将非刚性配准纳入期望最大化算法以分割磁共振图像。
Incorporating Non-rigid Registration into Expectation Maximization Algorithm to Segment MR Images.
作者信息
Pohl Kilian M, Wells William M, Guimond Alexandre, Kasai Kiyoto, Shenton Martha E, Kikinis Ron, Grimson W Eric L, Warfield Simon K
机构信息
Artificial Intelligence Laboratory, http://www.ai.mit.edu Massachusetts Institute of Technology, Cambridge MA, USA.
Surgical Planning Laboratory http://www.spl.harvard.edu Harvard Medical School and Brigham and Women's Hospital, 75 Francis St., Boston, MA 02115 USA.
出版信息
Med Image Comput Comput Assist Interv. 2002 Sep;2488:564-571. doi: 10.1007/3-540-45786-0_70. Epub 2002 Oct 10.
Abstract
The paper introduces an algorithm which allows the automatic segmentation of multi channel magnetic resonance images. We extended the Expectation Maximization-Mean Field Approximation Segmenter, to include Local Prior Probability Maps. Thereby our algorithm estimates the bias field in the image while simultaneously assigning voxels to different tissue classes under prior probability maps. The probability maps were aligned to the subject using nonrigid registration. This allowed the parcellation of cortical sub-structures including the superior temporal gyrus. To our knowledge this is the first description of an algorithm capable of automatic cortical parcellation incorporating strong noise reduction and image intensity correction.
摘要
本文介绍了一种可对多通道磁共振图像进行自动分割的算法。我们扩展了期望最大化 - 平均场近似分割器，以纳入局部先验概率图。由此，我们的算法在图像中估计偏差场，同时在先验概率图下将体素分配到不同的组织类别。通过非刚性配准将概率图与受试者对齐。这使得包括颞上回在内的皮质亚结构能够被分割。据我们所知，这是首次描述一种能够在进行自动皮质分割的同时实现强降噪和图像强度校正的算法。
相似文献
1
Incorporating Non-rigid Registration into Expectation Maximization Algorithm to Segment MR Images.将非刚性配准纳入期望最大化算法以分割磁共振图像。
Med Image Comput Comput Assist Interv. 2002 Sep;2488:564-571. doi: 10.1007/3-540-45786-0_70. Epub 2002 Oct 10.
2
Comparative assessment of statistical brain MR image segmentation algorithms and their impact on partial volume correction in PET.统计脑磁共振图像分割算法的比较评估及其对正电子发射断层扫描中部分容积校正的影响。
Neuroimage. 2006 Oct 1;32(4):1591-607. doi: 10.1016/j.neuroimage.2006.05.031. Epub 2006 Jul 7.
3
Rough Sets and Stomped Normal Distribution for Simultaneous Segmentation and Bias Field Correction in Brain MR Images.粗糙集和踩踏正态分布在脑磁共振图像中的同时分割和偏场校正。
IEEE Trans Image Process. 2015 Dec;24(12):5764-76. doi: 10.1109/TIP.2015.2488900. Epub 2015 Oct 8.
4
An information theoretic approach for non-rigid image registration using voxel class probabilities.一种使用体素类概率进行非刚性图像配准的信息论方法。
Med Image Anal. 2006 Jun;10(3):413-31. doi: 10.1016/j.media.2005.03.004.
5
Automatic segmentation for brain MR images via a convex optimized segmentation and bias field correction coupled model.通过凸优化分割与偏置场校正耦合模型实现脑磁共振图像的自动分割
Magn Reson Imaging. 2014 Sep;32(7):941-55. doi: 10.1016/j.mri.2014.05.003. Epub 2014 May 13.
6
Partial volume segmentation of brain magnetic resonance images based on maximum a posteriori probability.基于最大后验概率的脑磁共振图像部分容积分割
Med Phys. 2005 Jul;32(7Part1):2337-2345. doi: 10.1118/1.1944912.
7
Accurate CT∕MR vessel-guided nonrigid registration of largely deformed livers.精确的 CT/MR 血管引导的大幅变形肝脏的非刚性配准。
Med Phys. 2012 May;39(5):2463-77. doi: 10.1118/1.3701779.
8
Narrow band deformable registration of prostate magnetic resonance imaging, magnetic resonance spectroscopic imaging, and computed tomography studies.前列腺磁共振成像、磁共振波谱成像和计算机断层扫描研究的窄带可变形配准
Int J Radiat Oncol Biol Phys. 2005 Jun 1;62(2):595-605. doi: 10.1016/j.ijrobp.2005.02.001.
9
A vessel segmentation method for multi-modality angiographic images based on multi-scale filtering and statistical models.一种基于多尺度滤波和统计模型的多模态血管造影图像血管分割方法。
Biomed Eng Online. 2016 Nov 8;15(1):120. doi: 10.1186/s12938-016-0241-7.
10
Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm.通过隐马尔可夫随机场模型和期望最大化算法对脑部磁共振图像进行分割。
IEEE Trans Med Imaging. 2001 Jan;20(1):45-57. doi: 10.1109/42.906424.
引用本文的文献
1
A novel brain tumor magnetic resonance imaging dataset (Gazi Brains 2020): initial benchmark results and comprehensive analysis.一个新型脑肿瘤磁共振成像数据集（加齐脑影像2020）：初步基准测试结果及综合分析
PeerJ Comput Sci. 2025 Jun 10;11:e2920. doi: 10.7717/peerj-cs.2920. eCollection 2025.
2
Coupling Statistical Segmentation and PCA Shape Modeling.耦合统计分割与主成分分析形状建模
Med Image Comput Comput Assist Interv. 2004 Sep;3216:151-159. doi: 10.1007/978-3-540-30135-6_19.
3
ANATOMICAL GUIDED SEGMENTATION WITH NON-STATIONARY TISSUE CLASS DISTRIBUTIONS IN AN EXPECTATION-MAXIMIZATION FRAMEWORK.期望最大化框架下具有非平稳组织类别分布的解剖学引导分割
Proc IEEE Int Symp Biomed Imaging. 2004 Apr;2004:81-84. doi: 10.1109/ISBI.2004.1398479. Epub 2005 Mar 7.
4
MRI segmentation of the human brain: challenges, methods, and applications.人类大脑的磁共振成像分割：挑战、方法与应用
Comput Math Methods Med. 2015;2015:450341. doi: 10.1155/2015/450341. Epub 2015 Mar 1.
5
Combining spatial priors and anatomical information for fMRI detection.联合空间先验和解剖信息进行 fMRI 检测。
Med Image Anal. 2010 Jun;14(3):318-31. doi: 10.1016/j.media.2010.02.007. Epub 2010 Mar 6.
6
A hybrid geometric-statistical deformable model for automated 3-D segmentation in brain MRI.一种用于脑磁共振成像中自动三维分割的混合几何-统计可变形模型。
IEEE Trans Biomed Eng. 2009 Jul;56(7):1838-48. doi: 10.1109/TBME.2009.2017509. Epub 2009 Mar 27.
7
Restoration of MRI data for intensity non-uniformities using local high order intensity statistics.使用局部高阶强度统计恢复强度不均匀性的MRI数据。
Med Image Anal. 2009 Feb;13(1):36-48. doi: 10.1016/j.media.2008.05.003. Epub 2008 Jun 7.
8
Automatic localization of anatomical point landmarks for brain image processing algorithms.用于脑图像处理算法的解剖学点标志的自动定位
Neuroinformatics. 2008 Summer;6(2):135-48. doi: 10.1007/s12021-008-9018-x. Epub 2008 May 30.
9
Restoration of MRI Data for Field Nonuniformities using High Order Neighborhood Statistics.使用高阶邻域统计恢复磁场不均匀性的MRI数据
Proc SPIE Int Soc Opt Eng. 2007 Mar 5;6512:65121L. doi: 10.1117/12.711533.
10
A hierarchical algorithm for MR brain image parcellation.一种用于磁共振脑图像分割的分层算法。
IEEE Trans Med Imaging. 2007 Sep;26(9):1201-12. doi: 10.1109/TMI.2007.901433.
本文引用的文献
1
Morphometric analysis of white matter lesions in MR images: method and validation.磁共振图像中脑白质病变的形态计量分析：方法与验证。
IEEE Trans Med Imaging. 1994;13(4):716-24. doi: 10.1109/42.363096.
2
Adaptive segmentation of MRI data.MRI 数据的自适应分割。
IEEE Trans Med Imaging. 1996;15(4):429-42. doi: 10.1109/42.511747.
3
Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain.全脑分割：人脑神经解剖结构的自动标记
Neuron. 2002 Jan 31;33(3):341-55. doi: 10.1016/s0896-6273(02)00569-x.
4
An integrated visualization system for surgical planning and guidance using image fusion and an open MR.一种使用图像融合和开放式磁共振成像进行手术规划与引导的集成可视化系统。
J Magn Reson Imaging. 2001 Jun;13(6):967-75. doi: 10.1002/jmri.1139.
5
Three-dimensional multimodal brain warping using the demons algorithm and adaptive intensity corrections.使用恶魔算法和自适应强度校正的三维多模态脑图像配准
IEEE Trans Med Imaging. 2001 Jan;20(1):58-69. doi: 10.1109/42.906425.
6
Adaptive, template moderated, spatially varying statistical classification.自适应、模板调节、空间变化统计分类
Med Image Anal. 2000 Mar;4(1):43-55. doi: 10.1016/s1361-8415(00)00003-7.
7
Automated model-based bias field correction of MR images of the brain.基于模型的脑磁共振图像自动偏置场校正
IEEE Trans Med Imaging. 1999 Oct;18(10):885-96. doi: 10.1109/42.811268.
8
Image matching as a diffusion process: an analogy with Maxwell's demons.图像匹配作为一种扩散过程：与麦克斯韦妖的类比。
Med Image Anal. 1998 Sep;2(3):243-60. doi: 10.1016/s1361-8415(98)80022-4.
Zotero 插件