• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

X 射线源运动模糊建模与生成扩散去模糊在数字乳腺断层合成中的应用。

X-ray source motion blur modeling and deblurring with generative diffusion for digital breast tomosynthesis.

机构信息

Department of Radiology, University of Michigan, Ann Arbor, MI 48109, United States of America.

Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI 48109, United States of America.

出版信息

Phys Med Biol. 2024 May 14;69(11):115003. doi: 10.1088/1361-6560/ad40f8.

DOI:10.1088/1361-6560/ad40f8
PMID:38640913
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11103667/
Abstract

. Digital breast tomosynthesis (DBT) has significantly improved the diagnosis of breast cancer due to its high sensitivity and specificity in detecting breast lesions compared to two-dimensional mammography. However, one of the primary challenges in DBT is the image blur resulting from x-ray source motion, particularly in DBT systems with a source in continuous-motion mode. This motion-induced blur can degrade the spatial resolution of DBT images, potentially affecting the visibility of subtle lesions such as microcalcifications.. We addressed this issue by deriving an analytical in-plane source blur kernel for DBT images based on imaging geometry and proposing a post-processing image deblurring method with a generative diffusion model as an image prior.. We showed that the source blur could be approximated by a shift-invariant kernel over the DBT slice at a given height above the detector, and we validated the accuracy of our blur kernel modeling through simulation. We also demonstrated the ability of the diffusion model to generate realistic DBT images. The proposed deblurring method successfully enhanced spatial resolution when applied to DBT images reconstructed with detector blur and correlated noise modeling.. Our study demonstrated the advantages of modeling the imaging system components such as source motion blur for improving DBT image quality.

摘要

. 数字乳腺断层合成术(DBT)由于其在检测乳腺病变方面的高灵敏度和特异性,相比二维乳腺 X 线摄影术显著提高了乳腺癌的诊断水平。然而,DBT 中的一个主要挑战是由于射线源运动导致的图像模糊,特别是在射线源处于连续运动模式的 DBT 系统中。这种运动引起的模糊会降低 DBT 图像的空间分辨率,可能会影响到微钙化等细微病变的可视性。. 我们通过基于成像几何结构推导 DBT 图像的平面内源模糊核,并提出了一种基于生成式扩散模型的图像先验的后处理图像去模糊方法来解决这个问题。. 我们表明,在给定探测器上方高度的 DBT 切片上,源模糊可以用一个平移不变核来近似,并且通过模拟验证了我们的模糊核建模的准确性。我们还展示了扩散模型生成逼真的 DBT 图像的能力。当应用于具有探测器模糊和相关噪声建模的 DBT 图像重建时,所提出的去模糊方法成功地提高了空间分辨率。. 我们的研究表明,对成像系统组件(如源运动模糊)进行建模以提高 DBT 图像质量具有优势。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/4e9f3e438038/pmbad40f8f8_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/7b5fdb7c2251/pmbad40f8f1_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/107888687f88/pmbad40f8f2_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/92a5fee89582/pmbad40f8f3_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/db5cabf2aa71/pmbad40f8f5_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/71e45686c9d7/pmbad40f8f6_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/26da7677c36f/pmbad40f8f7_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/4e9f3e438038/pmbad40f8f8_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/7b5fdb7c2251/pmbad40f8f1_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/107888687f88/pmbad40f8f2_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/92a5fee89582/pmbad40f8f3_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/db5cabf2aa71/pmbad40f8f5_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/71e45686c9d7/pmbad40f8f6_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/26da7677c36f/pmbad40f8f7_lr.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4e14/11103667/4e9f3e438038/pmbad40f8f8_lr.jpg

相似文献

1
X-ray source motion blur modeling and deblurring with generative diffusion for digital breast tomosynthesis.X 射线源运动模糊建模与生成扩散去模糊在数字乳腺断层合成中的应用。
Phys Med Biol. 2024 May 14;69(11):115003. doi: 10.1088/1361-6560/ad40f8.
2
Effect of source blur on digital breast tomosynthesis reconstruction.源模糊度对数字乳腺断层合成重建的影响。
Med Phys. 2019 Dec;46(12):5572-5592. doi: 10.1002/mp.13801. Epub 2019 Oct 20.
3
Importance of point-by-point back projection correction for isocentric motion in digital breast tomosynthesis: relevance to morphology of structures such as microcalcifications.数字乳腺断层合成中针对等中心运动的逐点反投影校正的重要性:与微钙化等结构形态的相关性
Med Phys. 2007 Oct;34(10):3885-92. doi: 10.1118/1.2776256.
4
Image quality of microcalcifications in digital breast tomosynthesis: effects of projection-view distributions.数字乳腺断层合成中微钙化的图像质量:投影视角分布的影响。
Med Phys. 2011 Oct;38(10):5703-12. doi: 10.1118/1.3637492.
5
High resolution stationary digital breast tomosynthesis using distributed carbon nanotube x-ray source array.使用分布式碳纳米管 X 射线源阵列的高分辨率静态数字乳腺断层合成术。
Med Phys. 2012 Apr;39(4):2090-9. doi: 10.1118/1.3694667.
6
Design and characterization of a spatially distributed multibeam field emission x-ray source for stationary digital breast tomosynthesis.用于静止式数字乳腺断层合成的空间分布式多束场发射 X 射线源的设计与特性描述。
Med Phys. 2009 Oct;36(10):4389-99. doi: 10.1118/1.3213520.
7
Two-phase learning-based 3D deblurring method for digital breast tomosynthesis images.基于两阶段学习的数字乳腺断层合成图像三维去模糊方法。
PLoS One. 2022 Jan 24;17(1):e0262736. doi: 10.1371/journal.pone.0262736. eCollection 2022.
8
Segmented separable footprint projector for digital breast tomosynthesis and its application for subpixel reconstruction.用于数字乳腺断层合成的分段可分离式足迹投影仪及其在亚像素重建中的应用
Med Phys. 2017 Mar;44(3):986-1001. doi: 10.1002/mp.12092.
9
The effect of amorphous selenium detector thickness on dual-energy digital breast imaging.非晶硒探测器厚度对双能数字乳腺成像的影响。
Med Phys. 2014 Nov;41(11):111904. doi: 10.1118/1.4897244.
10
Model-based deep CNN-regularized reconstruction for digital breast tomosynthesis with a task-based CNN image assessment approach.基于模型的深度卷积神经网络正则化重建在基于任务的卷积神经网络图像评估方法下的数字乳腺断层合成
Phys Med Biol. 2023 Dec 13;68(24):245024. doi: 10.1088/1361-6560/ad0eb4.

本文引用的文献

1
Model-based deep CNN-regularized reconstruction for digital breast tomosynthesis with a task-based CNN image assessment approach.基于模型的深度卷积神经网络正则化重建在基于任务的卷积神经网络图像评估方法下的数字乳腺断层合成
Phys Med Biol. 2023 Dec 13;68(24):245024. doi: 10.1088/1361-6560/ad0eb4.
2
Mammographic Screening in Routine Practice: Multisite Study of Digital Breast Tomosynthesis and Digital Mammography Screenings.常规实践中的乳腺 X 光筛查:数字乳腺断层合成术和数字乳腺 X 光筛查的多地点研究。
Radiology. 2023 May;307(3):e221571. doi: 10.1148/radiol.221571. Epub 2023 Mar 14.
3
Image Super-Resolution via Iterative Refinement.
通过迭代细化实现图像超分辨率
IEEE Trans Pattern Anal Mach Intell. 2023 Apr;45(4):4713-4726. doi: 10.1109/TPAMI.2022.3204461. Epub 2023 Mar 7.
4
Effect of optical blurring of X-ray source on breast tomosynthesis image quality: Modulation transfer function, anatomical noise power spectrum, and signal detectability perspectives.X 射线源光学模糊对乳腺断层合成图像质量的影响:调制传递函数、解剖噪声功率谱和信号检测能力视角。
PLoS One. 2022 May 19;17(5):e0267850. doi: 10.1371/journal.pone.0267850. eCollection 2022.
5
DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring.DWDN:用于非盲图像去模糊的深度维纳反卷积网络。
IEEE Trans Pattern Anal Mach Intell. 2022 Dec;44(12):9960-9976. doi: 10.1109/TPAMI.2021.3138787. Epub 2022 Nov 7.
6
Deep Convolutional Neural Network With Adversarial Training for Denoising Digital Breast Tomosynthesis Images.基于对抗训练的深度卷积神经网络用于数字乳腺断层合成图像去噪。
IEEE Trans Med Imaging. 2021 Jul;40(7):1805-1816. doi: 10.1109/TMI.2021.3066896. Epub 2021 Jun 30.
7
Digital Breast Tomosynthesis: Update on Technology, Evidence, and Clinical Practice.数字乳腺断层合成技术:技术、证据和临床实践的更新。
Radiographics. 2021 Mar-Apr;41(2):321-337. doi: 10.1148/rg.2021200101. Epub 2021 Feb 5.
8
Effect of source blur on digital breast tomosynthesis reconstruction.源模糊度对数字乳腺断层合成重建的影响。
Med Phys. 2019 Dec;46(12):5572-5592. doi: 10.1002/mp.13801. Epub 2019 Oct 20.
9
Digital Breast Tomosynthesis: Concepts and Clinical Practice.数字乳腺断层合成:概念与临床实践。
Radiology. 2019 Jul;292(1):1-14. doi: 10.1148/radiol.2019180760. Epub 2019 May 14.
10
Evaluation of Digital Breast Tomosynthesis as Replacement of Full-Field Digital Mammography Using an In Silico Imaging Trial.数字乳腺断层合成作为全视野数字化乳腺摄影的替代方法的评估:一项基于计算机成像试验。
JAMA Netw Open. 2018 Nov 2;1(7):e185474. doi: 10.1001/jamanetworkopen.2018.5474.