Reinforcement learning using Deep Q networks and Q learning accurately localizes brain tumors on MRI with very small training sets.
Joseph N. StemberHrithwik ShaluPublished in: BMC Medical Imaging (2022)
Keyphrases
- brain tumors
- reinforcement learning
- magnetic resonance images
- mr images
- function approximation
- brain tumor segmentation
- state space
- reinforcement learning algorithms
- mri images
- model free
- tumor segmentation
- mri scans
- brain images
- medical image analysis
- brain tissue
- stochastic approximation
- temporal difference learning
- magnetic resonance imaging
- optimal policy
- medical images
- multi agent
- multi agent reinforcement learning
- reinforcement learning methods
- real patient data
- learning algorithm
- magnetic resonance
- low grade gliomas
- machine learning
- endoscopic images
- temporal difference
- action selection
- mri data
- continuous state and action spaces
- markov decision processes
- continuous state spaces
- magnetic resonance spectroscopy
- high quality
- brain mr images
- rl algorithms
- control policy
- relational reinforcement learning
- action space
- white matter
- tumor growth
- mr imaging