Department of Biomedical Informatics, Institute of Biomaterials and Bioengineering, Tokyo Medical and Dental University, Tokyo 101-0062, Japan.
Department of Anesthesiology, Fukushima Medical University, Fukushima 960-1295, Japan.
Sensors (Basel). 2024 Jun 6;24(11):3696. doi: 10.3390/s24113696.
Ultrasound imaging is an essential tool in anesthesiology, particularly for ultrasound-guided peripheral nerve blocks (US-PNBs). However, challenges such as speckle noise, acoustic shadows, and variability in nerve appearance complicate the accurate localization of nerve tissues. To address this issue, this study introduces a deep convolutional neural network (DCNN), specifically Scaled-YOLOv4, and investigates an appropriate network model and input image scaling for nerve detection on ultrasound images. Utilizing two datasets, a public dataset and an original dataset, we evaluated the effects of model scale and input image size on detection performance. Our findings reveal that smaller input images and larger model scales significantly improve detection accuracy. The optimal configuration of model size and input image size not only achieved high detection accuracy but also demonstrated real-time processing capabilities.
超声成像是麻醉学中的一种重要工具，特别是对于超声引导下的外周神经阻滞（US-PNB）。然而，超声图像中存在的斑点噪声、声影和神经形态的变化等挑战，使得神经组织的准确定位变得复杂。为了解决这个问题，本研究引入了一个深度卷积神经网络（DCNN），即 Scaled-YOLOv4，并研究了一种合适的网络模型和输入图像缩放方法，用于在超声图像上检测神经。我们利用两个数据集，一个公共数据集和一个原始数据集，评估了模型规模和输入图像大小对检测性能的影响。我们的研究结果表明，较小的输入图像和较大的模型规模可以显著提高检测精度。模型尺寸和输入图像尺寸的最佳配置不仅实现了高精度的检测，还展示了实时处理的能力。
