cMeta-INR: cohort-informed meta-learning-based implicit neural representation for deformable registration-driven real-time volumetric MRI estimation

Objective: Rapid and accurate reconstruction of high-quality 3D magnetic resonance (MR) images from undersampled k-space data with variable sampling patterns remains a challenge due to limited available information and the need to preserve rich anatomical details. Deformable image registration provides a promising solution by warping a fully-sampled reference image to align with undersampled data acquired on-board (from an image-guided treatment delivery platform like MR-LINACs). In this study, we proposed a novel registration framework—cohort-informed meta-learning (cMeta)—to enhance the accuracy and efficiency of implicit neural representations for limited k-space data-driven patient-specific deformable image registration. Approach: cMeta-INR incorporated token-aware modulation and population-level deformation priors to guide an INR template-based meta-learning process. By encoding contextual information and leveraging cohort-informed priors, the resulting meta-learning framework enabled the INR to rapidly adapt to new registration cases with undersampled k-space data. Specifically, for the meta learning, a modulation module with token-awareness was introduced to modulate the INR template, and a pre-trained population-based registration network (KS-RegNet) was employed to generate coarse, reference deformation vector fields (DVFs) and latent embeddings for computing the deformation discrepancy loss and embedding similarity loss. During test-time adaptation, the INR, initialized from the meta-learned template, was efficiently fine-tuned to new k-space data with minimal iterations. Main results: Experiments were conducted on 14 abdominal and 11 cardiac 4D MRIs with 5-13 spokes. cMeta-INR outperformed state-of-the-art methods, achieving the best average (± s.d.) Dice similarity coefficients (0.778 ± 0.056 for abdominal and 0.894 ± 0.076 for cardiac data), and center-of-mass errors (3.04 ± 1.48 mm and 1.32 ± 1.02 mm, respectively), while enabling rapid test-time adaptation of only ~35 seconds on an NVIDIA H100 GPU. Significance: The proposed cohort-informed meta-learning framework effectively enhanced the adaptation capabilities of INRs to individual patients under highly undersampled k-space scenarios, demonstrating strong potential for fast and accurate patient-specific deformable registration.