Simulator-generated training datasets as an alternative to using patient data for machine learning: An example in myocardial segmentation with MRI.
Christos G. XanthisDimitrios FilosKostas HarisAnthony H. AletrasPublished in: Comput. Methods Programs Biomed. (2021)
Keyphrases
- patient data
- healthy volunteers
- training dataset
- machine learning
- carotid artery
- phase contrast
- medical images
- clinical data
- medical data
- contrast enhanced
- magnetic resonance
- intraoperative
- region growing
- intensive care
- diffusion tensor images
- magnetic resonance images
- brain tumors
- mri images
- magnetic resonance imaging
- training data
- manual segmentation
- medical records
- automatic segmentation
- image segmentation
- medical imaging
- class labels
- segmentation algorithm
- ultrasound images
- semi supervised learning
- image analysis
- microscopy images
- accurate segmentation
- knowledge acquisition
- learning algorithm
- training samples
- decision trees
- mr images
- deformable models
- information extraction
- active learning
- tagged mri
- data analysis
- database
- left ventricular
- statistical analysis
- low contrast
- feature selection