Weakly supervised vessel segmentation in X-ray angiograms by self-paced learning from noisy labels with suggestive annotation.
Jingyang ZhangGuotai WangHongzhi XieShuyang ZhangNing HuangShaoting ZhangLixu GuPublished in: Neurocomputing (2020)
Keyphrases
- x ray
- weakly labeled
- vessel segmentation
- weakly supervised
- medical imaging
- region growing
- blood vessels
- retinal images
- topic models
- intraoperative
- superpixels
- vessel enhancement
- relation extraction
- object class
- semi supervised
- image segmentation
- three dimensional
- vessel tree
- ground truth
- viewpoint
- image annotation
- named entities
- domain specific
- co occurrence
- object detection
- image data
- color images
- object recognition
- multiscale
- machine learning