Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport
This work addresses the retrospective-to-prospective gap in medical imaging for improved reconstruction accuracy, representing a novel method for a known bottleneck.
The paper tackles the problem of medical image reconstruction from measurement data, where deep learning methods trained on simulated pairs degrade on real prospective data due to a gap between retrospective and prospective scenarios. The result is the introduction of KIDOT, a dynamic optimal transport framework that learns from unpaired data, achieving superior performance in MRI and CT reconstruction experiments.
Medical image reconstruction from measurement data is a vital but challenging inverse problem. Deep learning approaches have achieved promising results, but often requires paired measurement and high-quality images, which is typically simulated through a forward model, i.e., retrospective reconstruction. However, training on simulated pairs commonly leads to performance degradation on real prospective data due to the retrospective-to-prospective gap caused by incomplete imaging knowledge in simulation. To address this challenge, this paper introduces imaging Knowledge-Informed Dynamic Optimal Transport (KIDOT), a novel dynamic optimal transport framework with optimality in the sense of preserving consistency with imaging physics in transport, that conceptualizes reconstruction as finding a dynamic transport path. KIDOT learns from unpaired data by modeling reconstruction as a continuous evolution path from measurements to images, guided by an imaging knowledge-informed cost function and transport equation. This dynamic and knowledge-aware approach enhances robustness and better leverages unpaired data while respecting acquisition physics. Theoretically, we demonstrate that KIDOT naturally generalizes dynamic optimal transport, ensuring its mathematical rationale and solution existence. Extensive experiments on MRI and CT reconstruction demonstrate KIDOT's superior performance.