Tongue model construction based on ultrasound images with image processing and deep learning method
Tongue model construction based on ultrasound images with image processing and deep learning method
复制标题
DOI：
10.1007/s10396-022-01193-8
复制
发表时间：
2022-02
影响因子：
1.8
通讯作者：
N. Mukai;Kimie Mori;Yoshiko Takei
中科院分区：
文献类型：
--
作者：
N. Mukai;Kimie Mori;Yoshiko Takei
目的构建舌体三维模型，并生成舌体运动动画，为舌体侧音（lateralarticulation，LA）患者的语音治疗提供依据。通过图像处理技术和深度学习方法从US图像中提取舌头表面来构建舌头模型。首先使用正常说话者的US图像生成参考舌模型，然后通过修改参考舌模型来构建LA患者的模型。舌运动的动画生成通过变形的模型，根据时间sequence.ResultsThe的准确性由深度学习方法估计的舌表面分别为22/45 = 49%和29/45 = 64%的美国图像的正常扬声器和LA患者，分别。此外，地面真理和估计的样条曲线之间的最大垂直误差为1.01和1.03毫米，为美国图像的正常扬声器和LA patients.ConclusionWe已经构建了一个舌头模型，并产生了舌头运动动画的LA患者使用美国图像。地面真实值和估计的样条曲线之间的最大垂直误差仅为1.03 mm，我们已经确认生成的舌模型对于LA患者的言语治疗非常有用。
PurposeThe purpose of this paper is to construct a 3D tongue model and to generate an animation of tongue movement for speech therapy in patients with lateral articulation (LA).MethodsThe 3D tongue model is generated based on ultrasound (US) images, which are widely used in many clinics. A tongue model is constructed by extracting the tongue surfaces from US images with the help of image processing techniques and a deep learning method. A reference tongue model is generated first using US images of a normal speaker, and a model of an LA patient is then constructed by modifying the reference tongue model. An animation of the tongue movement is generated by deforming the model according to a time sequence.ResultsThe accuracy of the tongue surfaces estimated by a deep learning method were 22/45 = 49% and 29/45 = 64% for US images of a normal speaker and an LA patient, respectively. In addition, the maximum vertical errors between the ground truth and the estimated spline curves were 1.01 and 1.03 mm for US images of a normal speaker and an LA patient, respectively.ConclusionWe have constructed a tongue model and generated a tongue movement animation of an LA patient using US images. The maximum vertical error between the ground truth and the estimated spline curves was only 1.03 mm, and we have confirmed that the generated tongue model is very useful for speech therapy in LA patients.