基于改进凸包算法的肺实质分割研究

doi:10.3969/j.issn.0258-8021.2013.04.015

摘要
图/表
参考文献
相关文章 (0)

全文: PDF (1013 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要肺实质的精确分割一直都是肺部疾病计算机辅助诊断的重要研究内容，传统的分割方法大多只能分割出不包含病灶的肺实质区域，为后期的图像分析与辅助决策带来很大的影响。针对具有边缘型肺结节的肺部CT图像，提出一种实现简单且实验效果较好的肺实质分割算法。首先，利用常规方法提取肺实质的粗略轮廓；然后，针对上一步骤中肺实质病灶信息等的缺失现象，提出一种改进的二维凸包算法对肺实质的外轮廓进行再修复；最后，利用区域生长和形态学运算，修复肺实质的内部轮廓。运用新算法，对200张边缘型肺结节的肺部CT图像进肺实质分割。实验结果表明：与已有的“滚球法”和凸包算法修复肺实质相比，新算法具有较高的准确率，可以达到90%以上,边缘型肺结节等病灶信息能被较为准确地表示出来，为建立高效的肺部疾病诊断系统奠定基础。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李金郑冰梁洪^* 邓玉林

关键词 ：肺结节, 肺部CT, 自动分割, 凸包算法

Abstract：Accurate segmentation of pulmonary parenchyma has been one important research content of the computeraided diagnosis of lung disease. Pulmonary parenchyma area with lesions cannot be divided by most of the traditional method of segmentation, and a great impact is brought for the image analysis and computeraided decision.Thus, a lung parenchyma segmentation algorithm was proposed for lung CT image with edgetype pulmonary nodules. The algorithm is easy to implement and has a better experimental results. Firstly, we used conventional method to extract the rough contour of pulmonary parenchyma. Secondly, in connection with the absence of lung parenchyma lesions in the previous step, an improved twodimensional convex hull algorithm was proposed to repair the pulmonary parenchyma contour. Finally, the pulmonary parenchyma internal contour was acquired by using regional growth and morphology comprehensively. The test results of the experiment on 200 clinical chest CT images showed that: compared with the existing ball pivoting algorithm and convex hull algorithm to repair the lung parenchyma, the algorithm proposed in this paper has higher accuracy. The accuracy rate can reach 90% or more. Lesions like borderline pulmonary nodules can be represented exactly and it is the basics of establishing the efficient pulmonary disease diagnosis system.

Key words： pulmonary nodules pulmonary computed tomography images automated segmentation convex hull algorithm

基金资助:哈尔滨市科技创新人才研究专项资金项目（优秀学科带头人，2011RFXXG028）；黑龙江省自然科学基金（F201241）

引用本文:

李金郑冰梁洪^* 邓玉林. 基于改进凸包算法的肺实质分割研究[J]. 中国生物医学工程学报, 2013, 32(4): 484-490.
LI Jin ZHENG Bing LIANG Hong^* DENG Yu Lin. Segmentation Research of Pulmonary Parenchyma Based on Improved Convex Hull Algorithm. journal1, 2013, 32(4): 484-490.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2013.04.015 或 http://cjbme.csbme.org/CN/Y2013/V32/I4/484

［1］梁洪，李金. 一种肺部CT图像快速分割算法研究［J］. 国医疗设备, 2011, 26(3): 28-30.

［2］Pu JT, Roos J, Yi CA, et al. Adaptive border marching algorithm: Automatic lung segmentation on chest CT images ［J］. Computerized Medical Imaging and Graphics, 2008, 32(6): 452-462.
［3］Wang SJ, Summers RM. Machine learning and radiology［J］. Medical Image Analysis, 2012, 16: 933–951.

［4］Gu YH, Kumar V, Hall LO, et al. Automated delineation of lung tumors from ct images using a single click ensemble segmentation approach ［J］. Pattern Recognition, In Press, Accepted Manuscript, Available online 11 October 2012. 
［5］Armato SG, Sensakovic WF. Automated lung segmentation for thoracic CT: Impact on computeraided diagnosis ［J］. Academic Radiology, 2004, 11(9): 1011-1021
［6］Hu S, Hoffman EA, Reinhardt JM. Automatic lung segmentation for accurate quantitation of volumetric XRay CT images ［J］. IEEE Trans on Med Imaging , 2001, 20: 490-498.［7］Bollotti R, DeCarlo F, Gargano G, et al. A CAD system for nodules detection in lowdoes lung CTs based on region growing and a new active contour model ［J］.Medical Physics.2007, 34: 10-14. 
［8］Kanazawa K, Kawata Y, Niki N, et al. Computeraided diagnosis for pulmonary nodules based on helical CT images ［J］. Compute Med Imaging Graphics, 1998, 22: 157-167.
［9］王晶. 基于CT图像的肺实质分割算法研究［D］. 沈阳: 沈阳大学, 2010.
［10］袁克虹, 向兰茜. 用于计算机辅助诊断的肺实质自动分割方法［J］. 清华大学学报, 2011 51(1): 90-95.
［11］裴晓敏, 郭红宇, 戴建平. 胸部CT 中肺实质的自动分割及粘连肿瘤检测［J］. 哈尔滨工程大学学报, 2010, 31(5): 679-682.
［12］李丽. 基于CT影像分析的肺结节检测算法研究［D］. 大连: 大连理工大学, 2010, 7-10.
［13］刘宏兵, 邬长安, 周文勇. 基于二维凸包的TSP算法［J］. 计算机工程与设计, 2009, 30(8): 1954-2000.