SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture with Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation.
Yifei ChenBinfeng ZouZhaoxin GuoYiyu HuangYifan HuangFeiwei QinQinhai LiChangmiao WangPublished in: WACV (2024)
Keyphrases
- hybrid architecture
- pulmonary embolism
- image segmentation
- dual energy
- completely automated
- lung parenchyma
- data fusion
- fused image
- agent architecture
- graph cuts
- fusion method
- fully automated
- multi sensor
- ct images
- medical images
- level set
- multiscale
- information fusion
- process management
- ct scans
- image fusion
- deformable models
- active contours
- x ray
- region growing
- computer vision
- gray level
- ground truth
- image analysis
- three dimensional
- image processing
- segmentation method
- energy function
- segmentation algorithm
- case study