期刊文献+

改进的表面法向量投影叠加CT图像疑似肺结节检测算法 被引量:2

Suspected lung nodule detection algorithm based on improved surface normal overlap in thoracic CT images
下载PDF
导出
摘要 对表面法向量投影叠加法进行改进,提出一种基于三维局部形状约束并采用自适应投影距离的表面法向量叠加疑似肺结节检测方法。现有的表面法向量投影叠加法没有对初始ROI(region of interest)区域表面进行形状约束,采用单一投影距离,存在投影叠加计算量大且只适用于固定大小的肺结节检测问题。首先采用Otsu阈值方法得到初始ROI区域,计算初始ROI曲面的三维局部形状指数,对三维ROI的体素表面法向量进行投影约束,以提高球形选择性、减少投影叠加计算量;在表面法向量叠加过程中由ROI曲面自适应地决定投影距离,一方面限制表面法向量向ROI曲面外投影;另一方面可以克服检测固定大小肺结节的局限性;由于肺结节一般表现为球形,具有较大的表面法向量投影叠加值,选择局部最大叠加值,可以检测不同大小的球形疑似肺结节区域。实验结果表明,改进算法具有更好的球形选择性,可以较好地检测出不同大小的疑似肺结节,具有较高的敏感度和较低的假阳性率。 An improved surface normal overlap algorithm for suspected pulmonary nodule detection is proposed in this paper. The improved surface normal overlap detection algorithm is based on local 3-D shape constraint and adopts adaptive distance projections according to surface of original ROI. Existing surface normal overlap algorithm has no shape character restriction on RO1 surface and projection distance is fixed, it may fail to distinguish between a small size sphere object and a much larger size non-sphere object, and is also time-consuming. So, existing method is only applicable to the nodules with fixed size. In this paper, Original region of interests in pulmonary parenchyma is seg-mented with adaptive threshold method. Voxel surface normal of original ROI is constrained in projection. Local 3-D shape character is used in the courses of projection overlapping, which enhances the capability of sphere selection and increases the effect of projection overlapping. Surface of original ROI decision-making projection overcomes the limit of detecting fixed size nodules, prohibits the projection outside the original ROI. So the suspected lung nodules can be detected with local maximum method. Experiment results indicate that the improved algorithm has the ability of sphere selection, can detect suspected pulmonary nodules effectively, and has higher sensitivity and lower false positive rate.
出处 《仪器仪表学报》 EI CAS CSCD 北大核心 2011年第12期2787-2793,共7页 Chinese Journal of Scientific Instrument
基金 国家自然科学基金(60671050) 中央高校基本科研业务专项资金(N100404010)资助项目
关键词 疑似肺结节 法向量投影叠加 局部三维形状约束 曲面决策投影 suspected pulmonary nodule normal projection overlap local 3-D shape restriction surface decision-making projection
  • 相关文献

参考文献15

  • 1LI Q. Recent progress in computer-aided diagnosis of lung nodules on thin-section CT[ J ]. Computerized Med- ical Imaging and Graphics, 2007, 31 (3) :248-257. 被引量:1
  • 2LEE Y, I-IARA T, FUJITA H, et al. Automated detec- tion of pulmonary nodules in helical CT images based on an improved template-matching technique [ J ]. IEEE Transactions on Medical Imaging, 2001, 20 ( 7 ) : 595 -604. 被引量:1
  • 3LI Q, SONE S, DOI K. Selective enhancement filters for nodules, vessels, and airway walls in two- and three-di- mensional CT scans [ J ]. Med. Phys., 2003, 30: 2040 -2051. 被引量:1
  • 4OKUMURA T, MIWA T, JUNICHI K, et al. Automatic detection of lung cancers in chest CT images by variable N-Quoit filter [ C ]. Fourteenth International Conference on Pattern Recognition, Brisbane, Australia, 1998, 2 (8) :1671-1673. 被引量:1
  • 5WIEMKER R, ZWARKRUIS A. Optimal thresholding for 3D segmentation of pulmonary nodules in high resolution CT[C]. 15th Congress CARS 2001, Berlin, Germany. 2001,1230:653-658. 被引量:1
  • 6薛以峰.计算机辅助肺癌特征提取及分类方法的研究[D].南京:东南大学,2006:17-23. 被引量:1
  • 7魏颖,于谦,贾同,赵大哲.面向肺癌CAD的CT图像疑似病灶检测算法[J].仪器仪表学报,2009,30(1):1-6. 被引量:9
  • 8贾同,魏颖,吴成东.基于几何形变模型的三维肺血管图像分割方法[J].仪器仪表学报,2010,31(10):2296-2301. 被引量:18
  • 9PAIK D S, BEAULIEU C F, RUBIN G D, et al. Surface normal overlap: A computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT [ J]. IEEE Transactions on Medical Image, 2004,23 : 661-675. 被引量:1
  • 10ZHANG X W, STOCKEL J, WOLF M, et al. A new method for spherical object detection and its application to computer aided detection of pulmonary nodules in CT images[ C]. MICCAI 2007, Brisbane, Australia, 2007, Part 1 ,LNCS 4791:842-849. 被引量:1

二级参考文献36

共引文献56

同被引文献19

  • 1KARCAALTINCABA M,AKTAS A. Dual-energy CT revisited with multidetector CT:Review of principles and clinical applications[J].Diagn Interv Radiol,2011.181-194. 被引量:1
  • 2JOHNSON T R,KRAUSS B,SEDLMAIR M. Material differentiation by dual energy CT:Initial experience[J].Eur Radiol,2007,(06):1510-1517. 被引量:1
  • 3GRASER A,JOHNSON T R C,CHANDARANA H. dual-energy CT applications in the abdomen[J].AJR,2012,(05):S64-S70. 被引量:1
  • 4MONGAN J,RATHNAYAKE S,FU Y. In vivo differentiation of complementary contrast media at dual-energy CT[J].RADIOLOGY,2012,(01):267-272. 被引量:1
  • 5BENJAMIN M Y,SHEPHERD J A,WANG Z J. Dual-energy and low-kVp CT in the abdomen[J].AJR,2009,(01):47-54. 被引量:1
  • 6MANGOLD S,THOMAS C,FENCHEL M. Virtual nonenhanced dual-Energy CT urography with tin-filter technology:determinants of detection of urinary calctdi in the renal collecting system[J].RADIOLOGY,2012,(01):119-125. 被引量:1
  • 7LAURA A D,DAVID A J. Advances in image-guided radiation therapy[J].Journal of Clinical Oncology,2007,(08):938-946. 被引量:1
  • 8DONG Y,HUO J,WANG X. Generation of dual-energy CT image dataset from single-energy CT image dataset[J].Medical Physics,2013,(06):152. 被引量:1
  • 9BAI C Y,SHAO L,DA SILVA A J. A generalized model for the conversion from CT numbers to linear attenuation coefficients[J].IEEE Transactions on Nuclear Science,2003,(05):1510-1515. 被引量:1
  • 10TEIMOURIAN B,AY M R,ZAFARGHANDI M. A novel energy mapping approach for CT-based attenuation correction in PET[J].Medical Physics,2012,(04):2078-2089. 被引量:1

引证文献2

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部