Stochastic intervals speed up MRI image reconstruction with quality
Stochastic Finite-Transition Learning and Exploration for Accelerated MRI Reconstruction
Computer Vision and Pattern Recognition
Summary
MRI machines take pictures of the inside of your body by collecting data in steps. Making these pictures quickly and clearly can be hard because many small steps are needed. The authors propose a method called FLEX-MRI that divides the process into a few bigger steps and learns how to move between these steps, allowing for faster image creation. It also adds some randomness to explore different image possibilities, improving the final quality while keeping the process efficient.
What this means in practice
- •For medical imaging engineers: Help develop faster MRI reconstruction software that produces high-quality images with fewer processing steps.
- •For software developers in healthcare: Create MRI image reconstruction tools that balance speed and image fidelity, improving clinical workflow efficiency.
Authors
Muhammad Usama Mirza, Esin Öztürk Işık, Tolga Çukur
Abstract
Generative MRI reconstruction maps an initial source distribution to the target image distribution along a learned recovery trajectory. Common generative methods, such as diffusion and flow, typically learn fine-grained local dynamics whose integration defines this global mapping, hence requiring many network evaluations at inference. Existing few-step sampling approaches can lower computational burden by approximating large transformations from local dynamics, albeit at the expense of reconstruction fidelity. FLEX-MRI instead partitions recovery into a small number of finite intervals between retained states defined by progressive changes in k-space support, and directly learns the reconstruction change across each interval. Because such finite transitions can admit multiple plausible outcomes, FLEX-MRI combines support-relaxed finite-transition learning with stochastic exploration. During training, randomized k-space sampling masks define finite-transition targets with varying support, while the prediction loss remains unrestricted by each individual mask. At inference, FLEX-MRI perturbs a random subset of currently estimated k-space coefficients, allowing the learned predictor to stochastically explore alternative transition paths. Each predicted state is then reconciled with the acquired measurements through data consistency. We theoretically show that this stochastic exploration induces nonzero transition-level variation through the learned recovery map and data consistency without requiring an auxiliary generative sampler. Experiments on multi-coil MRI datasets show that FLEX-MRI outperforms competing methods while maintaining computational efficiency comparable to few-step baselines.