Back to Search
Start Over
ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks.
- Source :
-
Biomedical optics express [Biomed Opt Express] 2017 Jul 13; Vol. 8 (8), pp. 3627-3642. Date of Electronic Publication: 2017 Jul 13 (Print Publication: 2017). - Publication Year :
- 2017
-
Abstract
- Optical coherence tomography (OCT) is used for non-invasive diagnosis of diabetic macular edema assessing the retinal layers. In this paper, we propose a new fully convolutional deep architecture, termed ReLayNet, for end-to-end segmentation of retinal layers and fluid masses in eye OCT scans. ReLayNet uses a contracting path of convolutional blocks (encoders) to learn a hierarchy of contextual features, followed by an expansive path of convolutional blocks (decoders) for semantic segmentation. ReLayNet is trained to optimize a joint loss function comprising of weighted logistic regression and Dice overlap loss. The framework is validated on a publicly available benchmark dataset with comparisons against five state-of-the-art segmentation methods including two deep learning based approaches to substantiate its effectiveness.
Details
- Language :
- English
- ISSN :
- 2156-7085
- Volume :
- 8
- Issue :
- 8
- Database :
- MEDLINE
- Journal :
- Biomedical optics express
- Publication Type :
- Academic Journal
- Accession number :
- 28856040
- Full Text :
- https://doi.org/10.1364/BOE.8.003627