A novel method for unsupervised scanner-invariance with DCAE model
- Submitting institution
-
Queen's University of Belfast
- Unit of assessment
- 12 - Engineering
- Output identifier
- 161560317
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- British Machine Vision Conference (BMVC 2018)
- First page
- 1
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- September
- 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
- No
- Number of additional authors
-
5
- Research group(s)
-
C - Electrical and Electronic
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper reports part of the results of our research project funded by Philips Digital Pathology, studying deep learning and image recognition to histopathology image processing, for nuclei detection and cancer segmentation. We described a novel approach, the first of its kind, to achieve scanner-invariant representation of histopathology images. The new approach has significantly improved over existing approaches. The paper was presented in the highly prestigious and competitive BMVC 2018 (acceptance rate 29.5%). A more recent extension was presented in MIUA 2020, which was awarded the best paper in the conference.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -