Fully automated image-based estimation of postural point-features in children with cerebral palsy using deep learning
- Submitting institution
-
Manchester Metropolitan University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2383
- Type
- D - Journal article
- DOI
-
10.1098/rsos.191011
- Title of journal
- Royal Society Open Science
- Article number
- 191011
- First page
- -
- Volume
- 6
- Issue
- 11
- ISSN
- 2054-5703
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2019
- URL
-
https://e-space.mmu.ac.uk/624142/
- 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
-
4
- Research group(s)
-
B - Human Centred-Computing
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first publication on the efficacy of marker-less automated tracking of postural features of children with cerebral palsy from images during physiotherapy sessions. This is significant progress towards an objective analysis of trunk control in children with neuromotor disability. This work is distinct in its approach to tracking the spine – we track multiple segments including curvature that cannot currently be achieved with ‘off the shelf’ methods. This publication contributed to the award of over £900,000 in MRC funding (MRC Ref: MR/T002034/1) to develop this technology in a significant cohort.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
