Self-supervised multi-magnification feature enhancement for segmentation of hepatocellular carcinoma region in pathological images.
Songhui DiaoXiang LiuXuan LiuBoyun ZhengJiahui HeYaoqin XieWenjian QinPublished in: Eng. Appl. Artif. Intell. (2024)
Keyphrases
- image regions
- segmented images
- segmented regions
- segmentation algorithm
- input image
- image features
- grey level
- test images
- segmentation method
- region segmentation
- cell nuclei
- image analysis
- segmentation scheme
- image pixels
- segmentation errors
- ground truth
- image data
- edge detection
- region of interest
- accurate segmentation
- segmentation result
- level set framework
- segmentation accuracy
- foreground and background
- homogeneous regions
- image segmentation
- adjacent regions
- salient regions
- fully automatic
- pixel level
- pixel wise
- initial segmentation
- gray level co occurrence matrix
- intensity distribution
- level set
- gradient information
- high resolution images
- primitive features
- microscopy images
- textural features
- feature vectors
- region boundaries
- image segments
- texture features
- object regions
- region features
- image retrieval
- gray value
- image gradient
- contrast enhancement
- object region
- optimal segmentation
- texture and shape features
- markov random field
- enhanced image
- intensity variations
- region growing
- shape prior
- image structure
- automatic segmentation
- bounding box
- image processing