Multi-Level Dual-Attention Based CNN for Macular Optical Coherence Tomography Classification
- Submitting institution
-
University of Keele
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 358
- Type
- D - Journal article
- DOI
-
10.1109/LSP.2019.2949388
- Title of journal
- IEEE Signal Processing Letters
- Article number
- -
- First page
- 1793
- Volume
- 26
- Issue
- 12
- ISSN
- 1070-9908
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2019
- URL
-
https://ieeexplore.ieee.org/document/8882308
- 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
- Yes
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is one example of Mandal and his collaborators' state-of-the-art work using image analysis and deep convolutional neural networks to provide classification and identification of features of images (e.g. deformation in concrete https://doi.org/ffz6; food recognition https://doi.org/fd2h, melanoma identification https://doi.org/fgdp). The approach gains its efficacy from focusing on the salient coarser features and higher entropy regions of images -- here, eyes affected by two common diseases.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -