和角度,随着时间推移进行重复测量以检测问题可能需要专家回到同一位置。因此,我们开发了一种基于超声B模式图像的图像引导系统,使没有经验的用户能够将超声探头反复定位在同一位置,以便获取可比的多普勒读数时间序列。该系统利用一种可生物吸收的基准标记和由基准标记检测、关键点跟踪、探头姿态估计以及图形用户界面(GUI)模块组成的辅助软件。该基准标记是一种植入手术部位的回声标记,在超声B模式筛查期间能够被检测和跟踪。标记上的关键点接下来可用于确定超声探头相对于标记的姿态。然后,带有其位置和方向的探头的三维表示会显示在GUI中,为用户提供引导。基准标记检测已在从三项动物研究收集的数据集中进行了测试。姿态估计算法通过UR5机器人收集的五个数据集进行了验证。我们在一种增塑溶胶模型上对该系统进行了测试,结果表明它能够在实时显示探头姿态的同时检测和跟踪基准标记。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验