Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation

2026-03-12

AI Summary

This work addresses the challenges of anatomical inconsistency and texture degradation in multimodal MRI synthesis caused by arbitrary missing modalities. To this end, the authors propose the MSG-LDM framework, which introduces a multi-scale style-structure disentanglement mechanism within a latent diffusion model. This approach explicitly separates modality-specific stylistic features from shared anatomical structures and jointly models low-frequency spatial layouts and high-frequency boundary details. By incorporating a structure-aware loss and style consistency constraints, the method significantly enhances structural stability and detail fidelity in synthesized images. Experimental results on the BraTS2020 and WMH datasets demonstrate that the proposed framework outperforms existing methods in both anatomical completeness and overall image quality.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Although diffusion models have achieved remarkable progress in multi-modal magnetic resonance imaging (MRI) translation tasks, existing methods still tend to suffer from anatomical inconsistencies or degraded texture details when handling arbitrary missing-modality scenarios. To address these issues, we propose a latent diffusion-based multi-modal MRI translation framework, termed MSG-LDM. By leveraging the available modalities, the proposed method infers complete structural information, which preserves reliable boundary details. Specifically, we introduce a style--structure disentanglement mechanism in the latent space, which explicitly separates modality-specific style features from shared structural representations, and jointly models low-frequency anatomical layouts and high-frequency boundary details in a multi-scale feature space. During the structure disentanglement stage, high-frequency structural information is explicitly incorporated to enhance feature representations, guiding the model to focus on fine-grained structural cues while learning modality-invariant low-frequency anatomical representations. Furthermore, to reduce interference from modality-specific styles and improve the stability of structure representations, we design a style consistency loss and a structure-aware loss. Extensive experiments on the BraTS2020 and WMH datasets demonstrate that the proposed method outperforms existing MRI synthesis approaches, particularly in reconstructing complete structures. The source code is publicly available at https://github.com/ziyi-start/MSG-LDM.

Problem

• multimodal MRI translation
• anatomical inconsistency
• texture degradation
• missing-modality scenarios

Innovation

• latent diffusion
• structure-style disentanglement
• multiscale feature modeling
• multimodal MRI translation
• anatomical consistency