M-MSSEU: source-free domain adaptation for multi-modal stroke lesion segmentation using shadowed sets and evidential uncertainty.
Zhicheng WangHongqing ZhuBingcang HuangZiying WangWeiping LuNing ChenYing WangPublished in: Health Inf. Sci. Syst. (2023)
Keyphrases
- multi modal
- domain adaptation
- multiple sources
- lesion segmentation
- target domain
- cross domain
- transfer learning
- labeled data
- multiple sclerosis
- semi supervised
- domain specific
- test data
- magnetic resonance images
- sentiment classification
- training data
- document classification
- semi supervised learning
- high dimensional
- training samples
- decision support system
- data points