Unsupervised deep clustering and reinforcement learning can accurately segment MRI brain tumors with very small training sets.
Joseph N. StemberHrithwik ShaluPublished in: CoRR (2020)
Keyphrases
- brain tumors
- magnetic resonance images
- reinforcement learning
- mr images
- unsupervised learning
- mri images
- brain tumor segmentation
- magnetic resonance
- low grade gliomas
- brain tissue
- supervised learning
- tumor segmentation
- clustering algorithm
- unsupervised manner
- deformable registration
- medical images
- information bottleneck
- mri scans
- medical image analysis
- clustering method
- k means
- brain images
- cluster validation
- tumor growth
- mri data
- real patient data
- mr imaging
- magnetic resonance imaging
- deep architectures
- learning algorithm
- endoscopic images
- high quality
- image processing
- brain mr images
- cellular automata
- semi supervised
- ground truth
- machine learning
- web people search