Postnatal gestational age estimation of newborns using Small Sample Deep Learning
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1873108
- Type
- D - Journal article
- DOI
-
10.1016/j.imavis.2018.09.003
- Title of journal
- Image and Vision Computing
- Article number
- -
- First page
- 87
- Volume
- 83-84
- Issue
- -
- ISSN
- 0262-8856
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2018
- URL
-
-
- 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)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Complications related to preterm births (1.1% of all births) are the leading cause of death for children under five. Over 75% of these deaths are preventable with appropriate treatment, given by accurate Gestational Age (GA) estimation. Existing automatic methods (Ultra-Sound Scans) are accurate but expensive, while manual methods (Ballard Score) are widely available, but subjective. This paper presents a novel framework for postnatal GA estimation, using images of newborns, state-of-the-art computer vision methods, and decision-level data fusion. It is a follow-up to the paper which won the FG'17 Best Paper award.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -