Adaptive Conditional Contrast-Agnostic Deformable Image Registration with Uncertainty Estimation

2026-01-09

IEEE Transactions on Medical Imaging

AI Summary

This work proposes an adaptive, conditionally contrast-invariant deformable registration framework to address the poor generalization and low efficiency in multi-contrast medical image registration caused by nonlinear intensity variations. By integrating stochastic convolutional augmentation, an Adaptive Conditional Feature Modulator (ACFM), and contrast-invariant latent regularization, the method enables fast and accurate registration of unseen contrast images. Notably, it introduces a variance network for the first time to provide pixel-wise uncertainty estimates. Experimental results demonstrate that the proposed approach outperforms existing methods in both registration accuracy and cross-contrast generalization performance.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

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 optimisation 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.

Problem

• deformable image registration
• multi-contrast
• generalization
• contrast-agnostic
• uncertainty estimation

Innovation

• contrast-agnostic registration
• adaptive conditional feature modulation
• uncertainty estimation
• random convolution augmentation
• deformable image registration