Supervised learning-based retinal vascular segmentation by M-UNet full convolutional neural network.
Heng DongTing ZhangTianyi ZhangLifang WeiPublished in: Signal Image Video Process. (2022)
Keyphrases
- convolutional neural network
- optical coherence tomography
- supervised learning
- blood vessels
- retinal images
- vessel segmentation
- fundus images
- oct images
- tubular structures
- vessel detection
- optic disc
- segmentation algorithm
- retinal fundus images
- image segmentation
- face detection
- level set
- segmentation method
- retinal blood vessels
- region growing
- learning algorithm
- unsupervised learning
- multiscale
- energy function
- neural network
- machine learning
- accurate segmentation
- imaging modalities
- segmentation accuracy
- low contrast
- image analysis
- training set
- fully automatic
- medical images
- moving objects
- pairwise
- shape prior
- deformable models
- active contours
- vascular tree
- reinforcement learning
- decision trees
- feature selection