Bridging Modalities: Joint Synthesis and Registration Framework for Aligning Diffusion MRI with T1-Weighted Images

2026-01-16

AI Summary

This work addresses the challenge of inaccurate registration between diffusion MRI (dMRI) and T1-weighted (T1w) images due to their substantial modality differences. To overcome this, the authors propose an unsupervised joint synthesis-and-registration framework that generates synthetic images with T1w-like contrast, thereby transforming the cross-modal registration problem into a more tractable intra-modal task. The method jointly optimizes local structural similarity and cross-modal statistical dependencies to enhance deformation field estimation. By integrating generative image synthesis, multi-scale similarity metrics, and unsupervised deformable learning, the framework achieves significantly improved registration accuracy compared to current state-of-the-art methods on two independent datasets.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Multimodal image registration between diffusion MRI (dMRI) and T1-weighted (T1w) MRI images is a critical step for aligning diffusion-weighted imaging (DWI) data with structural anatomical space. Traditional registration methods often struggle to ensure accuracy due to the large intensity differences between diffusion data and high-resolution anatomical structures. This paper proposes an unsupervised registration framework based on a generative registration network, which transforms the original multimodal registration problem between b0 and T1w images into a unimodal registration task between a generated image and the real T1w image. This effectively reduces the complexity of cross-modal registration. The framework first employs an image synthesis model to generate images with T1w-like contrast, and then learns a deformation field from the generated image to the fixed T1w image. The registration network jointly optimizes local structural similarity and cross-modal statistical dependency to improve deformation estimation accuracy. Experiments conducted on two independent datasets demonstrate that the proposed method outperforms several state-of-the-art approaches in multimodal registration tasks.

Problem

• multimodal registration
• diffusion MRI
• T1-weighted MRI
• image alignment
• cross-modal registration

Innovation

• multimodal registration
• image synthesis
• unsupervised learning
• diffusion MRI
• deformation estimation