Deep Learning-Based Acute Ischemic Stroke Lesion Segmentation Method on Multimodal MR Images Using a Few Fully Labeled Subjects.
Bin ZhaoZhiyang LiuGuohua LiuChen CaoSong JinHong WuShuxue DingPublished in: Comput. Math. Methods Medicine (2021)
Keyphrases
- segmentation method
- mr images
- ischemic stroke
- magnetic resonance
- medical images
- magnetic resonance images
- region growing
- manual segmentation
- active contours
- active contour model
- object segmentation
- nonrigid registration
- image segmentation
- image data
- energy function
- segmentation algorithm
- automated segmentation
- superpixels
- model based segmentation
- region of interest
- brain structures
- semi supervised
- ground truth
- magnetic resonance imaging
- anatomical structures
- probabilistic model
- intensity information
- high resolution
- shape prior
- machine learning