肺CT图像的血管骨架化方法

计算机科学 ›› 2013, Vol. 40 ›› Issue (5): 274-278.

肺CT图像的血管骨架化方法

陈刚,吕煊,王志成,陈宇飞

同济大学CAD研究中心上海200092 企业数字化技术教育部工程研究中心上海200092;同济大学CAD研究中心上海200092 企业数字化技术教育部工程研究中心上海200092;同济大学CAD研究中心上海200092 企业数字化技术教育部工程研究中心上海200092;同济大学CAD研究中心上海200092 企业数字化技术教育部工程研究中心上海200092

出版日期:2018-11-16 发布日期:2018-11-16
基金资助:
本文受国家自然科学基金(61103070),中央高校基本科研业务费(0800219171),国家科技支撑计划课题(2012BAF10B12)资助

Vessel Skeletonization Method for Lung CT Images

CHEN Gang,LV Xuan,WANG Zhi-cheng and CHEN Yu-fei

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 在图像几何分析以及其他领域中,骨架化方法应用非常广泛。利用骨架表示图像可以保留图中的拓扑结构,减少冗余信息。在临床实践和治疗肺部疾病的过程中,如何有效地描绘并分析肺部血管骨架结构,对于计算机辅助诊断与辅助手术治疗是非常重要的。提出一种肺CT图像的血管骨架化方法:首先使用区域生长法将肺中的血管从胸腔其他组织中分离出来,接着使用数学形态学操作对分割结果进行处理,最后使用三维细化算法对血管进行骨架化。实验结果表明,该方法能快速、有效地实现肺部血管的骨架提取。

关键词: 肺CT图像,区域生长,形态学运算,骨架化

Abstract: The skeletonization method has been widely used in image analysis and other areas．Using skeleton to express image can preserve the topological structure and reduce redundant information．In the clinical practice of diagnosis and treatment of lung disease,how to effectively represent and analyze the vascular structure is very important for computeraided diagnosis and surgery．In this paper,a vessel skeletonization method for lung CT image was proposed．Firstly,vessels were segmented from the thoracic tissues by region growing algorithm．Secondly,the morphological operators were used to deal with the vessel segmentation results．Finally,skeleton of blood vessels was obtained by three-dimentional thinning algorithm．Experimental results show that the proposed method can accurately and efficiently extract vessel skeletons from lung CT image.

Key words: Lung CT image,Region growing,Morphology,Skeletonization

陈刚,吕煊,王志成,陈宇飞. 肺CT图像的血管骨架化方法[J]. 计算机科学, 2013, 40(5): 274-278. https://doi.org/

CHEN Gang,LV Xuan,WANG Zhi-cheng and CHEN Yu-fei. Vessel Skeletonization Method for Lung CT Images[J]. Computer Science, 2013, 40(5): 274-278. https://doi.org/

参考文献

[1] Ingrid S,Arnold S,Mathias P,et al．Computer Analysis of Computed Tomography Scans of the Lung:A Survey [J]．IEEE Transactions Medical Imaging,2006,25(4):385-405
[2] Agam G,Samuel G A．Vessel tree reconstruction in thoracic CT scans with application to Nodule Detection [J].IEEE Transactions on Medical Imaging,2005,24(4):486-499
[3] 孙晓鹏,张琪.层次渐进的三维骨架算法[J].计算机科学,2010,2(37):238-240
[4] Couprie M,Coeurjolly D,Zrour R.Discrete bisector function and Euclidean skeleton in 2D and 3D[J]．Image and Vision Computing,2007,5(10):1543-1556
[5] Beristain A,Grana M．Pruning algorithm for voronoi skeletons[J].Electronics Letters,2010,6(1):39-41
[6] Couprie M,Bertrand G．New characterizations of simple points in 2D,3D and 4D discrete spaces[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,1(4):637-648
[7] Chen Y,Drechsler K,Zhao W,et al.A Thinning-based LiverVessel Skeletonization Method[C]∥International Conference on Internet Computing and Information Services．2011:152-155
[8] Palagyi K,Kuba A．Directional 3D Thinning Using 8-Subiterations[C]∥Proceedings of Discrete Geometry for Computer Ima-gery．1999,8:325-336
[9] 陈磊,王胜军,郑全录,等．基于CT图像的三维拓扑细化算法及其在心脏CAD中的应用[J].计算机应用,2007,6(27):406-410
[10] 滕奇志,康瑕,唐棠,等.基于升序复核的并行三维图像骨架化算法[J].光学精密工程,2009,0(17):2528-2534
[11] Friman O,Hindennach M,Khnel C,et al．Multiple hypothesis template tracking of small 3D vessel structures[J]．Medical Ima-ge Analysis,2010,14(2):160-171
[12] 朱应礼,徐益明,崔秋梅．MSCT肺血管成像对肺动脉栓塞的诊断价值[J]．医学影像学杂志,2008,18(6):597-599
[13] Lin K S,Tsai C L,Sofka M,et al．Vascular tree construction with anatomical realism for retinal images[C]∥Proceedings of the 9th IEEE International Conference on BioInformatics and BioEngineering．2009:313-318

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed