Fully Automated Deep Learning Based Segmentation of Normal, Infarcted and Edema Regions from Multiple Cardiac MRI Sequences.
Xiaoran ZhangMichelle NogaKumaradevan PunithakumarPublished in: MyoPS@MICCAI (2020)
Keyphrases
- fully automated
- cardiac mri
- deep learning
- fully automatic
- magnetic resonance images
- physiological parameters
- manual segmentation
- left ventricle
- image regions
- unsupervised learning
- multiple objects
- machine learning
- seed points
- image segmentation
- segmented images
- left ventricular
- short axis
- medical images
- segmentation algorithm
- level set
- weakly supervised
- brain tumors
- ground truth
- image analysis
- pattern recognition
- shape prior
- semi automatic
- graph cuts
- input image
- high resolution
- seeded region growing