SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss.
Gengxin XuChuan-Xian RenPublished in: Neurocomputing (2023)
Keyphrases
- vessel segmentation
- retinal images
- blood vessels
- neural network
- low contrast
- vessel enhancement
- multiresolution
- optic disc
- region growing
- multiscale
- error concealment
- diabetic retinopathy
- back propagation
- artificial neural networks
- optical coherence tomography
- image segmentation
- competitive learning
- error propagation
- image analysis
- anatomical knowledge
- region of interest
- scale space
- gray level
- higher order
- co occurrence
- motion estimation
- preprocessing