Deep Learning in Ultrasound Images
Deep learning in ultrasound images is a very new application with many potential applications. Below is the paper presenting a deep learning based approach for identification of motor units in ultrasound of muscle tissues.
Recording and analyzing the bio-electric activity of motor units (MUs) in the muscles provide us with many insights. However, doing this in a non-invasive way is challenging.
Here comes the role of ultrafast ultrasound imaging.
Read this work to see how deep learning can be used to identify active MUs — providing: (i) segmentation of the spatial territories, and (ii) signal estimation of the mechanical response (We call it Twitch Train as it form a train of signals).
The full paper is available at: https://ieeexplore.ieee.org/document/9201287
If you are interested in the applications of deep learning in ultrasound images, keep an eye on this blog post. We will be adding more details here.
Full citation of the paper:
H. Ali, J. Umander, R. Rohlén and C. Grönlund, “A Deep Learning Pipeline for Identification of Motor Units in Musculoskeletal Ultrasound,” in IEEE Access, vol. 8, pp. 170595–170608, 2020.
