Optimize Flip Angle Schedules In MR Fingerprinting Using Reinforcement Learning
This work addresses a domain-specific problem in medical imaging for MRF researchers, offering an incremental improvement in sequence optimization.
The paper tackled the problem of optimizing flip angle schedules in Magnetic Resonance Fingerprinting (MRF) by using reinforcement learning to automate parameter selection, resulting in a learned schedule that enhances fingerprint separability and may reduce repetition time to accelerate acquisitions.
Magnetic Resonance Fingerprinting (MRF) leverages transient-state signal dynamics generated by the tunable acquisition parameters, making the design of an optimal, robust sequence a complex, high-dimensional sequential decision problem, such as optimizing one of the key parameters, flip angle. Reinforcement learning (RL) offers a promising approach to automate parameter selection, to optimize pulse sequences that maximize the distinguishability of fingerprints across the parameter space. In this work, we introduce an RL framework for optimizing the flip-angle schedule in MRF and demonstrate a learned schedule exhibiting non-periodic patterns that enhances fingerprint separability. Additionally, an interesting observation is that the RL-optimized schedule may enable a reduction in the number of repetition time, potentially accelerate MRF acquisitions.