The Right Prior for the Right Deformation: Rethinking Continuous Deformable Image Registration

📅 2026-08-17
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the performance degradation in continuous image registration caused by mismatches between implicit deformation priors and target motion patterns. We systematically investigate the impact of parameterization methods on registration accuracy by comparing SIREN, B-splines, and multi-resolution strategies. Consequently, we propose an "implicit prior-deformation matching" design principle that elucidates the applicability of different parameterizations. Building upon this principle, the proposed MR-D-BSCP method achieves state-of-the-art performance in both brain MRI and lung CT registration tasks. These results effectively validate the critical role of aligning implicit priors with deformation characteristics to enhance medical image registration accuracy, providing practical guidance for the design of continuous registration models.
📝 Abstract
Deformable image registration models implicitly encode deformation priors through their parametrization and optimization. In this work, we conduct a validation study on continuous registration methods to examine how these implicit priors affect performance across different registration tasks. Classic B-Spline transformations impose locality, smoothness, and scale through their control-point structure, whereas recent INR-based methods impose different priors through neural parameterization and optimization. We compare INR-Dense (IDIR), which directly models a dense displacement field using a SIREN-based INR; INR-BSCP (SINR), which predicts B-Spline control points with an INR; D-BSCP, which directly optimizes single-scale B-Spline control points; and MR-D-BSCP, which adds a multiresolution coarse-to-fine scheme. Experiments on inter-subject brain MR registration (OASIS) and intra-subject exhale-to-inhale lung CT registration (DIR-LAB 4DCT) reveal different behavior across deformation regimes. On OASIS, where deformations are moderate but locally complex, D-BSCP matches or slightly outperforms INR-BSCP, suggesting that the B-Spline parameterization accounts for much of INR-BSCP's effectiveness. On DIR-LAB 4DCT, where respiratory motion is larger and more coherent, single-scale B-Spline methods (D-BSCP and INR-BSCP) are less suitable, while INR-Dense and MR-D-BSCP are more effective. Across both tasks, MR-D-BSCP achieves the best performance among the tested continuous parameterizations. These findings highlight that registration accuracy depends strongly on matching the induced deformation prior to the target motion pattern, and support prior-deformation matching as a practical design principle for medical image registration. Our code will be available at https://github.com/HengjieLiu/RightPriorDIR.
Problem

Research questions and friction points this paper is trying to address.

Deformable Image Registration
Deformation Prior
Continuous Registration
Medical Image Registration
Innovation

Methods, ideas, or system contributions that make the work stand out.

Deformation Prior
Continuous Deformable Registration
Implicit Neural Representation
B-Spline Parametrization
Prior-Deformation Matching
💼 Related Jobs
No related jobs found.
H
Hengjie Liu
Department of Radiation Oncology, University of California, San Francisco, San Francisco, CA, USA
C
Chushu Shen
Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, USA
D
Dan Ruan
Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, USA; Department of Radiation Oncology, University of California, Los Angeles, Los Angeles, CA, USA
K
Ke Sheng
Department of Radiation Oncology, University of California, San Francisco, San Francisco, CA, USA