Xing Li; Ruiping Wang

A new efficient 2D combined with 3D CAD system for solitary pulmonary nodule detection in CT images

Full Text (PDF, 229KB), PP.18-24

Views: 0 Downloads: 0

Author(s)

Xing Li ^1,* Ruiping Wang ¹

1. Department of Biomedical Engineering Beijing Jiaotong University Beijing, China

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2011.04.03

Received: 17 Feb. 2011 / Revised: 24 Mar. 2011 / Accepted: 4 May 2011 / Published: 8 Jun. 2011

Index Terms

Lung Cancer, Computer-aided Diagnosis, Solitary pulmonary nodules, 3D, Automated

Abstract

Lung cancer has become one of the leading causes of death in the world. Clear evidence shows that early discovery, early diagnosis and early treatment of lung cancer can significantly increase the chance of survival for patients. Lung Computer-Aided Diagnosis (CAD) is a potential method to accomplish a range of quantitative tasks such as early cancer and disease detection. Many computer-aided diagnosis (CAD) methods, including 2D and 3D approaches, have been proposed for solitary pulmonary nodules (SPNs). However, the detection and diagnosis of SPNs remain challenging in many clinical circumstances. One goal of this work is to develop a two-stage approach that combines the simplicity of 2D and the accuracy of 3D methods. The experimental results show statistically signiﬁcant differences between the diagnostic accuracy of 2D and 3Dmethods. The results also show that with a very minor drop in diagnostic performance the two-stage approach can signiﬁcantly reduce the number of nodules needed to be processed by the 3D method, streamlining the computational demand. Finally, all malignant nodules were detected and a very low false-positive detection rate was achieved. The automated extraction of the lung in CT images is the most crucial step in a computer-aided diagnosis (CAD) system. In this paper we describe a method, consisting of appropriate techniques, for the automated identification of the pulmonary volume. The performance is evaluated as a fully automated computerized method for the detection of lung nodules in computed tomography (CT) scans in the identification of lung cancers that may be missed during visual interpretation.

Cite This Paper

Xing Li,Ruiping Wang,"A new efficient 2D combined with 3D CAD system for solitary pulmonary nodule detection in CT images",IJIGSP, vol.3, no.4, pp.18-24, 2011. DOI: 10.5815/ijigsp.2011.04.03

Reference

[1]HeitzmanER. The role of computed tomography in the diagnosis and management of lung cancer: an overview. Chest 1986; 89(suppl 4): 237S–241S.

[2]HoweMA, Gross BH. CT evaluation of the equivocal pulmonary nodule. Comput Radiol 1987; 11: 61–67.

[3]HenschkeCI, McCauley DI, Yankelevitz DF, et al. Early Lung Cancer Action Project: overall design and findings from baseline screening. Lancet 1999; 354: 99–105. CrossRefMedlineWeb of Science

[4]YankelevitzDF, Reeves AP, Kostis WJ, Zhao B, Henschke CI. Small pulmonary nodules: volumetrically determined growth rates based on CT evaluation. Radiology 2000; 217: 251–256.

[5]ormanns D, Fiebich M, Saidi M, Diederich S, Heindel W. Automatic detection of pulmonary nodules at spiral CT: clinical application of a computer-aided diagnosis system. Eur Radiol2002; 12: 1052 -1057.

[6]McNitt-Gray M. Lung nodules and beyond: approaches, challenges and opportunities in thoracic CAD. Int Congr Ser 2004;1268:896–901.

[7]Li Q, Li F, Suzuki K, Shiraishi J, Abe H, Engelmann R, et al. Computer-aided diagnosis in thoracic CT. Semin Ultrasound CT MR 2005;25(5):357–63.

[8]McNitt-GrayMF,WyckoffN, Sayre JW,Goldin JG,AberleDR. The effects of co-occurrence matrix based texture parameters on the classiﬁcation of solitary pulmonary nodules imaged on computed tomography. Comput Med Imaging Graph 1999;23(6):339–48.

[9]YiCA, LeeKS,KimEA,Han J,KimH,KwonOJ, et al. Solitary pulmonary nodules: dynamic enhanced multi-detector row CT study and comparison with vascular endothelial growth factor andmicrovessel density. Radiology 2004;233(1):191–9.

[10]Jeong YJ, Lee KS, Jeong SY, Chung MJ, Shim SS, Kim H, etal. Solitary pulmonary nodule: characterization with combined wash-inand washout features at dynamic multi-detector row CT. Radiology 2005;237(2):675–83.

[11]Suzuki K, Li F, Sone S, Doi K. Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artiﬁcial neural network. IEEE Trans Med Imag 2005;24(9):1138–50.

[12]Fuchs TOJ, Kachelriess M, Kalender WA, Fast volume scanning approaches by X-ray-computed tomography. In: Proc IEEE Comput Soc Bioinform Conf; 2003;91(10). p. 1492–502.

[13]Kanazawa K, Kawata Y, Niki N, Satoh H, Ohmatsu H, Kakinuma R, etal. Computer-aided diagnosis for pulmonary nodules based on helical CT images. Comput Med Imaging Graph 1998;22(2):157–67.

[14]Kawata Y, Niki N, Ohmatsu H, Moriyama N. Example-based assisting approach for pulmonary nodule classiﬁcation in three-dimensional thoracic computed tomography images. Acad Radiol 2003;10(12):1402–15.

[15]Awai K, Murao K, Ozawa A, Nakayama Y, Nakaura T, Liu D, et al. Pulmonary nodules: estimation ofmalignancy at thin-section helical CT-effect of computer-aided diagnosis on performance of radiologists. Radiology 2006;239(1):276–84.

[16]Mori K, Niki N, Kondo T, Kamiyama Y, Kodama T, Kawada Y, et al.Development of a novel computer-aided diagnosis system for automatic discrimination of malignant from benign solitary pulmonary nodules on thin-section dynamic computed tomography. J Comput Assist Tomogr 2005;29(2):215–22.

[17]Shah SK, McNitt-Gray MF, Rogers SR, Goldin JG, Suh RD, Sayre JW, et al. Computer aided characterization of the solitary pulmonary nodule using volumetric and contrast enhancement features. Acad Radiol 2005;12(10):1310–9.

[18]Petkovska I, Shah SK, McNitt-Gray MF, Goldin JG, Brown MS, Kim HJ, et al. Pulmonary nodule characterization: a comparison of conventionalwith quantitative and visual semi-quantitative analyses using contrast enhancement maps. Eur J Radiol 2006;59(2):244–52.

[19]Yeh C, Lin C-L, Wu M-T, Yen C-W, Wang J-F. A neural network based diagnosis method for characterizing solitary pulmonary nodules. Neuro computing 2008, doi:10.1016/j.neucom.2007.11.009.

[20]Hu S, Hoffman EA, Reinhardt JM. Automatic lung segmentation for accurate quantitation of volumetric x ray CT images. IEEE Trans Med Imag2001;20(6):490–8.

[21]Armato SG 3rd, MacMahon H. Automated lung segmentation and computer-aided diagnosis for thoracic CT scans. Int Congr Ser 2003; 1256:977–82.

[22]Kuhnigk JM, Dicken V, Bornemann L, Bakai A,Wormanns D, Krass S, etal. Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic CT scans. IEEE Trans Med Imag 2006;25(5):417–34. [23] Reeves AP, Chan AB, Yankelevitz DF, Henschke CI, Kressler B, Kostis WJ. On measuring the change in size of pulmonary nodules. IEEE Trans Med Imag 2006;25(4):435–50.

[24]H.P.Ng, S.H.ong, K.W.C.Foong, P.S.Goh, and W.L.Nowinski, “Medical image segmentation using K-means clustering and improver watershed algorithm,” in Proc. IEEE Southwest Symposium on Image Analysis and Interpretation, pp.61-65, 2006.

[25]V. Grau, A. U. J. Mewes, M. Alcañiz, R. Kikinis and S. K. Warfield, “Improved Watershed Transform for Medical Image Segmentation Using Prior Information”, IEEE Transactions on Medical Imaging, Vol. 23, No. 4, April 2004

[26]ormanns D, Fiebich M, Saidi M, Diederich S, Heindel W. Automatic detection of pulmonary nodules at spiral CT: clinical application of a computer-aided diagnosis system. Eur Radiol2002; 12: 1052 -1057.

[27]M.N. Gurcan, B. Sahiner, N. Petrick, H.P. Chan, E.A.Kazerooni, P.N. Cascade, L.M. Hadjiiski, Lung nodule detection on thoracic computed tomography images: preliminary evaluation of a computer-aided diagnosis system, Medical Physics (2002) 2552–2558.

[28]J.R.F. da Silva Sousa, Metodologia Automatica para Deteccao de Nodulos Pulmonares, Master’s Thesis, Universidade Federal do Maranhao, 2007.

[29]V.N. Vapnik, Statistical Learning Theory, Wiley-Interscience, ISBN: 0471030031, URL http://www.amazon.ca/exec/obidos/redirect?tag=citeulike0420&path=ASIN/0471030031,1998.

[30]G. Agam, S.G.A. Iii, C. Wu, Vessel tree reconstruction in thoracic CT scans with application to nodule detection, IEEE Transactions on Medical Imaging 24 (4) (2005) 486–499.

[31]K. Peldschus, P. Herzog, S.A. Wood, J.I. Cheema, P. Costello, U.J. Schoepf, Computer-aided diagnosis as a second reader: spectrum of ﬁndings in CT studies of the chest interpreted as normal, Chest 128 (2005) 1517–1523.

[32]J.R.F. da Silva Sousa, Metodologia Automatica para Deteccao de Nodulos Pulmonares, Master’s Thesis, Universidade Federal do Maranhao, 2007.

[33]S. Chang, H.D. Emoto, L.A. Metaxas, Pulmonary micronodule detection from 3-D chest CT, Lecture Notes in Computer Science-Medical Image Computing and Computer-Assisted Intervention 3217 (2004) 821–828.

[34]X. Lu, G.-Q. Wei, J.Z. Qian, A.K. Jain, Learning-based pulmonary nodule detection from multislice CT data, CARS (2004) 1356.

[35]W. Mousa, M. Khan, Lung nodule classiﬁcation utilizing support vector machines, in: ICIP02, III, 2002, pp. 153–156.

[36]J.R.F. da Silva Sousa, Metodologia Automatica para Deteccaode Nodulos Pulmonares, Master’s Thesis, Universidade Federal do Maranhao, 2007.

[37]K. Suzuki, Z. Shi, J. Zhang, Supervised enhancement of lung nodules by use of a massive-training artiﬁcial neural network (MTANN) in computer-aided diagnosis (CAD), in: ICPR08, 2008, pp. 1–4.

[38]S.-C.B. Lo, L.-Y. Hsu, M.T. Freedman, Y.M.F. Lure, H. Zhao, Classiﬁcation of lung nodules in diagnostic CT: an approach based on 3-D vascular features, in: Nodule Density Distributions, and Shape Features, The International Society for Optical Engineering, Presented at the Society of Photo-Optical Instrumentation Engineers (SPIE) Conference, San Jose, California -EUA, 2003, pp. 183–189.

[39]X. Zhang, G. McLennan, E.A. Hoffman, M. Sonka, Computerized detection of pulmonary nodules using cellular neural networks in CT images, in: Medical Imaging 2004: Image Processing, San Diego, CA, USA, 2004.

[40]A. Farag, A. El Baz, G. Gimel’farb, R. Falk, Detection and recognition of lung nodules in spiral CT images using deformable templates and Bayesian post-classiﬁcation, in: ICIP04 V, 2004, pp. 2921–2924.

[41]C.C. McCulloch, R.A. Kaucic, P.R. Mendonca, D.J. Walter, R.S. Avila, Model-based detection of lung nodules in computed tomography exams 1: thoracic computer-aided diagnosis, Academic Radiology 11 (3) (2004) 258–266.

[42]J.R.F. da Silva Sousa, A.C. Silva, A.C. de Paiva, Lung structure classiﬁcation using 3D geometric measurements and SVM, in: CIARP, Iberoamerican Congress on Pattern Recognition, 2007, pp. 783–792.

[43]S.G. Armato, M.L. Giger, H. MacMahon III, Automated detection of lung nodules in CT scans: preliminary results, Medical Physics 28 (2001) 1552–1561.

[44]H. Arimura, S. Katsuragawa, K. Suzuki, F. Li, J. Shiraishi, S. Sone, K. Doi, Computerized scheme for automated detection of lung nodules in low-dose CT images for lung cancer screening, Academic Radiology 11 (2004) 617–629.

[45]S.G.A. Li, F. Giger, M.L. MacMahon, H. Sone, S. Doi III, Lung cancer: performance of automated lung nodule detection applied to cancers missed in a CT screening program, Radiology, 225 (2002) 685–692.

[46] V. Grau, A. U. J. Mewes, M. Alcañiz, R. Kikinis and S. K. Warfield, “Improved Watershed Transform for Medical Image Segmentation Using Prior Information”, IEEE Transactions on Medical Imaging, Vol. 23, No. 4, April 2004.

International Journal of Image, Graphics and Signal Processing (IJIGSP)