Accurate 3-D geometries of arteries and veins are important clinical data for diagnosis of arterial disease and intervention planning. Automatic segmentation of vessels in the transverse view suffers from the low lateral resolution and contrast. Convolutional neural networks are a promising tool for automatic segmentation of medical images, outperforming the traditional segmentation methods with high robustness. In this study, we aim to create a general, robust, and accurate method to segment the lumen-wall boundary of healthy central and peripheral vessels in large field-of-view freehand ultrasound (US) datasets. Data were acquired using the freehand US, in combination with a probe tracker. A total of ±36 000 cross-sectional images, acquired in the common, internal, and external carotid artery ( N = 37 ), in the radial, ulnar artery, and cephalic vein ( N = 12 ), and in the femoral artery ( N = 5 ) were included. To create masks (of the lumen) for training data, a conventional automatic segmentation method was used. The neural networks were trained on: 1) data of all vessels and 2) the carotid artery only. The performance was compared and tested using an open-access dataset. The recall, precision, DICE, and intersection over union (IoU) were calculated. Overall, segmentation was successful in the carotid and peripheral arteries. The Multires U-net architecture performs best overall with DICE = 0.93 when trained on the total dataset. Future studies will focus on the inclusion of vascular pathologies.

中文翻译：

---

使用卷积神经网络对横向超声图像中血管进行自动 3-D 几何评估的通用方法。

动脉和静脉的准确 3-D 几何形状是诊断动脉疾病和干预计划的重要临床数据。横向视图中血管的自动分割受到低横向分辨率和对比度的影响。卷积神经网络是一种很有前途的医学图像自动分割工具，其鲁棒性优于传统的分割方法。在这项研究中，我们的目标是创建一种通用、稳健且准确的方法来分割大视野徒手超声 (US) 数据集中健康中央和外围血管的管腔壁边界。使用手绘美国结合探针跟踪器获取数据。在颈总动脉、颈内动脉和颈外动脉（ N = 37 ）、桡动脉、尺动脉、和头静脉 (N = 12) 和股动脉 (N = 5) 被包括在内。为了为训练数据创建掩码（管腔的），使用了传统的自动分割方法。神经网络接受了以下训练：1) 所有血管的数据和 2) 仅颈动脉的数据。使用开放访问数据集对性能进行了比较和测试。计算了召回率、精度、DICE 和联合交集 (IoU)。总体而言，颈动脉和外周动脉的分割是成功的。当在总数据集上训练时，Multires U-net 架构在 DICE = 0.93 下整体表现最佳。未来的研究将侧重于纳入血管病理。神经网络接受了以下训练：1) 所有血管的数据和 2) 仅颈动脉的数据。使用开放访问数据集对性能进行了比较和测试。计算了召回率、精度、DICE 和联合交集 (IoU)。总体而言，颈动脉和外周动脉的分割是成功的。当在总数据集上训练时，Multires U-net 架构在 DICE = 0.93 下整体表现最佳。未来的研究将侧重于纳入血管病理。神经网络接受了以下训练：1) 所有血管的数据和 2) 仅颈动脉的数据。使用开放访问数据集对性能进行了比较和测试。计算了召回率、精度、DICE 和联合交集 (IoU)。总体而言，颈动脉和外周动脉的分割是成功的。当在总数据集上训练时，Multires U-net 架构在 DICE = 0.93 下整体表现最佳。未来的研究将侧重于纳入血管病理。当在总数据集上训练时，Multires U-net 架构在 DICE = 0.93 下整体表现最佳。未来的研究将侧重于纳入血管病理。当在总数据集上训练时，Multires U-net 架构在 DICE = 0.93 下整体表现最佳。未来的研究将侧重于纳入血管病理。