Semantic segmentation of computed tomography for radiotherapy with deep learning: compensating insufficient annotation quality using contour augmentation.
Umair JavaidDamien DasnoyJohn A. LeePublished in: Medical Imaging: Image Processing (2019)
Keyphrases
- deep learning
- computed tomography
- semantic segmentation
- weakly supervised
- ct images
- medical images
- medical imaging
- image reconstruction
- superpixels
- unsupervised learning
- three dimensional
- machine learning
- conditional random fields
- high quality
- semi supervised
- object class
- topic models
- active learning
- image segmentation
- image annotation
- pairwise
- relation extraction
- pattern recognition
- feature extraction
- deformable models
- active contours
- probabilistic model
- object classes
- object recognition