Automatic Pathological Lung Segmentation in Low-Dose CT Image Using Eigenspace Sparse Shape Composition.
Geng ChenDehui XiangBin ZhangHaihong TianXiaoling YangFei ShiWeifang ZhuBei TianXinjian ChenPublished in: IEEE Trans. Medical Imaging (2019)
Keyphrases
- ct images
- low dose
- computed tomography
- lung nodules
- computer tomography
- ct scans
- medical images
- medical imaging
- automated segmentation
- lung parenchyma
- shape prior
- imaging modalities
- ct data
- shape analysis
- inter patient
- prostate segmentation
- dual energy
- fully automatic
- deformable models
- region of interest
- x ray
- ct volume
- treatment planning
- level set
- image segmentation
- anatomical structures
- lymph nodes
- shape model
- pulmonary nodules
- image reconstruction
- image analysis
- prior information
- segmentation algorithm
- computer vision
- image processing
- shape variations
- computer aided diagnosis
- medical image analysis
- magnetic resonance images
- magnetic resonance imaging
- remote sensing
- graph cuts
- input image
- clinical applications
- surface registration
- shape representation
- magnetic resonance
- segmentation method
- three dimensional