arXiv 2603.125812026-03-13eess.IVcs.AIcs.CV

多尺度结构引导的潜在扩散模型用于多模态MRI翻译

Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation

Computer Science and Engineering, Northeastern University, Shenyang, China（东北大学计算机科学与工程系，沈阳，中国）；Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University, Shenyang, China（教育部医学图像智能计算重点实验室，东北大学，沈阳，中国）；National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Shenyang, China（工业智能与系统优化国家级前沿科学中心，沈阳，中国）；Amii, University of Alberta, Edmonton, Alberta, Canada（阿尔伯塔大学阿米人工智能研究所，埃德蒙顿，阿尔伯塔，加拿大）；AiShiWeiLai AI Research, Beijing, China（人工智能研究（北京）有限公司，北京，中国）

Jianqiang Lin, Zhiqiang Shen, Peng Cao, Jinzhu Yang, Osmar R. Zaiane, Xiaoli Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出MSG-LDM框架，通过多尺度特征空间分离风格与结构信息，提升多模态MRI翻译的结构一致性与纹理细节。

摘要：

尽管扩散模型在多模态MRI翻译任务中取得了显著进展，但现有方法在处理任意缺失模态场景时仍面临解剖不一致或纹理细节退化的问题。为此，我们提出了一种基于潜在扩散的多模态MRI翻译框架MSG-LDM。通过利用可用模态，该方法推断出完整的结构信息，保持可靠的边界细节。具体而言，我们引入了潜在空间中的风格-结构解耦机制，将模态特定的风格特征与共享的结构表示显式分离，并在多尺度特征空间中联合建模低频解剖布局和高频边界细节。在结构解耦阶段，高频率的结构信息被显式纳入以增强特征表示，引导模型关注细粒度的结构线索，同时学习模态不变的低频解剖表示。此外，为了减少模态特定风格的干扰并提高结构表示的稳定性，我们设计了风格一致性损失和结构感知损失。在BraTS2020和WMH数据集上的大量实验表明，所提方法在重构完整结构方面优于现有MRI合成方法。源代码可在https://github.com/ziyi-start/MSG-LDM上公开获取。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。