General Vision Encoder Features as Guidance in Medical Image Registration
This work addresses the problem of enhancing medical image registration accuracy for applications in healthcare, though it is incremental as it builds on existing registration frameworks.
The study investigated using general vision encoder features as guidance in medical image registration, finding that incorporating features from encoders like DINOv2 and SAM into conventional metrics improved registration quality on cardiac cine MRI data.
General vision encoders like DINOv2 and SAM have recently transformed computer vision. Even though they are trained on natural images, such encoder models have excelled in medical imaging, e.g., in classification, segmentation, and registration. However, no in-depth comparison of different state-of-the-art general vision encoders for medical registration is available. In this work, we investigate how well general vision encoder features can be used in the dissimilarity metrics for medical image registration. We explore two encoders that were trained on natural images as well as one that was fine-tuned on medical data. We apply the features within the well-established B-spline FFD registration framework. In extensive experiments on cardiac cine MRI data, we find that using features as additional guidance for conventional metrics improves the registration quality. The code is available at github.com/compai-lab/2024-miccai-koegl.