检索结果-内蒙古大学图书馆

Fluorescence molecular tomography via score-based generative model

OPTICS AND LASERS IN ENGINEERING 2025年 187卷

作者： He, Peng Lin, Jiayuan Zhu, Yin Wan, Qiao Wu, Chengzhong Wan, Wenbo Liu, Qiegen Nanchang Univ Sch Informat Engn Nanchang 330031 Peoples R China Nanchang Univ Jiangxi Prov Key Lab Adv Signal Proc & Intelligent Nanchang 330031 Peoples R China Jiangxi Commun Terminal Ind Technol Res Inst Co Lt Jian 343121 Peoples R China

Fluorescence Molecular Tomography (FMT) imaging is a non-invasive quantitative detection technique that locates and quantifies fluorescent molecular probes in biological tissue. However, due to the light scattering effect and the ill-posed nature of the inverse problem, it is difficult to accurately reconstruct the fluorescence distribution. Traditional iterative reconstruction methods rely on the selection of regularization parameters, and data-driven deep learning methods have insufficient interpretability. In order to improve the imaging quality, fluorescence molecular tomography via score-based generative model (FTSG) is proposed. Prior information about the fluorescence target distribution is extracted via score-based generative model, which is used as a regularization term constraint for an iterative process based on the physical model. FTSG is validated through simulations and experiments using fluorescent targets with different radii and edge-to-edge distances. Compared with traditional methods, FTSG offers better resolution and reconstruction quality. This method can effectively distinguish two fluorescent targets with an edge-to-edge distance of 1 mm.

关键词： Fluorescence molecular tomography Priori learning Image reconstruction score-based generative model

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Improved score-based generative model for Medical Imaging

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2024年第3期43卷 966-979页

作者： Wu, Weiwen Wang, Yanyang Liu, Qiegen Wang, Ge Zhang, Jianjia Sun Yat Sen Univ Sch Biomed Engn Shenzhen Campus Shenzhen 518107 Peoples R China Nanchang Univ Dept Informat Engn Nanchang 330031 Peoples R China Rensselaer Polytech Inst Dept Biomed Engn Troy NY 12180 USA

The score-based generative model (SGM) has demonstrated remarkable performance in addressing challenging under-determined inverse problems in medical imaging. However, acquiring high-quality training datasets for these models remains a formidable task, especially in medical image reconstructions. Prevalent noise perturbations or artifacts in low-dose Computed Tomography (CT) or under-sampled Magnetic Resonance Imaging (MRI) hinder the accurate estimation of data distribution gradients, thereby compromising the overall performance of SGMs when trained with these data. To alleviate this issue, we propose a wavelet-improved denoising technique to cooperate with the SGMs, ensuring effective and stable training. Specifically, the proposed method integrates a wavelet sub-network and the standard SGM sub-network into a unified framework, effectively alleviating inaccurate distribution of the data distribution gradient and enhancing the overall stability. The mutual feedback mechanism between the wavelet sub-network and the SGM sub-network empowers the neural network to learn accurate scores even when handling noisy samples. This combination results in a framework that exhibits superior stability during the learning process, leading to the generation of more precise and reliable reconstructed images. During the reconstruction process, we further enhance the robustness and quality of the reconstructed images by incorporating regularization constraint. Our experiments, which encompass various scenarios of low-dose and sparse-view CT, as well as MRI with varying under-sampling rates and masks, demonstrate the effectiveness of the proposed method by significantly enhanced the quality of the reconstructed images. Especially, our method with noisy training samples achieves comparable results to those obtained using clean data.

关键词： Image reconstruction Training Biomedical imaging Noise measurement Computed tomography Magnetic resonance imaging Data models magnetic resonance imaging image reconstruction score-based generative model wavelet transform regularization constraint

来源：评论

学校读者我要写书评

暂无评论

scoreSeg: Leveraging score-based generative model for Self-Supervised Semantic Segmentation of Remote Sensing

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 8818-8833页

作者： Lu, Junzhe He, Guangjun Dou, Hongkun Gao, Qing Fang, Leyuan Deng, Yue Beihang Univ Sch Astronaut Beijing 100191 Peoples R China Space Star Technol Co Ltd State Key Lab Space Ground Integrated Informat Tec Beijing 100095 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Hunan Univ Coll Elect & Informat Engn Changsha 410082 Peoples R China Peng Cheng Lab Shenzhen 518000 Peoples R China

The performance of semantic segmentation of remote sensing images (RSIs) heavily depends on the number of pixel-level annotations. In practice, the accumulation of pixel-level annotations for large RSIs is quite expensive or even impossible under certain scenarios. Here, we try to solve this data-intensive problem from the novel aspect of score-based self-supervise learning (SSL) and introduce a robust RSI semantic segmentation model called scoreSeg. Unlike traditional pixel-level SSL paradigms, the generative SSL mechanism in scoreSeg is simple in loss design and stable in pretraining, granting it an indispensable ability in dense feature learning from very large RSIs. In the model implementation, scoreSeg first extracts pixelwise representations of RSIs by pretraining a time-dependent score-based model on abundant off-the-shelf unlabeled RSIs. Then, to address the sparse feature problem in RSIs, the collected features from different timesteps and resolutions are aggregated together forming a rich feature map for downstream semantic segmentation. Experimental results on three datasets show that our proposed scoreSeg outperforms state-of-the-art (SOTA) SSL methods and alternative pretraining models on ImageNet by nontrivial margins, especially with very limited annotations.

关键词： Remote sensing score-based generative model self-supervised learning semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Metal Inpainting in CBCT Projections Using score-based generative model 20

Metal Inpainting in CBCT Projections Using Score-based Gener...

引用

20th IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Mei, Siyuan Fan, Fuxin Maier, Andreas Friedrich Alexander Univ Erlangen Nuremberg Pattern Recognit Lab Erlangen Germany

ISBN: (纸本)9781665473583

During the orthopaedic surgery, the insertion of metallic implants or screws is often performed under mobile C-arm systems. However, due to the high attenuation of metals, severe metal artifacts occur in 3D reconstructions, which degrade the image quality significantly. Therefore, many metal artifact reduction algorithms have been developed to reduce the artifacts, and metal inpainting in the projection domain is an essential step. In this work, a score-based generative model is trained on simulated knee projections, and the inpainted images are obtained by removing the noise in the conditional resampling process. The result implies that the inpainted images by the score-based generative model have more detailed information and achieve the lowest mean absolute error of 0.069 and the highest peak-signal-to-noise ratio of 43.07 compared with the inverse distance weighting interpolation method and the mask pyramid network. Besides, the score-based model can also recover projections with large circular and rectangular masks, showing its generalization in inpainting tasks.

关键词： Knee projection inpainting score-based generative model unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Early Step Skipping score-based generative model for Low-dose CT Denoising

Early Step Skipping Score-based Generative Model for Low-dos...

引用

2025 Conference on Medical Imaging

作者： Jung, Hojin Baek, Jongduk Yonsei Univ Coll Comp Dept Artificial Intelligence Seoul South Korea Yonsei Univ Sch Integrated Technol Seoul South Korea

ISBN: (纸本)9781510685888;9781510685895

Reducing patient radiation exposure in computed tomography (CT) imaging necessitates the use of low-dose CT (LDCT) scans. However, LDCT scans are accompanied by increased quantum noise and various artifacts that degrade image quality. Traditional denoising methods often lead to oversmoothing, failing to preserve crucial texture details. To address these issues, we utilize a diffusion model approach, specifically employing a pre-trained score-based generative model (SGM), for the denoising of LDCT images. We employ the Variance Preserving (VP) SDE framework and train our SGM on normal-dose CT (NDCT) data. Our novel approach bypasses the initial stages of the SGM inference process by directly utilizing LDCT images as if they were generated in these early steps. However, directly inserting LDCT images into the inference process is not effective due to differences in noise characteristics between LDCT noise and Gaussian noise. To mitigate this issue, we introduce the Langevin Markov Chain Monte Carlo (LMC) technique, which refines the LDCT images, aligning them more closely with the expected noise distribution encountered during training. Our method outperformed conventional approaches like FBPConvNet in preserving fine textures and reducing noise, as demonstrated by improved LPIPS scores. The application of the LMC technique further improved performance across all metrics, including RMSE, SSIM, and LPIPS, compared to the approach without LMC. In this work, we leverages the generative capabilities of SGM, providing a significant advancement in LDCT image processing without the need for paired training data.

关键词： score-based generative model Low-dose CT denoising Noise fitting Langevin Markov Chain Monte Carlo Fan-beam CT

来源：评论

学校读者我要写书评

暂无评论

Preconditioned score-based generative models

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年第7期133卷 1-27页

作者： Ma, Hengyuan Zhu, Xiatian Feng, Jianfeng Zhang, Li Fudan Univ Shanghai Peoples R China Univ Surrey Guildford England

score-based generative models (SGMs) have recently emerged as a promising class of generative models. However, a fundamental limitation is that their sampling process is slow due to a need for many (e.g., 2000) iterations of sequential computations. An intuitive acceleration method is to reduce the sampling iterations which however causes severe performance degradation. We assault this problem to the ill-conditioned issues of the Langevin dynamics and reverse diffusion in the sampling process. Under this insight, we propose a novel preconditioned diffusion sampling (PDS) method that leverages matrix preconditioning to alleviate the aforementioned problem. PDS alters the sampling process of a vanilla SGM at marginal extra computation cost and without model retraining. Theoretically, we prove that PDS preserves the output distribution of the SGM, with no risk of inducing systematical bias to the original sampling process. We further theoretically reveal a relation between the parameter of PDS and the sampling iterations, easing the parameter estimation under varying sampling iterations. Extensive experiments on various image datasets with a variety of resolutions and diversity validate that our PDS consistently accelerates off-the-shelf SGMs whilst maintaining the synthesis quality. In particular, PDS can accelerate by up to 28x\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$28\times $$\end{document} on more challenging high-resolution (1024x\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\times $$\end{document}1024) image generation. Compared with the latest generative models (e.g., CLD-SGM, DDIM, and Analytic

关键词： Image synethsis score-based generative model Preconditioning

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Optimization generative model for Stable Ultra-Sparse-View CT Reconstruction

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2024年第10期43卷 3461-3475页

作者： Wu, Weiwen Pan, Jiayi Wang, Yanyang Wang, Shaoyu Zhang, Jianjia Sun Yat sen Univ Sch Biomed Engn Shenzhen Campus Shenzhen 518063 Guangdong Peoples R China PLA Strateg Support Force Informat Engn Univ Sch Informat Syst Engn Zhengzhou 450001 Peoples R China

score-based generative model (SGM) has risen to prominence in sparse-view CT reconstruction due to its impressive generation capability. The consistency of data is crucial in guiding the reconstruction process in SGM-based reconstruction methods. However, the existing data consistency policy exhibits certain limitations. Firstly, it employs partial data from the reconstructed image of the iteration process for image updates, which leads to secondary artifacts with compromising image quality. Moreover, the updates to the SGM and data consistency are considered as distinct stages, disregarding their interdependent relationship. Additionally, the reference image used to compute gradients in the reconstruction process is derived from the intermediate result rather than ground truth. Motivated by the fact that a typical SGM yields distinct outcomes with different random noise inputs, we propose a Multi-channel Optimization generative model (MOGM) for stable ultra-sparse-view CT reconstruction by integrating a novel data consistency term into the stochastic differential equation model. Notably, the unique aspect of this data consistency component is its exclusive reliance on original data for effectively confining generation outcomes. Furthermore, we pioneer an inference strategy that traces back from the current iteration result to ground truth, enhancing reconstruction stability through foundational theoretical support. We also establish a multi-channel optimization reconstruction framework, where conventional iterative techniques are employed to seek the reconstruction solution. Quantitative and qualitative assessments on 23 views datasets from numerical simulation, clinical cardiac and sheep's lung underscore the superiority of MOGM over alternative methods. Reconstructing from just 10 and 7 views, our method consistently demonstrates exceptional performance.

关键词： Image reconstruction Computed tomography Mathematical models Data models Reconstruction algorithms Optimization Noise reduction image reconstruction sparse-view score-based generative model data consistency

来源：评论

学校读者我要写书评

暂无评论

Device Activity Detection and Channel Estimation Using score-based generative models in Massive MIMO

引用

ZTE Communications 2025年第1期23卷 53-62页

作者： TANG Chenyue LI Zeshen CHEN Zihan Howard H.YANG ZJU-UIUC Institute Zhejiang UniversityHaining 314400China Singapore University of Technology and Design Singapore 487372Singapore

The growing demand for wireless connectivity has made massive multiple-input multiple-output(MIMO)a cornerstone of modern communication *** optimize network performance and resource allocation,an efficient and robust approach is joint device activity detection and channel *** this paper,we present an approach utilizing score-based generative models to address the underdetermined nature of channel estimation,which is data-driven and well-suited for the complex and dynamic environment of massive MIMO *** experimental results,based on a comprehensive dataset generated through Monte-Carlo sampling,demonstrate the high precision of our channel estimation approach,with errors reduced to as low as-45 d B,and exceptional accuracy in detecting active devices.

关键词： activity detection channel estimation inverse problem score-based generative model massive MIMO

来源：评论

学校读者我要写书评

暂无评论

ENHANCING SPARSE PHOTOACOUSTIC TOMOGRAPHY RECONSTRUCTION WITH score-based generative modelS 21

ENHANCING SPARSE PHOTOACOUSTIC TOMOGRAPHY RECONSTRUCTION WIT...

引用

21st IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Tong, Shangqing Lan, Hengrong Jiang, Daohuai Nie, Liming Luo, Jianwen Gao, Fei ShanghaiTech Univ Sch Informat Sci & Technol Shanghai Peoples R China Tsinghua Univ Sch Biomed Engn Beijing Peoples R China Fujian Normal Univ Coll Photon & Elect Engn Fuzhou Peoples R China Guangdong Acad Med Sci Guangdong Prov Peoples Hosp Guangzhou Peoples R China

ISBN: (纸本)9798350313345;9798350313338

Photoacoustic tomography (PAT) is a newly emerged imaging modality which enables both high optical contrast and acoustic depth of penetration. Reconstructing images of photoacoustic tomography from limited amount of sensor data is among one of the major challenges in photoacoustic imaging. Previous works based on deep learning were trained in supervised fashion, which directly map the input partially known sensor data to the ground truth reconstructed from full field of view. score-based generative models played an increasingly significant role in generative modeling, which generates samples through the gradient of the logarithmic data distribution approximated with score matching. Leveraging this probabilistic model, we proposed scorePAT, which recovers the PAT images by iterative sampling between the stochastic differential equation solver and a constraint term utilizing the rotation consistency between the images and the measurements. As a fully unsupervised approach, our proposed method achieved competitive results with supervised counterparts while more robust to different photoacoustic measurement processes.

关键词： score-based generative model Photoacoustic Tomography Inverse Problem Deep Learning

来源：评论

学校读者我要写书评

暂无评论

MadSGM: Multivariate Anomaly Detection with score-based generative models 23

MadSGM: Multivariate Anomaly Detection with Score-based Gene...

引用

32nd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Lim, Haksoo Park, Sewon Kim, Minjung Lee, Jaehoon Lim, Seonkyu Park, Noseong Yonsei Univ Seoul South Korea Samsung SDS Seoul South Korea LG AI Res Seoul South Korea

ISBN: (纸本)9798400701245

The time-series anomaly detection is one of the most fundamental tasks for time-series. Unlike the time-series forecasting and classification, the time-series anomaly detection typically requires unsupervised (or self-supervised) training since collecting and labeling anomalous observations are difficult. In addition, most existing methods resort to limited forms of anomaly measurements and therefore, it is not clear whether they are optimal in all circumstances. To this end, we present a multivariate time-series anomaly detector based on score-based generative models, called MadSGM, which considers the broadest ever set of anomaly measurement factors: i) reconstruction-based, ii) density-based, and iii) gradient-based anomaly measurements. We also design a conditional score network and its denoising score matching loss for the time-series anomaly detection. Experiments on five real-world benchmark datasets illustrate that MadSGM achieves the most robust and accurate predictions.

关键词： Time-series data Anomaly detection score-based generative model

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：