基于模型的标记心脏磁共振成像中左右心室的自动分割
Automated Model-Based Segmentation of the Left and Right Ventricles in Tagged Cardiac MRI.
作者信息
Montillo Albert, Metaxas Dimitris, Axel Leon
机构信息
University of Pennsylvania, Phila., PA 19104, USA.
Rutgers University, New Brunswick, NJ 08854 USA.
出版信息
Med Image Comput Comput Assist Interv. 2003;2878:507-515. doi: 10.1007/978-3-540-39899-8_63.
Abstract
We describe an automated, model-based method to segment the left and right ventricles in 4D tagged MR. We fit 3D epicardial and endocardial surface models to ventricle features we extract from the image data. Excellent segmentation is achieved using novel methods that (1) initialize the models and (2) that compute 3D model forces from 2D tagged MR images. The 3D forces guide the models to patient-specific anatomy while the fit is regularized via internal deformation strain energy of a thin plate. Deformation continues until the forces equilibrate or vanish. Validation of the segmentations is performed quantitatively and qualitatively on normal and diseased subjects.
摘要
我们描述了一种基于模型的自动化方法，用于在四维标记磁共振成像中分割左心室和右心室。我们将三维心外膜和心内膜表面模型拟合到从图像数据中提取的心室特征上。使用新颖的方法可实现出色的分割，这些方法包括：（1）初始化模型；（2）从二维标记磁共振图像计算三维模型力。三维力将模型引导至患者特定的解剖结构，同时通过薄板的内部变形应变能对拟合进行正则化。变形持续进行，直到力达到平衡或消失。我们对正常和患病受试者的分割结果进行了定量和定性验证。
相似文献
1
Automated Model-Based Segmentation of the Left and Right Ventricles in Tagged Cardiac MRI.基于模型的标记心脏磁共振成像中左右心室的自动分割
Med Image Comput Comput Assist Interv. 2003;2878:507-515. doi: 10.1007/978-3-540-39899-8_63.
2
Automated Segmentation of the Left and Right Ventricles in 4D Cardiac SPAMM Images.4D心脏SPAMM图像中左右心室的自动分割
Med Image Comput Comput Assist Interv. 2002 Sep;2488:620-633. doi: 10.1007/3-540-45786-0_77. Epub 2002 Oct 10.
3
Automated 3D U-net based segmentation of neonatal cerebral ventricles from 3D ultrasound images.基于自动化 3D U-net 的新生儿脑室内 3D 超声图像分割。
Med Phys. 2022 Feb;49(2):1034-1046. doi: 10.1002/mp.15432. Epub 2022 Jan 12.
4
Simultaneous extraction of endocardial and epicardial contours of the left ventricle by distance regularized level sets.通过距离正则化水平集同时提取左心室的心内膜和心外膜轮廓。
Med Phys. 2016 Jun;43(6):2741-2755. doi: 10.1118/1.4947126.
5
Fully automatic segmentation of 4D MRI for cardiac functional measurements.4D MRI 全自动分割用于心脏功能测量。
Med Phys. 2019 Jan;46(1):180-189. doi: 10.1002/mp.13245. Epub 2018 Nov 20.
6
Fully Automatic initialization and segmentation of left and right ventricles for large-scale cardiac MRI using a deeply supervised network and 3D-ASM.基于深度监督网络和 3D-ASM 的大规模心脏 MRI 左、右心室全自动初始化和分割。
Comput Methods Programs Biomed. 2023 Oct;240:107679. doi: 10.1016/j.cmpb.2023.107679. Epub 2023 Jun 14.
7
Image-based clustering and connected component labeling for rapid automated left and right ventricular endocardial volume extraction and segmentation in full cardiac cycle multi-frame MRI images of cardiac patients.基于图像的聚类和连通分量标记，用于快速自动提取和分割心脏患者全心动周期多帧 MRI 图像的左、右心室心内膜容积。
Med Biol Eng Comput. 2019 Jun;57(6):1213-1228. doi: 10.1007/s11517-019-01952-9. Epub 2019 Jan 28.
8
A novel level set method for segmentation of left and right ventricles from cardiac MR images.一种用于从心脏磁共振图像中分割左右心室的新型水平集方法。
Annu Int Conf IEEE Eng Med Biol Soc. 2014;2014:4719-22. doi: 10.1109/EMBC.2014.6944678.
9
Automatic Segmentation of Bone Selective MR Images for Visualization and Craniometry of the Cranial Vault.颅骨穹窿颅骨测量的骨选择性磁共振图像自动分割。
Acad Radiol. 2022 Mar;29 Suppl 3(Suppl 3):S98-S106. doi: 10.1016/j.acra.2021.03.010. Epub 2021 Apr 24.
10
Segmentation of left ventricle in late gadolinium enhanced MRI through 2D-4D registration for infarct localization in 3D patient-specific left ventricular model.通过二维到四维配准对晚期钆增强 MRI 中的左心室进行分段，以便在三维患者特定左心室模型中定位梗死部位。
Magn Reson Med. 2019 Feb;81(2):1385-1398. doi: 10.1002/mrm.27486. Epub 2018 Sep 19.
引用本文的文献
1
Extracting tissue deformation using Gabor filter banks.使用Gabor滤波器组提取组织变形。
Proc SPIE Int Soc Opt Eng. 2004 Feb;5369. doi: 10.1117/12.536860. Epub 2004 Apr 30.
2
Incompressible Biventricular Model Construction and Heart Segmentation of 4D Tagged MRI.基于4D标记磁共振成像的不可压缩双心室模型构建与心脏分割
Comput Biomech Med Soft Tiss Musculoskelet Syst. 2011;2011:143-155. doi: 10.1007/978-1-4419-9619-0. Epub 2011 May 4.
3
Tagged MRI based cardiac motion modeling and toxicity evaluation in breast cancer radiotherapy.基于标记MRI的乳腺癌放疗中心脏运动建模与毒性评估
Front Oncol. 2015 Feb 3;5:9. doi: 10.3389/fonc.2015.00009. eCollection 2015.
4
Meshless deformable models for 3D cardiac motion and strain analysis from tagged MRI.用于基于标记磁共振成像的三维心脏运动和应变分析的无网格可变形模型
Magn Reson Imaging. 2015 Jan;33(1):146-60. doi: 10.1016/j.mri.2014.08.007. Epub 2014 Aug 23.
5
Semi-automated left ventricular segmentation based on a guide point model approach for 3D cine DENSE cardiovascular magnetic resonance.基于引导点模型方法的半自动左心室分割在三维电影DENSE心血管磁共振成像中的应用
J Cardiovasc Magn Reson. 2014 Jan 14;16(1):8. doi: 10.1186/1532-429X-16-8.
6
Myocardial tagging by cardiovascular magnetic resonance: evolution of techniques--pulse sequences, analysis algorithms, and applications.心血管磁共振心肌标记：技术的发展——脉冲序列、分析算法和应用。
J Cardiovasc Magn Reson. 2011 Jul 28;13(1):36. doi: 10.1186/1532-429X-13-36.
7
Motion-guided segmentation for cine DENSE MRI.电影DENSE MRI的运动引导分割
Med Image Anal. 2009 Feb;13(1):105-15. doi: 10.1016/j.media.2008.06.016. Epub 2008 Jul 9.
本文引用的文献
1
Automated Segmentation of the Left and Right Ventricles in 4D Cardiac SPAMM Images.4D心脏SPAMM图像中左右心室的自动分割
Med Image Comput Comput Assist Interv. 2002 Sep;2488:620-633. doi: 10.1007/3-540-45786-0_77. Epub 2002 Oct 10.
2
Scale-based diffusive image filtering preserving boundary sharpness and fine structures.基于尺度的扩散图像滤波，保留边界清晰度和精细结构。
IEEE Trans Med Imaging. 2001 Nov;20(11):1140-55. doi: 10.1109/42.963817.
3
Human heart: tagging with MR imaging--a method for noninvasive assessment of myocardial motion.人类心脏：磁共振成像标记——一种无创评估心肌运动的方法。
Radiology. 1988 Oct;169(1):59-63. doi: 10.1148/radiology.169.1.3420283.
4
Heart wall motion: improved method of spatial modulation of magnetization for MR imaging.心脏壁运动：用于磁共振成像的改进的磁化空间调制方法。
Radiology. 1989 Aug;172(2):349-50. doi: 10.1148/radiology.172.2.2748813.
Zotero 插件