基于肿瘤生长模型的脑部扫描联合分割与可变形配准
Joint segmentation and deformable registration of brain scans guided by a tumor growth model.
作者信息
Gooya Ali, Pohl Kilian M, Bilello Michel, Biros George, Davatzikos Christos
机构信息
Section for Biomedical Image Analysis, Suite 380, 3600 Market St.,19104 Philadelphia, USA.
出版信息
Med Image Comput Comput Assist Interv. 2011;14(Pt 2):532-40. doi: 10.1007/978-3-642-23629-7_65.
Abstract
This paper presents an approach for joint segmentation and deformable registration of brain scans of glioma patients to a normal atlas. The proposed method is based on the Expectation Maximization (EM) algorithm that incorporates a glioma growth model for atlas seeding, a process which modifies the normal atlas into one with a tumor and edema. The modified atlas is registered into the patient space and utilized for the posterior probability estimation of various tissue labels. EM iteratively refines the estimates of the registration parameters, the posterior probabilities of tissue labels and the tumor growth model parameters. We have applied this approach to 10 glioma scans acquired with four Magnetic Resonance (MR) modalities (T1, T1-CE, T2 and FLAIR) and validated the result by comparing them to manual segmentations by clinical experts. The resulting segmentations look promising and quantitatively match well with the expert provided ground truth.
摘要
本文提出了一种将胶质瘤患者脑部扫描图像与正常图谱进行联合分割和可变形配准的方法。所提出的方法基于期望最大化（EM）算法，该算法结合了用于图谱种子点的胶质瘤生长模型，此过程将正常图谱修改为带有肿瘤和水肿的图谱。修改后的图谱被配准到患者空间，并用于各种组织标签的后验概率估计。EM迭代地细化配准参数估计、组织标签的后验概率以及肿瘤生长模型参数。我们已将此方法应用于通过四种磁共振（MR）模态（T1、T1增强、T2和液体衰减反转恢复序列（FLAIR））获取的10例胶质瘤扫描图像，并通过与临床专家的手动分割结果进行比较来验证结果。所得分割结果看起来很有前景，并且在定量上与专家提供的真实情况匹配良好。
相似文献
1
Joint segmentation and deformable registration of brain scans guided by a tumor growth model.基于肿瘤生长模型的脑部扫描联合分割与可变形配准
Med Image Comput Comput Assist Interv. 2011;14(Pt 2):532-40. doi: 10.1007/978-3-642-23629-7_65.
2
GLISTR: glioma image segmentation and registration.GLISTR：脑胶质瘤图像分割与配准。
IEEE Trans Med Imaging. 2012 Oct;31(10):1941-54. doi: 10.1109/TMI.2012.2210558. Epub 2012 Aug 13.
3
Deformable registration of glioma images using EM algorithm and diffusion reaction modeling.基于 EM 算法和扩散反应模型的脑肿瘤图像的可变形配准。
IEEE Trans Med Imaging. 2011 Feb;30(2):375-90. doi: 10.1109/TMI.2010.2078833. Epub 2010 Sep 27.
4
Combining generative models for multifocal glioma segmentation and registration.用于多灶性胶质瘤分割与配准的生成模型融合
Med Image Comput Comput Assist Interv. 2014;17(Pt 1):763-70. doi: 10.1007/978-3-319-10404-1_95.
5
Deformable registration of magnetic resonance images using unsupervised deep learning in neuro-/radiation oncology.使用无监督深度学习进行神经/放射肿瘤学中的磁共振图像的可变形配准。
Radiat Oncol. 2024 May 21;19(1):61. doi: 10.1186/s13014-024-02452-3.
6
Semi-automated segmentation of pre-operative low grade gliomas in magnetic resonance imaging.磁共振成像中术前低级别胶质瘤的半自动分割
Cancer Imaging. 2015 Aug 14;15(1):12. doi: 10.1186/s40644-015-0047-z.
7
Robust whole-brain segmentation: application to traumatic brain injury.稳健的全脑分割：在创伤性脑损伤中的应用。
Med Image Anal. 2015 Apr;21(1):40-58. doi: 10.1016/j.media.2014.12.003. Epub 2014 Dec 24.
8
Automated brain tumor segmentation using spatial accuracy-weighted hidden Markov Random Field.使用空间精度加权隐马尔可夫随机场的脑肿瘤自动分割
Comput Med Imaging Graph. 2009 Sep;33(6):431-41. doi: 10.1016/j.compmedimag.2009.04.006. Epub 2009 May 14.
9
Multi-parametric analysis and registration of brain tumors: constructing statistical atlases and diagnostic tools of predictive value.脑肿瘤的多参数分析与配准：构建具有预测价值的统计图谱和诊断工具。
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:6979-81. doi: 10.1109/IEMBS.2011.6091764.
10
Performance-based classifier combination in atlas-based image segmentation using expectation-maximization parameter estimation.基于期望最大化参数估计的基于图谱的图像分割中基于性能的分类器组合
IEEE Trans Med Imaging. 2004 Aug;23(8):983-94. doi: 10.1109/TMI.2004.830803.
引用本文的文献
1
Integrated Biophysical Modeling and Image Analysis: Application to Neuro-Oncology.一体化生物物理建模与图像分析：在神经肿瘤学中的应用。
Annu Rev Biomed Eng. 2020 Jun 4;22:309-341. doi: 10.1146/annurev-bioeng-062117-121105.
2
Coupling brain-tumor biophysical models and diffeomorphic image registration.耦合脑肿瘤生物物理模型与微分同胚图像配准
Comput Methods Appl Mech Eng. 2019 Apr 15;347:533-567. doi: 10.1016/j.cma.2018.12.008. Epub 2019 Jan 7.
3
Scalable Joint Segmentation and Registration Framework for Infant Brain Images.用于婴儿脑图像的可扩展联合分割与配准框架
Neurocomputing (Amst). 2017 Mar 15;229:54-62. doi: 10.1016/j.neucom.2016.05.107. Epub 2016 Nov 16.
4
Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features.利用专家分割标签和放射组学特征推进癌症基因组图谱胶质细胞瘤 MRI 数据集。
Sci Data. 2017 Sep 5;4:170117. doi: 10.1038/sdata.2017.117.
5
Segmentation of Gliomas in Pre-operative and Post-operative Multimodal Magnetic Resonance Imaging Volumes Based on a Hybrid Generative-Discriminative Framework.基于混合生成-判别框架的术前和术后多模态磁共振成像体积中胶质瘤的分割
Brainlesion. 2016 Oct;10154:184-194. doi: 10.1007/978-3-319-55524-9_18. Epub 2017 Apr 12.
6
GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation.GLISTRboost：结合多模态磁共振成像分割、配准和生物物理肿瘤生长建模与梯度提升机进行胶质瘤分割
Brainlesion. 2016;9556:144-155. doi: 10.1007/978-3-319-30858-6_1.
7
A Probabilistic Atlas of Diffuse WHO Grade II Glioma Locations in the Brain.大脑弥漫性世界卫生组织二级胶质瘤位置的概率图谱。
PLoS One. 2016 Jan 11;11(1):e0144200. doi: 10.1371/journal.pone.0144200. eCollection 2016.
8
Semiautomatic segmentation and follow-up of multicomponent low-grade tumors in longitudinal brain MRI studies.纵向脑磁共振成像研究中多成分低度肿瘤的半自动分割与随访
Med Phys. 2014 May;41(5):052303. doi: 10.1118/1.4871040.
9
Concurrent tumor segmentation and registration with uncertainty-based sparse non-uniform graphs.基于不确定性的稀疏非均匀图的肿瘤同时分割和配准。
Med Image Anal. 2014 May;18(4):647-59. doi: 10.1016/j.media.2014.02.006. Epub 2014 Feb 24.
10
GLISTR: glioma image segmentation and registration.GLISTR：脑胶质瘤图像分割与配准。
IEEE Trans Med Imaging. 2012 Oct;31(10):1941-54. doi: 10.1109/TMI.2012.2210558. Epub 2012 Aug 13.
本文引用的文献
1
Deformable registration of glioma images using EM algorithm and diffusion reaction modeling.基于 EM 算法和扩散反应模型的脑肿瘤图像的可变形配准。
IEEE Trans Med Imaging. 2011 Feb;30(2):375-90. doi: 10.1109/TMI.2010.2078833. Epub 2010 Sep 27.
2
An image-driven parameter estimation problem for a reaction-diffusion glioma growth model with mass effects.一个具有质量效应的反应扩散胶质瘤生长模型的图像驱动参数估计问题。
J Math Biol. 2008 Jun;56(6):793-825. doi: 10.1007/s00285-007-0139-x. Epub 2007 Nov 17.
3
Dense deformation field estimation for atlas-based segmentation of pathological MR brain images.用于基于图谱的病理性脑磁共振图像分割的密集变形场估计
Comput Methods Programs Biomed. 2006 Dec;84(2-3):66-75. doi: 10.1016/j.cmpb.2006.08.003. Epub 2006 Sep 18.
4
A Bayesian model for joint segmentation and registration.一种用于联合分割与配准的贝叶斯模型。
Neuroimage. 2006 May 15;31(1):228-39. doi: 10.1016/j.neuroimage.2005.11.044. Epub 2006 Feb 7.
5
Unified segmentation.统一分割
Neuroimage. 2005 Jul 1;26(3):839-51. doi: 10.1016/j.neuroimage.2005.02.018. Epub 2005 Apr 1.
6
Preferential brain locations of low-grade gliomas.低级别胶质瘤在脑内的好发部位
Cancer. 2004 Jun 15;100(12):2622-6. doi: 10.1002/cncr.20297.
7
Automatic brain tumor segmentation by subject specific modification of atlas priors.通过对图谱先验进行特定于个体的修改实现脑肿瘤自动分割。
Acad Radiol. 2003 Dec;10(12):1341-8. doi: 10.1016/s1076-6332(03)00506-3.
8
Improved optimization for the robust and accurate linear registration and motion correction of brain images.改进用于脑图像稳健且准确的线性配准和运动校正的优化方法。
Neuroimage. 2002 Oct;17(2):825-41. doi: 10.1016/s1053-8119(02)91132-8.
9
Automated segmentation of multiple sclerosis lesions by model outlier detection.通过模型离群值检测实现多发性硬化症病变的自动分割。
IEEE Trans Med Imaging. 2001 Aug;20(8):677-88. doi: 10.1109/42.938237.
10
Spatial normalization of brain images with focal lesions using cost function masking.使用代价函数掩膜对伴有局灶性病变的脑图像进行空间归一化。
Neuroimage. 2001 Aug;14(2):486-500. doi: 10.1006/nimg.2001.0845.
Zotero 插件