An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy
- Submitting institution
-
Middlesex University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1417
- Type
- D - Journal article
- DOI
-
10.1038/s41598-020-59413-5
- Title of journal
- Scientific Reports
- Article number
- 2748
- First page
- 1
- Volume
- 10
- Issue
- 1
- ISSN
- 2045-2322
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2020
- URL
-
http://eprints.mdx.ac.uk/31034/
- 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
- No
- Number of additional authors
-
28
- Research group(s)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Detecting artefacts from endoscopic videos plays a significant part in the development of computer-aided systems, allowing clinicians to make correct clinical decisions in real-time while patients are undergoing endoscopic procedures. This paper is significant because it details the state-of-the-art algorithms that are applied to this task by the top 10 submissions to the Endoscopy Artefact Detection Challenge (EAD2019), and provides a much wider view on the pros and cons of each approach developed by these teams, leading to recommendations to both practical implementation and to expediting more theoretical development of machine learning methods.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -