Intelligent Parameter Tuning in Optimization-Based Iterative CT Reconstruction via Deep Reinforcement Learning

Keyphrases

• Parameter Tuning 100%
• Deep Reinforcement Learning (deep RL) 100%
• Policy Networks 60%
• Image Patch 20%
• Manual Parameters 20%
• Solution Quality 20%
• End-to-end Reinforcement Learning 20%
• Learning Procedure 20%

Computer Science

• Deep Reinforcement Learning 100%
• Reinforcement Learning 50%
• Solution Quality 50%

Engineering

• Reinforcement Learning 100%
• Image Patch 33%