SonoMyoNet: A Convolutional Neural Network for Predicting Isometric Force From Highly Sparse Ultrasound Images

Abstract

Ultrasound imaging or sonomyography has been found to be a robust modality for sensing muscle activity due to its ability to directly image deep-seated muscles while providing superior spatiotemporal specificity compared to surface electromyography-based techniques. Quantifying the morphological changes during muscle activity involves computationally expensive approaches to track muscle anatomical structures or extracting features from B-mode images and A-mode signals. In this paper an offline regression convolutional neural network (CNN) called SonoMyoNet for estimating continuous isometric force from sparse ultrasound scanlines has been presented. SonoMyoNet learns features from a few equispaced scanlines selected from B-mode images and utilizes the learned features to accurately estimate continuous isometric force. The performance of SonoMyoNet was evaluated by varying the number of scanlines to simulate the placement of multiple single element ultrasound transducers in a wearable system. Results showed that SonoMyoNet could accurately predict isometric force with just four scanlines and is immune to speckle noise and shifts in the scanline location. Thus, the proposed network reduces the computational load involved in feature tracking algorithms and estimates muscle force from global features of sparse ultrasound images.