FgC2F-UDiff: Frequency-Guided and Coarse-to-Fine Unified Diffusion Model for Multi-Modality Missing MRI Synthesis

IF 4.2 2区 计算机科学 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Xiaojiao Xiao;Qinmin Vivian Hu;Guanghui Wang
{"title":"FgC2F-UDiff: Frequency-Guided and Coarse-to-Fine Unified Diffusion Model for Multi-Modality Missing MRI Synthesis","authors":"Xiaojiao Xiao;Qinmin Vivian Hu;Guanghui Wang","doi":"10.1109/TCI.2024.3516574","DOIUrl":null,"url":null,"abstract":"Multi-modality magnetic resonance imaging (MRI) is essential for the diagnosis and treatment of brain tumors. However, missing modalities are commonly observed due to limitations in scan time, scan corruption, artifacts, motion, and contrast agent intolerance. Synthesis of missing MRI has been a means to address the limitations of modality insufficiency in clinical practice and research. However, there are still some challenges, such as poor generalization, inaccurate non-linear mapping, and slow processing speeds. To address the aforementioned issues, we propose a novel unified synthesis model, the \n<bold>Frequency-guided and Coarse-to-fine Unified Diffusion Model (FgC2F-UDiff)</b>\n, designed for multiple inputs and outputs. Specifically, the Coarse-to-fine Unified Network (CUN) fully exploits the iterative denoising properties of diffusion models, from global to detail, by dividing the denoising process into two stages—coarse and fine—to enhance the fidelity of synthesized images. Secondly, the Frequency-guided Collaborative Strategy (FCS) harnesses appropriate frequency information as prior knowledge to guide the learning of a unified, highly non-linear mapping. Thirdly, the Specific-acceleration Hybrid Mechanism (SHM) integrates specific mechanisms to accelerate the diffusion model and enhance the feasibility of many-to-many synthesis. Extensive experimental evaluations have demonstrated that our proposed FgC2F-UDiff model achieves superior performance on two datasets, validated through a comprehensive assessment that includes both qualitative observations and quantitative metrics, such as PSNR SSIM, LPIPS, and FID.","PeriodicalId":56022,"journal":{"name":"IEEE Transactions on Computational Imaging","volume":"10 ","pages":"1815-1828"},"PeriodicalIF":4.2000,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Computational Imaging","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10794786/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Multi-modality magnetic resonance imaging (MRI) is essential for the diagnosis and treatment of brain tumors. However, missing modalities are commonly observed due to limitations in scan time, scan corruption, artifacts, motion, and contrast agent intolerance. Synthesis of missing MRI has been a means to address the limitations of modality insufficiency in clinical practice and research. However, there are still some challenges, such as poor generalization, inaccurate non-linear mapping, and slow processing speeds. To address the aforementioned issues, we propose a novel unified synthesis model, the Frequency-guided and Coarse-to-fine Unified Diffusion Model (FgC2F-UDiff) , designed for multiple inputs and outputs. Specifically, the Coarse-to-fine Unified Network (CUN) fully exploits the iterative denoising properties of diffusion models, from global to detail, by dividing the denoising process into two stages—coarse and fine—to enhance the fidelity of synthesized images. Secondly, the Frequency-guided Collaborative Strategy (FCS) harnesses appropriate frequency information as prior knowledge to guide the learning of a unified, highly non-linear mapping. Thirdly, the Specific-acceleration Hybrid Mechanism (SHM) integrates specific mechanisms to accelerate the diffusion model and enhance the feasibility of many-to-many synthesis. Extensive experimental evaluations have demonstrated that our proposed FgC2F-UDiff model achieves superior performance on two datasets, validated through a comprehensive assessment that includes both qualitative observations and quantitative metrics, such as PSNR SSIM, LPIPS, and FID.
求助全文
约1分钟内获得全文 求助全文
来源期刊
IEEE Transactions on Computational Imaging
IEEE Transactions on Computational Imaging Mathematics-Computational Mathematics
CiteScore
8.20
自引率
7.40%
发文量
59
期刊介绍: The IEEE Transactions on Computational Imaging will publish articles where computation plays an integral role in the image formation process. Papers will cover all areas of computational imaging ranging from fundamental theoretical methods to the latest innovative computational imaging system designs. Topics of interest will include advanced algorithms and mathematical techniques, model-based data inversion, methods for image and signal recovery from sparse and incomplete data, techniques for non-traditional sensing of image data, methods for dynamic information acquisition and extraction from imaging sensors, software and hardware for efficient computation in imaging systems, and highly novel imaging system design.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信