SD-LayerNet: Semi-supervised retinal layer segmentation in OCT using disentangled representation with anatomical priors.
Botond FazekasGuilherme ArestaDmitrii A. LachinovSophie RiedlJulia MaiUrsula Schmidt-ErfurthHrvoje BogunovicPublished in: CoRR (2022)
Keyphrases
- optical coherence tomography
- oct images
- semi supervised
- medical images
- imaging modalities
- retinal images
- layered representation
- semi supervised learning
- multi directional
- image analysis
- parametric representation
- anatomical structures
- three dimensional
- pairwise
- segmentation method
- segmentation algorithm
- cross sections
- image segmentation
- fundus images
- vessel segmentation
- medical imaging
- labeled data
- prior model
- energy function
- brain mri
- magnetic resonance images
- multi view
- level set
- fully automatic
- multiscale
- deformable models