Improving the Segmentation of Anatomical Structures in Chest Radiographs using U-Net with an ImageNet Pre-trained Encoder.
Maayan Frid-AdarAvi Ben-CohenRula AmerHayit GreenspanPublished in: CoRR (2018)
Keyphrases
- anatomical structures
- medical images
- medical imaging
- pre trained
- chest radiographs
- x ray images
- x ray
- lung nodules
- computer aided diagnosis
- image segmentation
- image analysis
- deformable models
- segmentation method
- segmentation algorithm
- training data
- shape model
- ct images
- shape analysis
- multiscale
- motion estimation
- computer vision
- shape prior
- object classes
- control signals