Deep Learning of Image Features from Unlabeled Data for Multiple Sclerosis Lesion Segmentation.
Youngjin YooTom BroschAnthony TraboulseeDavid K. B. LiRoger C. TamPublished in: MLMI (2014)
Keyphrases
- unlabeled data
- lesion segmentation
- multiple sclerosis
- image features
- semi supervised learning
- labeled data
- semi supervised
- magnetic resonance images
- active learning
- training data
- brain mri
- supervised learning
- clinical trials
- mr images
- unsupervised learning
- white matter
- text classification
- magnetic resonance
- labeled and unlabeled data
- learning algorithm
- training set
- computer vision
- feature vectors
- data points
- object recognition
- training examples
- prior knowledge
- magnetic resonance imaging
- weakly supervised
- pattern recognition
- brain tissue
- decision trees
- multiscale
- machine learning
- object categories
- medical images
- decision making
- co occurrence