CT图像肺结节的毛刺检测与量化评估

计算机应用 ›› 2014, Vol. 34 ›› Issue (12): 3599-3604.

CT图像肺结节的毛刺检测与量化评估

邢谦谦¹,刘哲星¹,林炳权²,钱俊¹,曹蕾¹

1. 南方医科大学生物医学工程学院,广州 510515
2. 南方医院影像中心,广州 510515

收稿日期:2014-06-09 修回日期:2014-07-23 出版日期:2014-12-01 发布日期:2014-12-31
通讯作者: 邢谦谦
作者简介:邢谦谦(1989-),女,山东济南人,硕士研究生,主要研究方向:医学图像处理；刘哲星(1972-),男,山西太原人,副教授,主要研究方向:医学图像处理；林炳权(1983-),男,广东汕头人,博士,主要研究方向:CT影像诊断；钱俊(1975-),女,安徽歙县人,副教授,主要研究方向:生物统计；曹蕾(1974-),女,湖南沅江人,副教授,主要研究方向:医学图像处理、软件工程。
基金资助:
国家自然科学基金青年基金资助项目;国家自然科学基金资助项目;广东省教育部产学研项目

Detection and quantitative evaluation of lung nodule spiculation in CT images

XING Qiamqiam¹,LIU Zhexing¹,LIN Binquan²,QIAN Jun¹,CAO Lei¹

1. School of Biomedical Engineering, Southern Medical University, Guangzhou Guangdong 510515, China;
2. Image Center, Nanfang Hospital, Guangzhou Guangdong 510515, China

Received:2014-06-09 Revised:2014-07-23 Online:2014-12-01 Published:2014-12-31
Contact: XING Qiamqiam

摘要/Abstract

摘要：

为准确检测并量化评估毛刺征,提出一种CT图像肺结节的毛刺检测与量化评估方法。首先利用区域生长算法与水平集方法结合进行结节主体的准确分割；而后利用线性滤波模板提取结节主体周边区域的毛刺；最后引入毛刺水平指数作为毛刺特征的量化指标。在此基础上对结节有无毛刺进行分类,并与肺部图像数据库联盟(LIDC)的量化评级进行一致性和相关性分析。实验结果表明,该方法可以有效地检测并定量描述CT图像肺结节的毛刺征。

Abstract:

A new method was proposed to accurately detect and quantitatively evaluate the lung nodule spiculation. First, the region growing method followed by level set method was used to accurately segment the main part of the lung nodule. Then, spiculated lines connected to the nodule boundary were extracted using a line detector in polar coordinates system. Finally, spiculation index was introduced as the quantitative measurement of spiculation features, which was then used as a criteria for distinguishing between spiculated and non-spiculated nodules. The consistency and correlation of spiculation index of the method and Lung Image Database Consortium (LIDC) were evaluated in detail. The experimental results show that the proposed method can effectively detect and quantitatively describe the lung nodule spiculation in CT images.

中图分类号:

TP391.41

邢谦谦刘哲星林炳权钱俊曹蕾. CT图像肺结节的毛刺检测与量化评估[J]. 计算机应用, 2014, 34(12): 3599-3604.

XING Qiamqiam LIU Zhexing LIN Binquan QIAN Jun CAO Lei. Detection and quantitative evaluation of lung nodule spiculation in CT images[J]. Journal of Computer Applications, 2014, 34(12): 3599-3604.

参考文献

［1］YANG S. The status quo, confusion and prospect of early diagnosis for lung cancer［J］.Journal of Xi’an Jiaotong University: Medical Sciences, 2011,32(1):1-5.(杨拴盈.肺癌早期诊断的现状,困惑和希望［J］.西安交通大学学报:医学版,2011, 32(1): 1-5.)
［2］WINER-MURAM H T. The solitary pulmonary nodule［J］. Radiology, 2006, 239(1):34-49.
［3］HODNETT P A, KO J P. Evaluation and management of indeterminate pulmonary nodules［J］. Radiologic Clinics of North America, 2012,50(5):895-914.
［4］WANG Q, GONG J, SONG E, et al. Computerized quantification method for lung nodule speculation features on CT images［J］. Journal of Huazhong University of Science and Technology: Natural Science Edition, 2011,39(7):26-29.(王倩,龚建平,宋恩民,等.CT图像中肺结节毛刺特征的计算机量化方法［J］.华中科技大学学报:自然科学版,2011,39(7):26-29.)
［5］HE K. Research on pulmonary nodule feature extraction in CT images［D］.Wuhan: Huazhong University of Science and Technology,2011.(何珂程.CT图像的肺结节特征提取的方法研究［D］.武汉:华中科技大学,2011.)
［6］JIANG L, SONG E, XU X, et al. Automated detection of breast mass spiculation levels and evaluation of scheme performance［J］. Academic Radiology, 2008, 15(12): 1534-1544.
［7］CAO L, LU L, YANG R, et al. Self-adapted segmentation of pulmonary nodule based on region growing［J］. Southern Medical University, 2011,39(7):26-30.(曹蕾,路利军,杨蕊梦,等.基于区域增长的肺结节自适应形态分割［J］.南方医科大学学报,2011,39(7):26-30.)
［8］GU Y, VIRENDRA KUMAR, HALL L, et al. Automated delineation of lung tumors from CT images using a single click ensemble segmentation approach［J］.Pattern Recognition, 2013, 46(3):692-702.
［9］YE X, BEDDOE G, SLABAUGH G. Automatic graph cut segmentation of lesions in CT using mean shift superpixels［J］. International Journal of Biomedical Imaging, 2010, 210: 1-14.
［10］WEI Y, LI R, YANG J, et al. An algorithm for segmentation of lung ROI by mean-shift clustering combined with multi-scale HESSIAN matrix dot filtering[J]. Journal of Central South University, 2012,19(12): 3500-3509.
［11］TAN Y, SCHWARTZ L H, ZHAO B. Segmentation of lung lesions on CT scans using watershed, active contours, and Markov random field［J］. Medical Physics, 2013, 40(4): 043502.
［12］LE T K. Segmentation of lung vessels together with nodules in CT images using morphological operations and level set method［J］. Journal of Medical and Bioengineering, 2013, 2(1):5-10.
［13］OTSU N. A threshold selection method from gray level histogram［J］. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
［14］WANG K, LYU Q, CAO L, et al. A novel structure analysis filter based on the adaptive window for pulmonary nodules detection［C］// Proceedings of the 3rd International Conference on Computer Science and Automation Engineering. Piscataway: IEEE, 2013:1087-1091.
［15］LI C, XU C. Distance regularized level set evolution and its application to image segmentation［J］. IEEE Transactions on Image Processing, 2010, 19(12): 3243-3254.
［16］MIN M, XIE Y. Comparative study of the histopathological type of peripheral lung cancer and MSCT images with different reconstruction methods［J］.Chinese and Foreign Medical Research, 2012,10(27):2-6.(闵敏,谢应朗.周围型肺癌病理组织学类型与不同重建方法的MSCT征象对比研究［J］.中外医学研究,2012,10(27):2-6.)
［17］WANG X, MA D, CHEN H. Value of spiculation on CT in diagnosis of small peripheral lung carcinoma［J］. Chinese Journal of Medical Imaging, 2006,14(2):127-130.(王晓华,马大庆,陈卉.毛刺征在CT诊断周围型小肺癌中的价值［J］.中国医学影像学杂志,2006,14(2):127-130.)
［18］LI L, ZHENG Y, ZHANG L, et al. False-positive reduction in CAD mass detection using a competitive classification strategy［J］. Medical Physics, 2001, 28(2):250-258.
［19］METZ C E, HERMAN B A, SHEN J H. Maximum-likelihood estimation of Receiver Operating Characteristic (ROC) curves from continuously-distributed data［J］. Statistics in Medicine, 1998, 17(9):1033-1053.
［20］HE Y, SUN A. Explore the calculation formula and mutual relations of Spearman rank correlation coefficient［J］. Chinese Journal of Modern Drug Application,2007,1(7):72-73. (何艳频,孙爱峰. Spearman等级相关系数计算公式及其相互关系的探讨［J］.中国现代医药应用,2007,1(7):72-73.)
［21］ZHENG B, MELLO-THOMS C, WANG X, et al. Interactive computer-aided diagnosis of breast masses: computerized selection of visually similar image sets from a reference library［J］. Academic Radiology, 2007, 14(8):917-927.
［22］WARFIELD S K, ZOU K H,WWLLS W M. Validation of image segmentation by estimating rater bias and variance［C］// MICCAI 2006, LNCS 4191. Berlin: Springer, 2006, 839-847.

[1]	杨鼎康黄帅王顺利翟鹏李一丹张立华. 基于对抗生成网络和网络集成的面部表情识别方法EE-GAN[J]. 计算机应用, 0, (): 0-0.
[2]	秦庭威赵鹏程秦品乐曾建朝柴锐黄永琦. 基于残差注意力机制的点云配准算法[J]. 计算机应用, 0, (): 0-0.
[3]	魏淳武, 赵涓涓, 唐笑先, 强彦. 基于多时期蒸馏网络的随访数据知识提取方法[J]. 计算机应用, 2021, 41(10): 2871-2878.
[4]	李自强, 王正勇, 陈洪刚, 李林怡, 何小海. 基于外观和动作特征双预测模型的视频异常行为检测[J]. 计算机应用, 2021, 41(10): 2997-3003.
[5]	裴仪瑶, 郭会明, 张丹普, 陈文博. 基于定位不确定性的鲁棒3D目标检测方法[J]. 计算机应用, 2021, 41(10): 2979-2984.
[6]	许学斌, 张佳达, 刘伟, 路龙宾, 赵雨晴. 融合空间和通道特征的高精度乳腺癌分类方法[J]. 计算机应用, 2021, 41(10): 3025-3032.
[7]	汪虹余, 张彧, 杨恒, 穆楠. 基于蚁群优化算法的弱光图像显著性目标检测[J]. 计算机应用, 2021, 41(10): 2970-2978.
[8]	张怡孙永荣赵科东李华曾庆化. 空中加油场景下的目标联合检测跟踪算法[J]. 计算机应用, 0, (): 0-0.
[9]	马峻姚震徐翠锋陈寿宏. 基于改进PP-YOLO和Deep-SORT的多无人机实时跟踪算法[J]. 计算机应用, 0, (): 0-0.
[10]	贺怀清闫建青惠康华. 基于深度残差网络的轻量级人脸识别方法[J]. 计算机应用, 0, (): 0-0.
[11]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[12]	张笑非, 杨阳, 黄佳进, 钟宁. 基于度中心性的认知特征选择方法[J]. 计算机应用, 2021, 41(9): 2767-2772.
[13]	姬张建, 任兴旺. 带旋转与尺度估计的全卷积孪生网络目标跟踪算法[J]. 计算机应用, 2021, 41(9): 2705-2711.
[14]	闫钧华侯平张寅吕向阳马越王高飞. 基于多尺度多分类器卷积神经网络的混合失真类型判定方法 [J]. 计算机应用, 0, (): 0-0.
[15]	李福海蒋慕蓉杨磊谌俊毅. 基于生成对抗网络的梯度引导太阳斑点图像去模糊方法[J]. 计算机应用, 0, (): 0-0.