Abstract
This paper analyzes the application of Moran’s index and Geary’s coefficient to the characterization of lung nodules as malignant or benign in computerized tomography images. The characterization method is based on a process that verifies which combination of measures, from the proposed measures, has been best able to discriminate between the benign and malignant nodules using stepwise discriminant analysis. Then, a linear discriminant analysis procedure was performed using the selected features to evaluate the ability of these in predicting the classification for each nodule. In order to verify this application we also describe tests that were carried out using a sample of 36 nodules: 29 benign and 7 malignant. A leave-one-out procedure was used to provide a less biased estimate of the linear discriminator’s performance. The two analyzed functions and its combinations have provided above 90% of accuracy and a value area under receiver operation characteristic (ROC) curve above 0.85, that indicates a promising potential to be used as nodules signature measures. The preliminary results of this approach are very encouraging in characterizing nodules using the two functions presented.
Similar content being viewed by others
References
Anselin L (2001) Computing enviroments for spatial data analysis. J Geogr Syst 2:201–220
Anselin L, Kim Y, Syabri I (2004) Web-based analytical tools for the exploration of spatial data. J Geogr Syst 6:197–218
Arimura H, Katsuragawa S, Suzuki K, Li F, Shiraishi J, Sone S, Doi K (2004) Computerized scheme for automated detection of lung nodules in low-dose CT images for lung cancer screening. Acad Radiol 11:617–629
Armato SG III, Giger ML, Moran CJ, Blackburn JT, Doi K, MacMahon H (1999) Computerized detection of pulmonary nodules on CT scans. Radiographics 19(5):1303–1311
Armato SG III, Li F, Giger ML, MacMahon H, Sone S, Doi K (2002) Lung cancer: Performance of automated lung nodule detection applied to cancers missed in a CT screening program. Radiology 225:685–692
Brown MS, Goldin JG, Suh RD, McNitt-Gray MF, Sayre JW, Aberle DR (2003) Lung micronodules: automated method for detection at thin-section CT-initial experience 1. Radiology 226:256–262
Chica-Olmo M, Abarca-Hernandez F (2000) Computing geostatistical image texture for remotely sensed data classification. Comput Geosci 26:373–383
Clark I (1979) Practical geostatistics. Applied Sience, London
Clunie DA (2000) DICOM structered reporting. PixelMed, Pennsylvania
Dehmeshki J, Ye X, Valdivieso M, Roddie M, Costello J (2003) Shape based region growing using derivatives of 3D medical images: application to automatic detection of pulmonary nodules. Image and Signal Processing and Analysis, 2:1118–1123 vol 2, September 2003. ISPA 2003. Proceedings of the 3rd International Symposium
Ferreyra RA, Apezteguia HP, Sereno R, Jones JW (2002) Reduction of soil water spatial sampling density using scaled semivariograms and simulated annealing. Geoderma 110:265–289
Fortin M, Drapeau P, Legendre P (1989) Spatial autocorrelation and sampling design in plant ecology. Plant Ecol 83(1–2):209–222
Fukunaga K (1990) Introduction to statistical pattern recognition, 2nd edn. Academic, London
Gonzalez RC, Woods RE (1992) Digital image processing, 3rd edn. Addison-Wesley, Reading
Goodin DG, Gao J, Henebry GM (2004) The effect of solar illumination angle and sensor view angle on observed patterns of spatial structure in tallgrass prairie. IEEE Trans Geosci Remote Sens 42(1):154–165
Gould MK (2003) Cost-effectiveness of alternative management strategies for patients with solitary pulmonary nodules. Ann Intern Med 9(138):724–735
Greinera M, Pfeifferb D, Smithc RD (2000) Principles and practical application of the receiver-operating characteristic analysis for diagnostic tests. Prev Vet Med 45:23–41
Griffith DA (2004) Distributional properties of georeferenced random variables based on the eigenfunction spatial filter. J Geogr Syst 6:263–288
Hashimoto Y, Tsujikawa T, Kando C, Maki M, Mamore M, Nagai A, Ohnuki T, Nishikawa T, Kusakabe K (2006) Accuracy of PET diagnosis of solid pulmonary lesions with 18 F-FDG de 2,5. J Nucl Med 47 (3):426–31
INCA (2003) Estimativas da incidência e mortalidade por câncer no Brasil. Available in: http://www.inca.gov.br/estimativas/2003/versaofinal.pdf
Jeong YJ, Lee KS, Jeong SY, Chung MJ, Shim SS, Kim H, Kwon OJ, Kim S (2005) Solitary pulmonary nodule: characterization with combine wash-in and washout features of dynamic multidector row CT. Radiology 2(237):675–683
Johnson WH (2000) Exploratory use of spatial statistics to inform the choice of variables for stratifying non-self representing cities for the next CPI PSU sample selection. Available at http://www.amstat.org/sections/srms/Proceedings/papers/2000_043.pdf
Journel AG, Huijbregts CHJ (1978) Mining geostatistics. Academic, London
Kawata Y, Niki N, Ohmatsu H, Kakinuma R, Eguchi K, Kaneko M, Moriyama N (1997) Classification of pulmonary nodules in thin-section CT images based on shape characterization. In: International conference on image processing, vol 3, pp 528–530. IEEE Computer Society Press
Kovalev VA, Kruggel F, Gertz H-J, Yves Von Cramon D (2001) Three-dimensional texture analysis of MRI brain datasets. IEEE Trans Med Imaging 20(5):424–433
Lachenbruch PA (1975) Discriminant analysis. Hafner, New York
Lag R (2005) Seer cancer statistics review, 1975–2002. Technical report, National Cancer Institute, Bethesda 2002. Available at http://seer.cancer.gov/csr/1975_2002/, based on November 2004 SEER data submission, posted to the SEER web site
Levine N (2004) CrimeStat III: A spatial statistics program for the analysis of crime incident locations (version 3.0). Ned Levine & Associates/National Institute of Justice, Houston/Washington, DC
Li X (2001) Texture analysis for optical coherence tomography image. Master’s thesis, The University of Arizona
Lead Technologies (2003) SPSS 11.0 for windows. Available at http://www.spss.com
Metz CE (2003) ROCKIT software. Available at http://www-radiology.uchicago.edu/krl/toppage11.htm
Meyer-Baese A (2003) Pattern recognition for medical imaging. Elsevier, Amsterdam
Mudigonda NR, Rangayyan RM, Leo Desautels JE (2000) Gradient and texture analysis for the classification of mammographic masses. IEEE Trans Med Imaging 19(10):1032–1043
Mark RT, Dixon DP, Fortin M-J, Legendre P, Myers DE, Rosenberg MS (2002) Conceptual and mathematical relationships among methods for spatial analysis. Ecography 25:558–577
Nakamura Y, Fukano G, Takizawa H, Mizuno S, Yamamoto S, Matsumoto T, Tateno Y, Iinuma T (2004) Eigen nodule: view-based recognition of lung nodule in chest x-ray CT images using subspace method. Pattern Recognition, 4:681–684 ICPR 2004. Proceedings of the 17th international conference on publication
Nikolaidis N, Pitas I (2001) 3-D image processing algorithms. Wiley, New York
Ost D, Fein AM, Feinsilver SH (2003) The solitary pulmonary nodule. N Engl J Med 25(348):2535–2542
Páez A, Scott DM (2004) Spatial statistics for urban analysis: A review of techniques with examples. Geo J 2004:53–67
Pepe G, Rosseti C, Sironi S, Landoni G, Gianoli L, Pastorino U, Zannini P, Mezzetti M, Grimaldi A, Galli L, Messa C, Fazio F (2005) Patients with known or suspected lung cancer: evaluation of clinical management changes due to 18 F-deoxyglucose positron emission tomography (18 F-FDG PET) study. Nucl Med Commun 9(26):831–837
Rosenberg MS, Sokal RR, Oden NL, DiGiovanni D (1999) Spatial autocorrelation of cancer in western Europe. Eur J Epidemiol 15(1):15–22
Schrump DS, Altorki NK, Henschke CL, Carter D, Turrisi AT Gutierrez ME Non-Small Cell Lung Cancer. In: De Vita VT, Hellman S, Rosenberg SA (eds) Cancer, principles and practice of Oncology, 6th edn. Lippincott Williams and Wilkins, Philadelphia pp 753–810
Sergiacomi G, Schiallaci O, Leporace M, Lavini F, Danieli CM, Simonetti G (2006) Integrated multislice CT and Tc-99 m sestamibi spect-CT-evaluation of solitary pulmonary nodule. Radiol Med 111(2):213–24
Shah S, McNitt-Gray M, Rogers S, Goldin J, Suh R, Sayre J, Petkovska I, Kim H, Aberle D (2005) Computer aided characterization of the solitary pulmonary nodule using volumetric and contrast enhancement features. Acad Radiol 12(10):1310–1319
Shimada T (2002) Global Moran’s I and small distance adjustment: spatial pattern of crime in Tokyo. National Research Institute of Police Science, National Police Agency, Chiba Available at http://www.icpsr.umich.edu/CRIMESTAT/files/CrimeStatChapter.4.pdf
Silva AC, Carvalho PCP (2002) Sistema de análise de nódulo pulmonar. In II Workshop de Informática aplicada a Saúde. Itajai, Agosto Universidade de Itajai. Available at http://www.cbcomp.univali.br/pdf/2002/wsp035.pdf
Silva AC, Pinto Carvalho PC, Gattass M (2004) Analysis of spatial variability using geostatistical functions for diagnosis of lung nodule in computerized tomography images. Pattern Anal Appl 7(3):227 – 234
Su H, Qian W, Sankar R, Sun X (2004) A new knowledge-based lung nodule detection system. Acoustics, Speech, and Signal Processing. 5:V–445-8 vol 5, May 2004. Proceedings. (ICASSP ’04). IEEE International Conference
Swensen SJ (1997) The probability of malignancy in solitary nodules. application to small radiologically indeterminate nodules. Arch Intern Med 8(157):849–855
Tarantino AB (1997) Chapter 38. Nódulo Solitário Do Pulmão, 4th edn. Guanabara Koogan, Rio de Janeiro, pp 733–753
Wormanns D, Fiebich M, Saidi M, Diederich S, Heindel W (2002) Automatic detection of pulmonary nodules at spiral CT: clinical application of a computer-aided diagnosis system. Eur Radiol 12(5):1052–1057
Yi CA, Lee KS, Kim BT, Choi JY, Kwon OJ, Kim H, Shim YM, Chung MJ (2006) Tissue characterization of solitary pulmonary nodule: comparative study between helical dynamic CT and integrated PET/CT. J Nucl Med 47(3):443–50
Acknowledgments
We would like to thank CNPQ (process 506624/2004-8) and CAPES (process 0044/05-9) for the financial support, the staff from Instituto Fernandes Figueira, particularly Dr. Marcia Cristina Bastos Boechat, for the images provided.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
da Silva, E.C., Silva, A.C., de Paiva, A.C. et al. Diagnosis of lung nodule using Moran’s index and Geary’s coefficient in computerized tomography images. Pattern Anal Applic 11, 89–99 (2008). https://doi.org/10.1007/s10044-007-0081-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-007-0081-y