Efficient Medical Image Segmentation via Reinforcement Learning-Driven K-Space Sampling

Magnetic Resonance Imaging (MRI) excels in medical diagnostics with its superior soft tissue contrast and detailed anatomical visualization, providing critical support for precise medical image segmentation. However, traditional full K-space sampling is time-consuming, limiting efficiency in clinical settings. To address this challenge, we propose a novel method leveraging Reinforcement Learning (RL) to adaptively sample K-space, optimizing both MRI acquisition efficiency and segmentation accuracy. Our approach features an RL-driven policy network that strategically selects the most informative K-space samples, substantially reducing scan times while maintaining critical anatomical details. By integrating segmentation performance into the reward model, our method directly aligns the sampling process with accurate pathological segmentation. Furthermore, sparse K-space data are reconstructed into high-quality images, ensuring precise inputs for segmentation networks. Experiments on ACDC, AMOS, M&Ms-2, CHAOS and MSD datasets demonstrate that our approach not only accelerates MRI processing but also significantly enhances segmentation accuracy, showcasing its potential for clinical applications where speed and precision are paramount.