DeTrac: Transfer Learning of Class Decomposed Medical Images in Convolutional Neural Networks
- Submitting institution
-
Birmingham City University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11Z_OP_D2016
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2020.2989273
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 74901
- Volume
- 8
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2020
- 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
-
-
- Research group(s)
-
-
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Decompose, Transfer, and Compose (DeTraC) approach is a novel Convolutional Neural Network architecture. DeTraC has achieved remarkable advances in the classification of real medical images (e.g. histological images of human colorectal cancer, chest X-ray images and mammogram images). DeTraC has inspired work on COVID-19 detection (e.g., DeTraC has been adopted to cope with data irregularities problem for the detection of COVID-19 cases using Chest X-ray images DOI: https://doi.org/10.1007/s10489-020-01829-7).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -