用于病变分割的磁共振造影合成
MR CONTRAST SYNTHESIS FOR LESION SEGMENTATION.
作者信息
Roy Snehashis, Carass Aaron, Shiee Navid, Pham Dzung L, Prince Jerry L
机构信息
Image Analysis and Communications Laboratory, Electrical and Computer Engineering, The Johns Hopkins University.
出版信息
Proc IEEE Int Symp Biomed Imaging. 2010 Jun 21;2010:932-935. doi: 10.1109/ISBI.2010.5490140.
Abstract
The magnetic resonance contrast of a neuroimaging data set has strong impact on the utility of the data in image analysis tasks, such as registration and segmentation. Lengthy acquisition times often prevent routine acquisition of multiple MR contrast images, and opportunities for detailed analysis using these data would seem to be irrevocably lost. This paper describes an example based approach which uses patch matching from a multiple contrast atlas with the intended goal of generating an alternate MR contrast image, thus effectively simulating alternative pulse sequences from one another. In this paper, we deal specifically with Fluid Attenuated Inversion Recovery (FLAIR) sequence generation from T1 and T2 pulse sequences. The applicability of this synthetic FLAIR for estimating white matter lesions segmentation is demonstrated.
摘要
神经成像数据集的磁共振对比度对图像分析任务（如配准和分割）中数据的效用有很大影响。较长的采集时间常常阻碍多个磁共振对比度图像的常规采集，使用这些数据进行详细分析的机会似乎将不可挽回地丧失。本文描述了一种基于示例的方法，该方法使用来自多对比度图谱的补丁匹配，目的是生成替代的磁共振对比度图像，从而有效地相互模拟替代脉冲序列。在本文中，我们专门处理从T1和T2脉冲序列生成液体衰减反转恢复（FLAIR）序列。证明了这种合成FLAIR在估计白质病变分割方面的适用性。
相似文献
1
MR CONTRAST SYNTHESIS FOR LESION SEGMENTATION.用于病变分割的磁共振造影合成
Proc IEEE Int Symp Biomed Imaging. 2010 Jun 21;2010:932-935. doi: 10.1109/ISBI.2010.5490140.
2
Synthesizing MR Contrast and Resolution through a Patch Matching Technique.通过补丁匹配技术合成磁共振成像对比度与分辨率
Proc SPIE Int Soc Opt Eng. 2010;7623:76230j. doi: 10.1117/12.844575.
3
T1-weighted fluid-attenuated inversion recovery and T1-weighted fast spin-echo contrast-enhanced imaging: a comparison in 20 patients with brain lesions.T1加权液体衰减反转恢复序列与T1加权快速自旋回波对比增强成像：20例脑病变患者的比较
J Med Imaging Radiat Oncol. 2009 Aug;53(4):366-72. doi: 10.1111/j.1754-9485.2009.02093.x.
4
Targeted magnetic resonance imaging (tMRI) of small changes in the T and spatial properties of normal or near normal appearing white and gray matter in disease of the brain using divided subtracted inversion recovery (dSIR) and divided reverse subtracted inversion recovery (drSIR) sequences.利用分割减法反转恢复（dSIR）序列和分割反向减法反转恢复（drSIR）序列，对脑部疾病中正常或接近正常的白质和灰质的T值及空间特性的微小变化进行靶向磁共振成像（tMRI）。
Quant Imaging Med Surg. 2023 Oct 1;13(10):7304-7337. doi: 10.21037/qims-23-232. Epub 2023 Aug 15.
5
Relationship between contrast enhancement on fluid-attenuated inversion recovery MR sequences and signal intensity on T2-weighted MR images: visual evaluation of brain tumors.液体衰减反转恢复磁共振序列上的对比增强与T2加权磁共振图像上的信号强度之间的关系：脑肿瘤的视觉评估
J Magn Reson Imaging. 2005 Jun;21(6):694-700. doi: 10.1002/jmri.20331.
6
Image quality at synthetic brain magnetic resonance imaging in children.儿童合成脑磁共振成像的图像质量
Pediatr Radiol. 2017 Nov;47(12):1638-1647. doi: 10.1007/s00247-017-3913-y. Epub 2017 Jun 22.
7
[Evaluation of Improvement of Tissue Contrast and Reduction of Imaging Time by Shortening TR in Brain T FLAIR Using MTC Pulse].[使用MTC脉冲缩短脑T2加权液体衰减反转恢复序列（T FLAIR）中的重复时间（TR）对组织对比度改善和成像时间缩短的评估]
Nihon Hoshasen Gijutsu Gakkai Zasshi. 2020;76(12):1256-1265. doi: 10.6009/jjrt.2020_JSRT_76.12.1256.
8
Synthetic double inversion recovery imaging in brain MRI: quantitative evaluation and feasibility of synthetic MRI and a comparison with conventional double inversion recovery and fluid-attenuated inversion recovery sequences.脑 MRI 中的合成双反转恢复成像：合成 MRI 的定量评估和可行性，以及与常规双反转恢复和液体衰减反转恢复序列的比较。
BMC Med Imaging. 2022 Oct 27;22(1):183. doi: 10.1186/s12880-022-00877-4.
9
Are multi-contrast magnetic resonance images necessary for segmenting multiple sclerosis brains? A large cohort study based on deep learning.多对比度磁共振成像对于多发性硬化症大脑的分割是否必要？一项基于深度学习的大型队列研究。
Magn Reson Imaging. 2020 Jan;65:8-14. doi: 10.1016/j.mri.2019.10.003. Epub 2019 Oct 25.
10
Reducing annotation burden in MR: A novel MR-contrast guided contrastive learning approach for image segmentation.减少磁共振成像中的标注负担：一种新的基于磁共振对比引导的对比学习方法用于图像分割。
Med Phys. 2024 Apr;51(4):2707-2720. doi: 10.1002/mp.16820. Epub 2023 Nov 13.
引用本文的文献
1
One Model to Synthesize Them All: Multi-Contrast Multi-Scale Transformer for Missing Data Imputation.一模型统合之：用于缺失数据插补的多对比多尺度变换模型。
IEEE Trans Med Imaging. 2023 Sep;42(9):2577-2591. doi: 10.1109/TMI.2023.3261707. Epub 2023 Aug 31.
2
Generalizing deep whole-brain segmentation for post-contrast MRI with transfer learning.通过迁移学习实现增强后MRI全脑深度分割的泛化
J Med Imaging (Bellingham). 2020 Nov;7(6):064004. doi: 10.1117/1.JMI.7.6.064004. Epub 2020 Dec 23.
3
Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis.使用改进的 Sørensen-Dice 分析评估脑白质病变分割。
Sci Rep. 2020 May 19;10(1):8242. doi: 10.1038/s41598-020-64803-w.
4
Fluid-attenuated inversion recovery MRI synthesis from multisequence MRI using three-dimensional fully convolutional networks for multiple sclerosis.利用三维全卷积网络从多序列磁共振成像进行液体衰减反转恢复磁共振成像合成以用于多发性硬化症研究
J Med Imaging (Bellingham). 2019 Jan;6(1):014005. doi: 10.1117/1.JMI.6.1.014005. Epub 2019 Feb 19.
5
Registration of Pathological Images.病理图像的登记
Simul Synth Med Imaging. 2016 Oct;9968:97-107. doi: 10.1007/978-3-319-46630-9_10. Epub 2016 Sep 23.
6
Learning Implicit Brain MRI Manifolds with Deep Learning.利用深度学习学习隐式脑磁共振成像流形
Proc SPIE Int Soc Opt Eng. 2018 Mar;10574. doi: 10.1117/12.2293515.
7
Brain lesion segmentation through image synthesis and outlier detection.通过图像合成和异常值检测进行脑损伤分割。
Neuroimage Clin. 2017 Sep 8;16:643-658. doi: 10.1016/j.nicl.2017.09.003. eCollection 2017.
8
Deep embedding convolutional neural network for synthesizing CT image from T1-Weighted MR image.基于深度嵌入卷积神经网络的 T1 加权磁共振图像到 CT 图像的合成。
Med Image Anal. 2018 Jul;47:31-44. doi: 10.1016/j.media.2018.03.011. Epub 2018 Mar 30.
9
Dual-core steered non-rigid registration for multi-modal images via bi-directional image synthesis.基于双向图像合成的双模图像双核心导向非刚性配准。
Med Image Anal. 2017 Oct;41:18-31. doi: 10.1016/j.media.2017.05.004. Epub 2017 May 13.
10
Patch Based Synthesis of Whole Head MR Images: Application to EPI Distortion Correction.基于补丁的全脑磁共振图像合成：在回波平面成像失真校正中的应用。
Simul Synth Med Imaging. 2016 Oct;9968:146-156. doi: 10.1007/978-3-319-46630-9_15. Epub 2016 Sep 23.
本文引用的文献
1
A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions.一种保持拓扑结构的方法，用于分割多发性硬化病变的脑图像。
Neuroimage. 2010 Jan 15;49(2):1524-35. doi: 10.1016/j.neuroimage.2009.09.005. Epub 2009 Sep 17.
2
Topology-preserving tissue classification of magnetic resonance brain images.磁共振脑图像的拓扑保持组织分类
IEEE Trans Med Imaging. 2007 Apr;26(4):487-96. doi: 10.1109/TMI.2007.893283.
3
An information fidelity criterion for image quality assessment using natural scene statistics.一种基于自然场景统计的图像质量评估的信息保真度准则。
IEEE Trans Image Process. 2005 Dec;14(12):2117-28. doi: 10.1109/tip.2005.859389.
4
Sequence-independent segmentation of magnetic resonance images.磁共振图像的序列无关分割
Neuroimage. 2004;23 Suppl 1:S69-84. doi: 10.1016/j.neuroimage.2004.07.016.
5
Automatic "pipeline" analysis of 3-D MRI data for clinical trials: application to multiple sclerosis.用于临床试验的3D磁共振成像数据自动“流水线”分析：在多发性硬化症中的应用
IEEE Trans Med Imaging. 2002 Oct;21(10):1280-91. doi: 10.1109/TMI.2002.806283.
6
Cortical surface-based analysis. I. Segmentation and surface reconstruction.基于皮质表面的分析。I. 分割与表面重建。
Neuroimage. 1999 Feb;9(2):179-94. doi: 10.1006/nimg.1998.0395.
7
Quantitative assessment of MRI lesion load in multiple sclerosis. A comparison of conventional spin-echo with fast fluid-attenuated inversion recovery.多发性硬化症中MRI病灶负荷的定量评估。传统自旋回波与快速液体衰减反转恢复序列的比较。
Brain. 1996 Aug;119 ( Pt 4):1349-55. doi: 10.1093/brain/119.4.1349.
Zotero 插件