Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow.
Qiao ZhengHervé DelingetteNicholas AyachePublished in: Medical Image Anal. (2019)
Keyphrases
- semi supervised learning
- supervised learning
- improve the classification accuracy
- semi supervised classification
- semi supervised
- wall motion
- unlabeled data
- co training
- machine learning
- cardiac imaging
- unsupervised learning
- labeled and unlabeled data
- semi supervised learning algorithms
- magnetic resonance imaging
- transductive support vector machine
- left ventricle
- mr imaging
- labeled data
- mr images
- tagged mri
- unlabeled samples
- active learning
- classification accuracy
- label propagation
- motion tracking
- manifold regularization
- class labels
- pattern recognition
- training data
- classification models
- magnetic resonance images
- beating heart
- mri data
- dimension reduction
- feature extraction
- text classification
- medical images
- transfer learning
- labeled instances
- training set
- support vector machine
- mri images
- left ventricular
- graph based semi supervised learning
- cardiac motion
- metric learning
- decision trees
- image reconstruction
- feature selection
- computer vision
- feature set
- feature space
- model selection
- training examples
- machine learning algorithms
- motion field