An automatic tool for quantification of nerve fibers in corneal confocal microscopy images
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1323525
- Type
- D - Journal article
- DOI
-
10.1109/TBME.2016.2573642
- Title of journal
- IEEE Transactions on Biomedical Engineering
- Article number
- -
- First page
- 786
- Volume
- 64
- Issue
- 4
- ISSN
- 0018-9294
- Open access status
- Compliant
- Month of publication
- June
- Year of publication
- 2016
- 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
-
5
- Research group(s)
-
-
- Citation count
- 43
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work is based on a classical machine learning framework using novel handcrafted features and random forest classifier to achieve fully automatic nerve fibre segmentation and quantification in confocal microscopic images. The developed software has significantly contributed to the clinical diagnosis of several neurodegenerative diseases (e.g. diabetes, dry eye, Parkinsons, etc). The software has been used free of charge by over 100 research groups worldwide and has been licenced for clinical trials, leading to several high-impact clinical publications. (Refer to: http://research.bmh.manchester.ac.uk/ena/ACCMetricsuserinstructions/ )
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
