Train a 3D U-Net to segment cranial vasculature in CTA volume without manual annotation.
Xuhui ChenYi LuJunjie BaiYoubing YinKunlin CaoYuwei LiHanbo ChenQi SongJun WuPublished in: ISBI (2018)
Keyphrases
- manual annotation
- fully automatic
- automatic annotation
- error prone
- semi automatic
- manually annotated
- automatic analysis
- automatic image annotation
- computed tomography angiography
- image annotation
- text classification
- machine learning
- semantic annotation
- content based retrieval
- video streams
- co occurrence
- ground truth
- image data
- feature space