期刊
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL
卷 68, 期 11, 页码 3326-3335出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TUFFC.2021.3090461
关键词
Convolutional neural network; machine learning; medical image segmentation; vascular ultrasound (US)
资金
- Stichting Lijf and Leven
This study aimed to develop a robust method for vessel segmentation using convolutional neural networks, achieving successful segmentation in both carotid and peripheral arteries. The Multires U-net architecture performed best when trained on the total dataset. Future studies will focus on including vascular pathologies.
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-viewfreehandultrasound(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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据