使用粒子滤波器对脊柱磁共振成像中的神经束和神经节进行分割。
Segmentation of nerve bundles and ganglia in spine MRI using particle filters.
作者信息
Dalca Adrian, Danagoulian Giovanna, Kikinis Ron, Schmidt Ehud, Golland Polina
机构信息
MIT Computer Science and Artificial Inteligence, Cambridge, MA, USA.
出版信息
Med Image Comput Comput Assist Interv. 2011;14(Pt 3):537-45. doi: 10.1007/978-3-642-23626-6_66.
Abstract
Automatic segmentation of spinal nerve bundles that originate within the dural sac and exit the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves seen in high resolution myelographic MR images makes segmentation a challenging task. In this paper, we present an automatic tracking method for nerve segmentation based on particle filters. We develop a novel approach to particle representation and dynamics, based on Bézier splines. Moreover, we introduce a robust image likelihood model that enables delineation of nerve bundles and ganglia from the surrounding anatomical structures. We demonstrate accurate and fast nerve tracking and compare it to expert manual segmentation.
摘要
自动分割起源于硬脊膜囊并穿出椎管的脊神经束，对于诊断和手术规划非常重要。在高分辨率脊髓造影磁共振图像中，神经在强度、对比度、形状和方向上的变化使得分割成为一项具有挑战性的任务。在本文中，我们提出了一种基于粒子滤波器的神经分割自动跟踪方法。我们基于贝塞尔样条开发了一种新颖的粒子表示和动力学方法。此外，我们引入了一种强大的图像似然模型，能够从周围的解剖结构中勾勒出神经束和神经节。我们展示了准确快速的神经跟踪，并将其与专家手动分割进行了比较。
相似文献
1
Segmentation of nerve bundles and ganglia in spine MRI using particle filters.使用粒子滤波器对脊柱磁共振成像中的神经束和神经节进行分割。
Med Image Comput Comput Assist Interv. 2011;14(Pt 3):537-45. doi: 10.1007/978-3-642-23626-6_66.
2
Quantitative evaluation of an automatic segmentation method for 3D reconstruction of intervertebral scoliotic disks from MR images.基于磁共振图像的脊柱侧凸椎间盘 3D 重建自动分割方法的定量评估。
BMC Med Imaging. 2012 Aug 2;12:26. doi: 10.1186/1471-2342-12-26.
3
Automatic hippocampus segmentation of 7.0 Tesla MR images by combining multiple atlases and auto-context models.通过结合多个图谱和自动上下文模型对7.0特斯拉磁共振图像进行海马体自动分割。
Neuroimage. 2013 Dec;83:335-45. doi: 10.1016/j.neuroimage.2013.06.006. Epub 2013 Jun 11.
4
Accuracy Validation of an Automated Method for Prostate Segmentation in Magnetic Resonance Imaging.磁共振成像中前列腺自动分割方法的准确性验证。
J Digit Imaging. 2017 Dec;30(6):782-795. doi: 10.1007/s10278-017-9964-7.
5
Multi-atlas multi-shape segmentation of fetal brain MRI for volumetric and morphometric analysis of ventriculomegaly.多图谱多形状分割胎儿脑 MRI 进行脑室扩大的容积和形态分析。
Neuroimage. 2012 Apr 15;60(3):1819-31. doi: 10.1016/j.neuroimage.2012.01.128. Epub 2012 Feb 10.
6
Spatially varying accuracy and reproducibility of prostate segmentation in magnetic resonance images using manual and semiautomated methods.使用手动和半自动方法在磁共振图像中前列腺分割的空间变化准确性和可重复性。
Med Phys. 2014 Nov;41(11):113503. doi: 10.1118/1.4899182.
7
Minimally interactive segmentation of 4D dynamic upper airway MR images via fuzzy connectedness.通过模糊连接性对4D动态上呼吸道磁共振图像进行最小交互分割。
Med Phys. 2016 May;43(5):2323. doi: 10.1118/1.4945698.
8
Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI.基于学习的脊椎检测和迭代归一化切割分割在脊髓 MRI 中的应用。
IEEE Trans Med Imaging. 2009 Oct;28(10):1595-605. doi: 10.1109/TMI.2009.2023362.
9
Non-rigid registration based segmentation of brain subcortical structures using a priori knowledge.基于非刚性配准并利用先验知识对脑皮质下结构进行分割
Annu Int Conf IEEE Eng Med Biol Soc. 2008;2008:3971-4. doi: 10.1109/IEMBS.2008.4650079.
10
Multistage processing procedure for 4D breast MRI segmentation.用于4D乳腺MRI分割的多阶段处理程序。
Annu Int Conf IEEE Eng Med Biol Soc. 2008;2008:3036-9. doi: 10.1109/IEMBS.2008.4649843.
引用本文的文献
1
Learned iterative segmentation of highly variable anatomy from limited data: Applications to whole heart segmentation for congenital heart disease.从有限数据中学习高度可变解剖结构的迭代分割：在先天性心脏病的全心脏分割中的应用。
Med Image Anal. 2022 Aug;80:102469. doi: 10.1016/j.media.2022.102469. Epub 2022 May 13.
2
Parallel and distributed encoding of speech across human auditory cortex.人类听觉皮层中语音的并行和分布式编码。
Cell. 2021 Sep 2;184(18):4626-4639.e13. doi: 10.1016/j.cell.2021.07.019. Epub 2021 Aug 18.
3
DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes.深度血管网络：三维血管造影体积中的血管分割、中心线预测和分叉检测
Front Neurosci. 2020 Dec 8;14:592352. doi: 10.3389/fnins.2020.592352. eCollection 2020.
4
Comparison of wideband steady-state free precession and T₂-weighted fast spin echo in spine disorder assessment at 1.5 and 3 T.1.5T 和 3T 下宽频稳态自由进动与 T₂加权快速自旋回波在脊柱病变评估中的比较。
Magn Reson Med. 2012 Nov;68(5):1527-35. doi: 10.1002/mrm.24163. Epub 2012 Jan 27.
本文引用的文献
1
Tractography of lumbar nerve roots: initial results.腰椎神经根轨迹追踪：初步结果。
Eur Radiol. 2011 Jun;21(6):1153-9. doi: 10.1007/s00330-010-2049-3. Epub 2011 Jan 16.
2
A review of 3D vessel lumen segmentation techniques: models, features and extraction schemes.三维血管管腔分割技术综述：模型、特征和提取方案。
Med Image Anal. 2009 Dec;13(6):819-45. doi: 10.1016/j.media.2009.07.011. Epub 2009 Aug 12.
3
Robust vessel tree modeling.稳健的血管树建模
Med Image Comput Comput Assist Interv. 2008;11(Pt 1):602-11. doi: 10.1007/978-3-540-85988-8_72.
4
Bayesian tracking of tubular structures and its application to carotid arteries in CTA.管状结构的贝叶斯追踪及其在CTA中对颈动脉的应用。
Med Image Comput Comput Assist Interv. 2007;10(Pt 2):562-70. doi: 10.1007/978-3-540-75759-7_68.
5
Vessels as 4-D curves: global minimal 4-D paths to extract 3-D tubular surfaces and centerlines.作为四维曲线的血管：用于提取三维管状表面和中心线的全局最小四维路径。
IEEE Trans Med Imaging. 2007 Sep;26(9):1213-23. doi: 10.1109/tmi.2007.903696.
6
Robust 3-D modeling of vasculature imagery using superellipsoids.使用超椭圆体对脉管系统图像进行稳健的三维建模。
IEEE Trans Med Imaging. 2007 Feb;26(2):223-37. doi: 10.1109/TMI.2006.889722.
7
Particle filters, a quasi-Monte-Carlo-solution for segmentation of coronaries.粒子滤波器，一种用于冠状动脉分割的准蒙特卡罗解决方案。
Med Image Comput Comput Assist Interv. 2005;8(Pt 1):246-53. doi: 10.1007/11566465_31.
8
New vessel analysis tool for morphometric quantification and visualization of vessels in CT and MR imaging data sets.用于CT和MR成像数据集中血管形态计量定量和可视化的新型血管分析工具。
Radiographics. 2004 Jan-Feb;24(1):287-97. doi: 10.1148/rg.241035073.
9
Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction.用于管状物体中心线提取的高度脊线遍历中的初始化、噪声、奇点和尺度
IEEE Trans Med Imaging. 2002 Feb;21(2):61-75. doi: 10.1109/42.993126.
10
CURVES: curve evolution for vessel segmentation.曲线：用于血管分割的曲线演化
Med Image Anal. 2001 Sep;5(3):195-206. doi: 10.1016/s1361-8415(01)00040-8.
Zotero 插件