De-smokeGCN: Generative Cooperative Networks for Joint Surgical Smoke Detection and Removal
- Submitting institution
-
University of Chester
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 10034/622801
- Type
- D - Journal article
- DOI
-
10.1109/TMI.2019.2953717
- Title of journal
- IEEE Transactions on Medical Imaging
- Article number
- -
- First page
- 1615
- Volume
- 39
- Issue
- 5
- ISSN
- 0278-0062
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2019
- 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
- No
- 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
- Smoke detection and removal is a particular problem for image guided surgery such as in minimally invasive approaches where energy generating devices are used. A camera inside the patient (e.g. as part of an endoscope) sends images to a monitor and these can be obscured by the smoke. This collaborative work with the University of Bournemouth proposes a novel generative-collaborative learning scheme that filters out the smoke inspired by Generative Adversarial Networks. We demonstrate superior performance to the current state of the art when applied to simulated data and augurs well for clinical use.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -