# Adaptive Conditional Contrast-Agnostic Deformable Image Registration with Uncertainty Estimation

Source: [Adaptive Conditional Contrast-Agnostic Deformable Image Registration with Uncertainty Estimation](<https://www.sota2.com/research/paper/69647fdd53fdd5c36174462b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-13T05:00:04.831Z

Authors: Yinsong Wang, Xinzhe Luo, Siyi Du, Chen Qin

Published: 2026-01-09T18:00:49.000Z

## Abstract

Deformable multi-contrast image registration is a challenging yet crucial task due to the complex, non-linear intensity relationships across different imaging contrasts. Conventional registration methods typically rely on iterative optimization of the deformation field, which is time-consuming. Although recent learning-based approaches enable fast and accurate registration during inference, their generalizability remains limited to the specific contrasts observed during training. In this work, we propose an adaptive conditional contrast-agnostic deformable image registration framework (AC-CAR) based on a random convolution-based contrast augmentation scheme. AC-CAR can generalize to arbitrary imaging contrasts without observing them during training. To encourage contrast-invariant feature learning, we propose an adaptive conditional feature modulator (ACFM) that adaptively modulates the features and the contrast-invariant latent regularization to enforce the consistency of the learned feature across different imaging contrasts. Additionally, we enable our framework to provide contrast-agnostic registration uncertainty by integrating a variance network that leverages the contrast-agnostic registration encoder to improve the trustworthiness and reliability of AC-CAR. Experimental results demonstrate that AC-CAR outperforms baseline methods in registration accuracy and exhibits superior generalization to unseen imaging contrasts. Code is available at https://github.com/Yinsong0510/AC-CAR.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Deformable Image Registration on CamCAN T1w→T2w](<https://www.sota2.com/research/sota/deformable-image-registration-on-camcan-t1w-t2w.md>): Deformable Image Registration; CamCAN T1w→T2w; Dice: 0.808.

- [3D Inter-patient Brain MRI Registration on IXI T1w to T2w (test)](<https://www.sota2.com/research/sota/3d-inter-patient-brain-mri-registration-on-ixi-t1w-to-t2w-test.md>): 3D Inter-patient Brain MRI Registration; IXI T1w to T2w (test); Dice: 80.5.

- [3D Inter-patient Brain MRI Registration on IXI T1w to PD (test)](<https://www.sota2.com/research/sota/3d-inter-patient-brain-mri-registration-on-ixi-t1w-to-pd-test.md>): 3D Inter-patient Brain MRI Registration; IXI T1w to PD (test); Dice: 79.6.

- [3D Inter-patient Brain MRI Registration on IXI T2w to PD (test)](<https://www.sota2.com/research/sota/3d-inter-patient-brain-mri-registration-on-ixi-t2w-to-pd-test.md>): 3D Inter-patient Brain MRI Registration; IXI T2w to PD (test); Dice: 79.1.

- [Deformable Image Registration on 3D CamCAN T2w→T1w](<https://www.sota2.com/research/sota/deformable-image-registration-on-3d-camcan-t2w-t1w.md>): Deformable Image Registration; 3D CamCAN T2w→T1w; Dice: 81.4.

- [Deformable Image Registration on 3D CamCAN T1w→T1w](<https://www.sota2.com/research/sota/deformable-image-registration-on-3d-camcan-t1w-t1w.md>): Deformable Image Registration; 3D CamCAN T1w→T1w; Dice Coefficient: 0.844.

- [Deformable Image Registration on 3D CamCAN T2w→T2w](<https://www.sota2.com/research/sota/deformable-image-registration-on-3d-camcan-t2w-t2w.md>): Deformable Image Registration; 3D CamCAN T2w→T2w; Dice: 0.799.

- [2D Cardiac MRI Registration on CMRxRecon T1 Mapping (test)](<https://www.sota2.com/research/sota/2d-cardiac-mri-registration-on-cmrxrecon-t1-mapping-test.md>): 2D cardiac MRI registration; CMRxRecon T1 Mapping (test); Dice: 87.6.

- [Deformable Image Registration on CMRxRecon (test)](<https://www.sota2.com/research/sota/deformable-image-registration-on-cmrxrecon-test.md>): Deformable Image Registration; CMRxRecon (test); Dice: 87.1.

- [Image Registration on Learn2Reg Abdominal CT-MR (test)](<https://www.sota2.com/research/sota/image-registration-on-learn2reg-abdominal-ct-mr-test.md>): Image Registration; Learn2Reg Abdominal CT-MR (test); Dice: 64.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.05981>)

[PDF](<https://arxiv.org/pdf/2601.05981.pdf>)
