SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss.
Gengxin XuChuan-Xian RenPublished in: CoRR (2022)
Keyphrases
- vessel segmentation
- retinal images
- neural network
- blood vessels
- artificial neural networks
- multiresolution
- low contrast
- vessel enhancement
- region growing
- back propagation
- multiscale
- region of interest
- diabetic retinopathy
- optical coherence tomography
- anatomical knowledge
- optic disc
- self organizing maps
- error concealment
- input image
- image segmentation
- error propagation