OCT retinal image-to-image translation: Analysing the use of CycleGAN to improve retinal boundary semantic segmentation.
Ignacio A. ViedmaDavid Alonso-CaneiroScott A. ReadMichael J. CollinsPublished in: DICTA (2021)
Keyphrases
- retinal images
- semantic segmentation
- blood vessels
- fundus images
- optical coherence tomography
- region of interest
- retinal blood vessels
- optic disc
- vascular tree
- image analysis
- image features
- image data
- single image
- input image
- multiscale
- retinal fundus
- conditional random fields
- image segmentation
- weakly supervised
- image classification
- superpixels
- scene classification
- image retrieval
- object categories
- object classes
- segmentation method
- image representation
- pixel level
- semi supervised
- keypoints
- test images
- image matching
- object class
- image structure
- generative model
- d objects
- viewpoint
- image content