RealKeyMorph: Keypoints in Real-world Coordinates for Resolution-agnostic Image Registration

2025/06/12 by Mina C. Moghadam, Moghadam, Mina C., Alan Q. Wang +7
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Medical Image Segmentation Techniques #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.2506.10344

openalex publication_date 2025/06/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Many real-world settings require registration of a pair of medical images that differ in spatial resolution, which may arise from differences in image acquisition parameters like pixel spacing, slice thickness, and field-of-view. However, all previous machine learning-based registration techniques resample images onto a fixed resolution. This is suboptimal because resampling can introduce artifacts due to interpolation. To address this, we present RealKeyMorph (RKM), a resolution-agnostic method for image registration. RKM is an extension of KeyMorph, a registration framework which works by training a network to learn corresponding keypoints for a given pair of images, after which a closed-form keypoint matching step is used to derive the transformation that aligns them. To avoid resampling and enable operating on the raw data, RKM outputs keypoints in real-world coordinates of the scanner. To do this, we leverage the affine matrix produced by the scanner (e.g., MRI machine) that encodes the mapping from voxel coordinates to real world coordinates. By transforming keypoints into real-world space and integrating this into the training process, RKM effectively enables the extracted keypoints to be resolution-agnostic. In our experiments, we demonstrate the advantages of RKM on the registration task for orthogonal 2D stacks of abdominal MRIs, as well as 3D volumes with varying resolutions in brain datasets.

Citations

• Diffeomorphic Transformer-based Abdomen MRI-CT Deformable Image Registration
• A Robust and Interpretable Deep Learning Framework for Multi-modal Registration via Keypoints
• SVoRT: Iterative Transformer for Slice-to-Volume Registration in Fetal Brain MRI
• SAME: Deformable Image Registration based on Self-supervised Anatomical Embeddings
• HyperMorph: Amortized Hyperparameter Learning for Image Registration
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• Dual-Stream Pyramid Registration Network
• Image-and-Spatial Transformer Networks for Structure-Guided Image Registration
• Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representations
• Generative Adversarial Networks for MR-CT Deformable Image Registration
• Keypoint Transfer for Fast Whole-Body Segmentation
• LF-Net: Learning Local Features from Images
• SuperPoint: Self-Supervised Interest Point Detection and Description
• Learning to Find Good Correspondences
• Quicksilver: Fast Predictive Image Registration - a Deep Learning Approach
• Learning Covariant Feature Detectors
• LIFT: Learned Invariant Feature Transform
• FlowNet: Learning Optical Flow with Convolutional Networks
• Image quality assessment: from error visibility to structural similarity

Related

• A Robust and Interpretable Deep Learning Framework for Multi-modal Registration via Keypoints
• BrainMorph: A Foundational Keypoint Model for Robust and Flexible Brain MRI Registration
• MICS : Multi-steps, Inverse Consistency and Symmetric deep learning registration network
• Spatial regularisation for improved accuracy and interpretability in keypoint-based registration
• One registration is worth two segmentations