The objective is to test automated in vivo estimation of active and passive skeletal muscle states using ultrasonic imaging. Current technology (electromyography, dynamometry, shear wave imaging) provides no general, non-invasive method for online estimation of skeletal muscle states. Ultrasound (US) allows non-invasive imaging of muscle, yet current computational approaches have never achieved simultaneous extraction or generalization of independently varying active and passive states. We use deep learning to investigate the generalizable content of two-dimensional (2D) US muscle images. US data synchronized with electromyography of the calf muscles, with measures of joint moment/angle, were recorded from 32 healthy participants (seven female; ages: 27.5, 19-65). We extracted a region of interest of medial gastrocnemius and soleus using our prior developed accurate segmentation algorithm. From the segmented images, a deep convolutional neural network was trained to predict three absolute, drift-free components of the neurobiomechanical state (activity, joint angle, joint moment) during experimentally designed, simultaneous independent variation of passive (joint angle) and active (electromyography) inputs. For all 32 held-out participants (16-fold cross-validation) the ankle joint angle, electromyography and joint moment were estimated to accuracy 55 ± 8%, 57 ± 11% and 46 ± 9%, respectively. With 2D US imaging, deep neural networks can encode, in generalizable form, the activity-length-tension state relationship of these muscles. Observation-only, low-power 2D US imaging can provide a new category of technology for non-invasive estimation of neural output, length and tension in skeletal muscle. This proof of principle has value for personalized muscle assessment in pain, injury, neurological conditions, neuropathies, myopathies and ageing.
Keywords: contraction; deep learning; imaging; model; muscle; ultrasound.