Improving cardiac MRI convolutional neural network segmentation on small training datasets and dataset shift: A continuous kernel cut approach.
Fumin GuoMatthew NgMaged GoubranSteffen E. PetersenStefan K. PiechnikStefan NeubauerGraham A. WrightPublished in: Medical Image Anal. (2020)
Keyphrases
- training dataset
- cardiac mri
- convolutional neural network
- physiological parameters
- left ventricle
- training data
- training set
- training samples
- face detection
- left ventricular
- magnetic resonance images
- small number
- support vector
- neural network
- wall thickness
- segmentation algorithm
- class labels
- image analysis
- decision trees
- level set
- synthetic data
- fully automatic
- image registration
- semi supervised
- short axis
- video sequences