AdaPR: Adaptive Plane Reformatting for 4D flow MRI using deep reinforcement learning

Plane reformatting for Four-dimensional Phase Contrast Magnetic Resonance Imaging (4D flow MRI) is time-consuming and prone to inter-observer variability, which limits fast cardiovascular flow assessment. Deep reinforcement learning (DRL) trains agents to iteratively adjust plane position and orientation, enabling accurate plane reformatting without the need of detailed landmarks, making it suitable for images with limited contrast and resolution, such as 4D flow MRI. However, current DRL methods assume that test volumes share the same spatial alignment as training data, limiting generalization across scanners and institutions. To address this limitation, we introduce AdaPR (Adaptive Plane Reformatting), a DRL framework that uses a local coordinate system to navigate volumes with arbitrary positions and orientations.

We implemented AdaPR using the Asynchronous Advantage Actor-Critic (A3C) algorithm and validated on 88 4D flow MRI datasets acquired from multiple vendors, including patients with congenital heart disease.

AdaPR achieved a mean angular error of 6.12° ± 3.53°and distance error of 3.44 ± 3.02 mm, outperforming global coordinate DRL methods. AdaPR maintained consistent accuracy under different volume orientations and positions. Flow measurements from AdaPR planes showed no significant differences compared to two manual observers, with excellent correlation (R²= 0.972 and R²= 0.967), comparable to inter-observer agreement (R²= 0.969).

AdaPR provides robust, orientation-independent plane reformatting for 4D flow MRI, achieving flow quantification comparable to expert observers. Its adaptability across datasets and scanners makes it a promising candidate for other medical imaging applications beyond 4D flow MRI.