Fast and accurate tumor segmentation of histology images using persistent homology and deep convolutional features
- Submitting institution
-
The University of Warwick
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 10574
- Type
- D - Journal article
- DOI
-
10.1016/j.media.2019.03.014
- Title of journal
- Medical Image Analysis
- Article number
- -
- First page
- 1
- Volume
- 55
- Issue
- -
- ISSN
- 1361-8415
- Open access status
- Compliant
- Month of publication
- July
- 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
-
6
- Research group(s)
-
A - Applied Computing
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Published in a top medical imaging journal, this article was the first to demonstrate that a combination of persistent homology features and deep convolutional features can achieve fast yet high-accuracy segmentation of tumour regions in histology images. An earlier version of this work won the Best Paper Award at MIUA'16, the premier UK conference on medical imaging, and formed the basis of a $1M award by the Japanese Ministry of Science and Technology. The licensing of software for this algorithm from Warwick University to Osaka University has led recently to the founding of APSAM Imaging Corporation [https://apsamimage.com] based in Osaka.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -