Tongue model construction based on ultrasound images with image processing and deep learning method

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.
Source: Journal of Medical Ultrasonics - Category: Radiology Source Type: research