Estimation of absolute states of human skeletal muscle via standard B-mode ultrasound imaging and deep convolutional neural networks
- Submitting institution
-
Manchester Metropolitan University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2547
- Type
- D - Journal article
- DOI
-
10.1098/rsif.2019.0715
- Title of journal
- Journal of The Royal Society Interface
- Article number
- 20190715
- First page
- -
- Volume
- 17
- Issue
- 162
- ISSN
- 1742-5662
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2020
- URL
-
https://doi.org/10.1098/rsif.2019.0715
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
1
- Research group(s)
-
B - Human Centred-Computing
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- To answer a first principles science question about human muscle, we innovated and engineered a computer vision solution based upon previous works pioneered in our lab (DOI: 10.1109/TMI.2016.2623819). We designed novel regional feature extractors from which to predict the continuous biomechanical state of deep muscle directly from a single ultrasound image. This work attempts to estimate the active motor and length state of muscle using ultrasound. We show for the first time, a generalised ability to model and extract this information, which has impact throughout medicine: neuromotor disability, injury, pain. We are collaborating with clinicians (christopher.kobylecki@manchester.ac.uk) to develop this work.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -