Image registration is essential for medical image applications where alignment of voxels across multiple images is needed for qualitative or quantitative analysis. With recent advances in deep neural networks and parallel computing, deep learning-based medical image registration methods become competitive with their flexible modeling and fast inference capabilities. However, compared to traditional optimization-based registration methods, the speed advantage may come at the cost of registration performance at inference time. Besides, deep neural networks ideally demand large training datasets while optimization-based methods are training-free. To improve registration accuracy and data efficiency, we propose a novel image registration method, termed Recurrent Inference Image Registration (RIIR) network. RIIR is formulated as a meta-learning solver for the registration problem in an iterative manner. RIIR addresses the accuracy and data efficiency issues, by learning the update rule of optimization, with implicit regularization combined with explicit gradient input.

We extensively evaluated RIIR on brain MRI, lung CT, and quantitative cardiac MRI datasets, in terms of both registration accuracy and training data efficiency. Our experiments showed that RIIR outperformed a range of deep learning-based methods, even with only 5% of the training data, demonstrating high data efficiency. Key findings from our ablation studies highlighted the important added value of the hidden states introduced in the recurrent inference framework for meta-learning. Our proposed RIIR offers a highly data-efficient framework for deep learning-based medical image registration.

Purpose: To implement a free-breathing sequence for simultaneous quantification of (Formula presented.), (Formula presented.), and (Formula presented.) for comprehensive tissue characterization of the myocardium in a single scan using a multi-gradient-echo readout with saturation and (Formula presented.) preparation pulses. Methods: In the proposed Saturation And (Formula presented.) -prepared Relaxometry with Navigator-gating (SATURN) technique, a series of multi-gradient-echo (GRE) images with different magnetization preparations was acquired during free breathing. A total of 35 images were acquired in 26.5 ± 14.9 seconds using multiple saturation times and (Formula presented.) preparation durations and with imaging at 5 echo times. Bloch simulations and phantom experiments were used to validate a 5-parameter fit model for accurate relaxometry. Free-breathing simultaneous (Formula presented.), (Formula presented.), and (Formula presented.) measurements were performed in 10 healthy volunteers and 2 patients using SATURN at 3T and quantitatively compared to conventional single-parameter methods such as SASHA for (Formula presented.), (Formula presented.) -prepared bSSFP, and multi-GRE for (Formula presented.). Results: Simulations confirmed accurate fitting with the 5-parameter model. Phantom measurements showed good agreement with the reference methods in the relevant range for in vivo measurements. Compared to single-parameter methods comparable accuracy was achieved. SATURN produced in vivo parameter maps that were visually comparable to single-parameter methods. No significant difference between (Formula presented.), (Formula presented.), and (Formula presented.) times acquired with SATURN and single-parameter methods was shown in quantitative measurements (SATURN (Formula presented.), (Formula presented.), (Formula presented.); conventional methods: (Formula presented.), (Formula presented.), (Formula presented.); (Formula presented.)). Conclusion: SATURN enables simultaneous quantification of (Formula presented.), (Formula presented.), and (Formula presented.) in the myocardium for comprehensive tissue characterization with co-registered maps, in a single scan with good agreement to single-parameter methods.