uniGradICON: A Foundation Model for Medical Image Registration
This addresses the problem of task-specific limitations in medical image registration for researchers and practitioners, offering a more versatile tool, though it is incremental as it builds on existing learning-based and conventional methods.
The authors tackled the lack of generality in deep learning-based medical image registration by proposing uniGradICON, a foundation model that achieves strong performance across multiple datasets, offers zero-shot capabilities for new tasks, and provides a good initialization for finetuning, unifying speed and accuracy with broad applicability.
Conventional medical image registration approaches directly optimize over the parameters of a transformation model. These approaches have been highly successful and are used generically for registrations of different anatomical regions. Recent deep registration networks are incredibly fast and accurate but are only trained for specific tasks. Hence, they are no longer generic registration approaches. We therefore propose uniGradICON, a first step toward a foundation model for registration providing 1) great performance \emph{across} multiple datasets which is not feasible for current learning-based registration methods, 2) zero-shot capabilities for new registration tasks suitable for different acquisitions, anatomical regions, and modalities compared to the training dataset, and 3) a strong initialization for finetuning on out-of-distribution registration tasks. UniGradICON unifies the speed and accuracy benefits of learning-based registration algorithms with the generic applicability of conventional non-deep-learning approaches. We extensively trained and evaluated uniGradICON on twelve different public datasets. Our code and the uniGradICON model are available at https://github.com/uncbiag/uniGradICON.