Adversarial Uni- and Multi-modal Stream Networks for Multimodal Image Registration
This work addresses a critical problem in image-guided therapies by improving registration accuracy for medical imaging, though it appears incremental as it builds on existing translation-based approaches.
The paper tackles multimodal image registration between CT and MR images by proposing a novel unsupervised method that fuses deformation fields from translated and original images in a dual-stream network, achieving promising results compared to state-of-the-art methods on two clinical datasets.
Deformable image registration between Computed Tomography (CT) images and Magnetic Resonance (MR) imaging is essential for many image-guided therapies. In this paper, we propose a novel translation-based unsupervised deformable image registration method. Distinct from other translation-based methods that attempt to convert the multimodal problem (e.g., CT-to-MR) into a unimodal problem (e.g., MR-to-MR) via image-to-image translation, our method leverages the deformation fields estimated from both: (i) the translated MR image and (ii) the original CT image in a dual-stream fashion, and automatically learns how to fuse them to achieve better registration performance. The multimodal registration network can be effectively trained by computationally efficient similarity metrics without any ground-truth deformation. Our method has been evaluated on two clinical datasets and demonstrates promising results compared to state-of-the-art traditional and learning-based methods.