Encoder-Decoder CNN Models for Automatic Tracking of Tongue Contours in Real-time Ultrasound Data,Methods

当前位置： X-MOL 学术 › Methods › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Encoder-Decoder CNN Models for Automatic Tracking of Tongue Contours in Real-time Ultrasound Data
Methods ( IF 4.2 ) Pub Date : 2020-07-01 , DOI: 10.1016/j.ymeth.2020.05.011
M Hamed Mozaffari ₁ , Won-Sook Lee ₁

Affiliation

One application of medical ultrasound imaging is to visualize and characterize human tongue shape and motion in real-time to study healthy or impaired speech production. Due to the low-contrast characteristic and noisy nature of ultrasound images, it requires knowledge about the tongue structure and ultrasound data interpretation for users to recognize tongue locations and gestures easily. Moreover, quantitative analysis of tongue motion needs the tongue contour to be extracted, tracked and visualized instead of the whole tongue region. Manual tongue contour extraction is a cumbersome, subjective, and error-prone task. Furthermore, it is not a feasible solution for real-time applications where the tongue contour moves rapidly with nuance gestures. This paper presents two new deep neural networks (named BowNet models) that benefit from the ability of global prediction of encoding-decoding fully convolutional neural networks and the capability of full-resolution extraction of dilated convolutions. Both qualitatively and quantitatively studies over datasets from two ultrasound machines disclosed the outstanding performances of the proposed deep learning models in terms of performance speed and robustness. Experimental results also revealed a significant improvement in the accuracy of prediction maps due to the better exploration and exploitation ability of the proposed network models.

中文翻译：

用于在实时超声数据中自动跟踪舌头轮廓的编码器-解码器 CNN 模型

医学超声成像的一种应用是实时可视化和表征人类舌头的形状和运动，以研究健康或受损的言语产生。由于超声图像的低对比度特性和噪声特性，用户需要了解舌头结构和超声数据解释，才能轻松识别舌头位置和手势。此外，舌头运动的定量分析需要提取、跟踪和可视化舌头轮廓，而不是整个舌头区域。手动舌头轮廓提取是一项繁琐、主观且容易出错的任务。此外，对于舌头轮廓随着细微手势快速移动的实时应用，这不是一个可行的解决方案。本文介绍了两种新的深度神经网络（称为 BowNet 模型），它们受益于编码解码全卷积神经网络的全局预测能力和空洞卷积的全分辨率提取能力。对来自两台超声机器的数据集的定性和定量研究都揭示了所提出的深度学习模型在性能速度和鲁棒性方面的出色表现。实验结果还表明，由于所提出的网络模型具有更好的探索和开发能力，预测地图的准确性有了显着提高。对来自两台超声机器的数据集的定性和定量研究都揭示了所提出的深度学习模型在性能速度和鲁棒性方面的出色表现。实验结果还表明，由于所提出的网络模型具有更好的探索和开发能力，预测地图的准确性有了显着提高。对来自两台超声机器的数据集的定性和定量研究都揭示了所提出的深度学习模型在性能速度和鲁棒性方面的出色表现。实验结果还表明，由于所提出的网络模型具有更好的探索和开发能力，预测地图的准确性有了显着提高。

更新日期：2020-07-01

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11