Carotid plaque segmentation in ultrasound longitudinal B-mode images using deep learning is presented in this work. We report on 101 severely stenotic carotid plaque patients. A standard U-Net is compared with a dilated U-Net architecture in which the dilated convolution layers were used in the bottleneck. Both a fully automatic and a semi-automatic approach with a bounding box was implemented. The performance degradation in plaque segmentation due to errors in the bounding box is quantified. We found that the bounding box significantly improved the performance of the networks with U-Net Dice coefficients of 0.48 for automatic and 0.83 for semi-automatic segmentation of plaque. Similar results were also obtained for the dilated U-Net with Dice coefficients of 0.55 for automatic and 0.84 for semi-automatic when compared to manual segmentations of the same plaque by an experienced sonographer. A 5% error in the bounding box in both dimensions reduced the Dice coefficient to 0.79 and 0.80 for U-Net and dilated U-Net respectively.

中文翻译：

---

使用扩张的 U-Net 架构深度学习颈动脉斑块分割

在这项工作中介绍了使用深度学习的超声纵向 B 模式图像中的颈动脉斑块分割。我们报告了 101 名严重狭窄的颈动脉斑块患者。将标准 U-Net 与膨胀的 U-Net 架构进行比较，其中膨胀的卷积层用于瓶颈。实现了带有边界框的全自动和半自动方法。由于边界框错误导致斑块分割的性能下降被量化。我们发现边界框显着提高了网络的性能，自动分割 U-Net Dice 系数为 0.48，半自动分割斑块系数为 0.83。对于自动和 0 的 Dice 系数为 0.55 的扩张 U-Net，也获得了类似的结果。84 与经验丰富的超声医师对同一斑块的手动分割相比，半自动。两个维度中边界框的 5% 错误使 U-Net 和扩张的 U-Net 的 Dice 系数分别降低到 0.79 和 0.80。