Self-Supervised 2D/3D Registration for X-Ray to CT Image Fusion
This addresses the need for accurate image fusion in interventional medical scenarios without requiring costly annotated data, representing a strong specific gain.
The paper tackles the problem of 2D/3D registration for X-ray to CT image fusion without paired annotated datasets by proposing a self-supervised framework with domain adaptation, achieving a registration accuracy of 1.83±1.16 mm and a 90.1% success ratio on real X-ray images.
Deep Learning-based 2D/3D registration enables fast, robust, and accurate X-ray to CT image fusion when large annotated paired datasets are available for training. However, the need for paired CT volume and X-ray images with ground truth registration limits the applicability in interventional scenarios. An alternative is to use simulated X-ray projections from CT volumes, thus removing the need for paired annotated datasets. Deep Neural Networks trained exclusively on simulated X-ray projections can perform significantly worse on real X-ray images due to the domain gap. We propose a self-supervised 2D/3D registration framework combining simulated training with unsupervised feature and pixel space domain adaptation to overcome the domain gap and eliminate the need for paired annotated datasets. Our framework achieves a registration accuracy of 1.83$\pm$1.16 mm with a high success ratio of 90.1% on real X-ray images showing a 23.9% increase in success ratio compared to reference annotation-free algorithms.