Skip to main content
SpringerLink
Log in

Analysis of spatial variability using geostatistical functions for diagnosis of lung nodule in computerized tomography images

  • Short Paper
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

This paper analyzes four geostatistical functions—semivariogram, semimadogram, covariogram, and correlogram—with the purpose of characterizing lung nodules as malignant or benign in computerized tomography images. The tests described in this paper were carried out using a sample of 30 nodules, 24 benign and 6 malignant. Stepwise discriminant analysis was used to determine which combination of measures were best able to discriminate between the benign and malignant nodules. Then, a linear discriminant analysis procedure was performed using the selected features to evaluate the ability of these features to predict the classification for each nodule. A leave-one-out procedure was used to provide a less biased estimate of the linear discriminator’s performance. All analyzed functions have value area under receiver operation characteristic (ROC) curve above 0.800, which means results with accuracy between good and excellent. The preliminary results of this approach are very promising in characterizing nodules using geostatistical functions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Tarantino AB (1997) In: Doenças Pulmonares (ed) Nódulo solitário do pulmão, 4th edn. Guanabara Koogan, Rio de Janeiro pp 733–753

  2. Gonzalez RC, Woods RE (1992) Digital image processing. 3rd edn. Addison-Wesley, Reading, Massachusetts

  3. Kovalev VA, Kruggel F, Gertz HJ, Cramon DYV (2001) Three-dimensional texture analysis of MRI brain datasets. IEEE Trans Med Imaging 20:424–433

    Article  Google Scholar 

  4. Li X (2001) Texture analysis for optical coherence tomography image. Masters thesis, University of Arizona

  5. Freeborough PA, Fox NC (1998) MR texture analysis to the diagnosis and tracking of Alzheimer’s disease. IEEE Trans Med Imaging 17:475–479

    Article  Google Scholar 

  6. McNitt-Gray MF, Hart EM, Wyckoff N, Sayre JW, Goldin JG, Aberle DR (1999) A pattern classification approach to characterizing solitary pulmonary nodules imaged on high resolution CT: preliminary results. Med Phys 26:880–888

    Article  Google Scholar 

  7. McNitt-Gray MF, Hart EM, Wyckoff N, Sayre JW, Goldin JG, Aberle DR (1999) The effects of co-occurrence matrix based texture parameters on the classification of solitary pulmonary nodules imaged on computed tomography. Comput Med Imaging Graph 23:339–348

    Article  Google Scholar 

  8. Sahine B, Chan HP, Petrick N, Wei D, Helvie MA, Adler DD, Goodsill MM (1996) Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images. IEEE Trans Med Imaging 15:598–610

    Article  Google Scholar 

  9. Mudigonda NR, Rangayyan RM, Desautels JEL (2000) Gradient and texture analysis for the classification of mammographic masses. IEEE Trans Med Imaging 19:1032–1043

    Article  Google Scholar 

  10. Galloway MM (1975) Texture analysis using gray level run lengths. Comput Graph Image Processing 4:172–179

    Google Scholar 

  11. Ferreyra R, Apezteguia H, Sereno R, Jones J (2002) Reduction of soil water spatial sampling density using scaled semivariograms and simulated annealing. Geoderma 110:265–289

    Article  Google Scholar 

  12. Bruniquel-Pinel V, Gastellu-Etchegorry JP (1998) Sensitivity of texture of high resolution images of forest to biophysical and acquisition parameters. Remote Sensing Environ 65:61–85

    Article  Google Scholar 

  13. Carr JR, de Miranda FP (1998) The semivariogram in comparison to the co-occurrence matrix for classification of image texture. IEEE Trans Geosci Remote Sensing 36:1945–1952

    Article  Google Scholar 

  14. Goodin D, Henebry GM (1998) Variability of spectral reflectance and vegetation indices in tallgrass prairie: spatio-temporal analysis using semivariograms and close-range remote sensing. In: Proceedings of the IEEE international geoscience and remote sensing symposium (IGARSS’98), vol 2, Seattle, Washington, July 1998, pp 825–827

  15. Goodin D, 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 Sensing 42:154–165

    Article  Google Scholar 

  16. Dai X, Khorram S (1998) The effects of image misregistration on the accuracy of remotely sensed change detection. IEEE Trans Geosci Remote Sensing 36:1566–1577

    Article  Google Scholar 

  17. Chica-Olmo M, Abarca-Hernandez F (2000) Computing geostatistical image texture for remotely sensed data classification. Comput Geosci 26:373–383

    Article  Google Scholar 

  18. Toshioka S, Kanawawa K, Niki N (1997) Computer aided diagnosis system for lung cancer based on helical CT images. Proc Med Imaging SPIE 3034:975–984

    Google Scholar 

  19. Kawata Y, Niki N, Ohmatsu H, Kusumoto M, Kakinuma R, Mori K, Nishiyama H, Eguchi K, Kaneko M, Moriyama N (1999) Computer aided differential diagnosis of pulmonary nodules using curvature based analysis. In: Proceedings of the international conference on image analysis and processing, vol 2, Venice, Italy, September 1999. IEEE Computer Society Press, Washington, DC, pp 470–475

  20. Silva AC, Carvalho PCP, Gattass M (2003) Investigaçãode métodos estatísticos baseados em textura 3D para diagnóstico de nódulo pulmonar em imagens de tomografia computadorizada. In: III Workshop de Informática Médica, Fortaleza

  21. Clunie DA (2000) DICOM structured reporting. PixelMed Publishing, Pennsylvania

  22. Nikolaidis N, Pitas I (2001) 3-D image processing algorithms. Wiley, New York

  23. Silva AC, Carvalho PCP (2002) Sistema de análise de nódulo pulmonar. In: II Workshop de Informática aplicada a saúde, Itajai, Universidade de Itajai. Available at http://www.visgraf.impa.br/Projects/vismed/lung/doc1/CBComp2002.pdf.

  24. Clark I (1979) Practical geostatistics. Applied Science Publishers, London

  25. Cressie NAC (1993) Statistical for spatial data. Wiley, New York

  26. Journel AG, Huijbregts CJ (1978) Mining geostatistics. Academic Press, London

  27. Lachenbruch PA (1975) Discriminant analysis. Hafner Press, New York

  28. Fukunaga K (1990) Introduction to statistical pattern recognition, 2nd edn. Academic Press, London

  29. Erkel ARV, Pattynama PMT (1998) Receiver operating characteristic (ROC) analysis: basic principles and applications in radiology. Eur J Radiol 27:88–94

    Article  Google Scholar 

  30. Technologies L (2003) SPSS 11.0 for Windows. Available at http://www.spss.com

  31. Metz CE (2003) ROCKIT software. Available at http://xray.bsd.uchicago.edu/krl/KRL_ROC/software_index.htm

  32. Deutsch CV, Journel AG (1992) GSLIB: geostatistical software library and user’s guide. Oxford University Press, New York

  33. Greinera M, Pfeifferb D, Smithc R (2000) Principles and practical application of the receiver-operating characteristic analysis for diagnostic tests. Prev Vet Med 45:23–41

    Article  Google Scholar 

Download references

Acknowledgments

We would like to thank CAPES and FAPERJ for the financial support, Dr. Rodolfo A. Nunes and his team for the clinical support, and the staff from Instituto Fernandes Figueira, particularly Dr. Marcia Cristina Bastos Boechat, for the images provided.

Author information

Authors and Affiliations

  1. Department of Computer Science, Pontifical Catholic University of Rio de Janeiro - PUC-Rio, R. Marquês de São Vicente, 225, Gávea, 22453-900, Rio de Janeiro, RJ, Brazil

    Aristófanes C. Silva & Marcelo Gattass

  2. Institute of Pure and Applied Mathematics - IMPA, Estrada D. Castorina, 110, Horto, 22460-320, Rio de Janeiro, RJ, Brazil

    Paulo Cezar P. Carvalho

Authors
  1. Aristófanes C. Silva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Paulo Cezar P. Carvalho
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marcelo Gattass
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Aristófanes C. Silva.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Silva, A.C., Carvalho, P.C.P. & Gattass, M. Analysis of spatial variability using geostatistical functions for diagnosis of lung nodule in computerized tomography images. Pattern Anal Applic 7, 227–234 (2004). https://doi.org/10.1007/s10044-004-0219-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-004-0219-0

Keywords

Search

Navigation