Artificial Intelligence in Medicine
Volume 41, Issue 1 , Pages 39-55 , September 2007

Multi-scaled morphological features for the characterization of mammographic masses using statistical classification schemes

  • Harris Georgiou

      Affiliations

    • University of Athens, Informatics Department, TYPA Buildings, University Campus, 15771 Athens, Greece
    • Corresponding Author InformationCorresponding author at: 11 Vas. Dipla str, P.O. 11745, Athens, Greece. Tel.: +30 210 9313361; fax: +30 210 9313631.
    • ,
  • Michael Mavroforakis

      Affiliations

    • University of Athens, Informatics Department, TYPA Buildings, University Campus, 15771 Athens, Greece
    • ,
  • Nikos Dimitropoulos

      Affiliations

    • Medical Imaging Department, EUROMEDICA Medical Center, 2 Mesogeion Avenue, Athens, Greece
    • ,
  • Dionisis Cavouras

      Affiliations

    • Medical Imaging Technologies Department, TEI-Athens, 12210 Athens, Greece
    • ,
  • Sergios Theodoridis

      Affiliations

    • University of Athens, Informatics Department, TYPA Buildings, University Campus, 15771 Athens, Greece

Received 14 October 2006 ,Revised 11 June 2007 ,Accepted 12 June 2007.

References 

  1. Egan RL. Breast imaging: diagnosis and morphology of breast diseases. Philadelphia: Saunders; 1988;
  2. Robbins SL, Angell M, Kumar V. Basic pathology. Philadelphia: Saunders; 1981;
  3. Bocchi L, Coppini G, De Dominicis R, Valli G. Tissue characterization from X-ray images. Med Eng Phys. 1997;19(4):336–342
  4. Bruce LM, Adhami RR. Classifying mammographic mass shapes using the wavelet transform modulus-maxima method. IEEE Trans Med Imag. 1999;18(12):1170–1177
  5. Newstead GM, Baute PB, Toth HK. Invasive lobular and ductal carcinoma: mammographic findings and stage at diagnosis. Radiology. 1992;184:623–627
  6. Meyer JE, Amin E, Lindfors KK, Lipman JC, Stomper PC, Genest D. Medulary carcinoma of the breast: mammographic and US appearance. Radiology. 1989;170:79–82
  7. Sickles EA. Breast masses: mammographic evaluation. Radiology. 1989;173:297–303
  8. Encarnacao JL, Peitgen H-O, Sakas G, Englert G. Fractal geometry and computer graphics. Berlin: Springer-Verlag; 1992;
  9. Caldwell CB, Stapleton SJ, Holdsworth DW, Jong RA, Weiser WJ, Cooke G, et al. Characterization of mammographic parenchymal pattern by fractal dimension. Phys Med Biol. 1990;35:235–247
  10. Homer MJ. Imaging features and management of characteristically benign and probably benign lesions. Radiol Clin N Am. 1987;25(5):939–951
  11. Homer MJ. Breast imaging: pitfalls, controversies and some practical thoughts. Radiol Clin N Am. 1985;23(3):459–472
  12. Mavroforakis M, Georgiou H, Dimitropoulos N, Cavouras D, Theodoridis S. Significance analysis of qualitative mammographic features, using linear classifiers, neural networks and support vector machines. Eur J Radiol. 2005;54:80–89
  13. Georgiou H, Cavouras D, Dimitropoulos N, Theodoridis S. Mammographic mass shape characterization using neural networks. In: Proceedings of the 2nd European symposium on biomedical engineering and medical physics, Patras, Greece; 2000 BME 13.
  14. Kilday J, Palmieri F, Fox MD. Classifying mammographic lesions using computerized image analysis. IEEE Trans Med Imag. 1993;12(4):664–669
  15. Kilday J, Palmieri F, Fox MD. Linear discriminant based mammographic tumor classification using shape descriptors. In: Proceedings of the 12th annual international conference of IEEE engineering in medicine and biology 1, IEEE, New Jersey; 1990. p. 434.
  16. Petersen EM, Ridder D, Handels H. Image processing with neural networks—a review. Pat Rec. 2002;35:2279–2301
  17. Massopust PR. Fractal functions, fractal surfaces and wavelets. San Diego: Academic Press; 1994;
  18. Burrus CS, Gopinath RA, Guo H. Introduction to wavelets and wavelet transforms—a primer. New Jersey: Prentice Hall; 1998;
  19. Daubechies I. Ten lectures on wavelets, 2nd ed. CBMS-NSF regional conference series in applied mathematics 61. Philadelphia: SIAM; 1992.
  20. Vetterli M, Herley C. Wavelets and filter banks: theory and design. IEEE Trans Sig Proc. 1992;40(9):2207–2232
  21. Zhang D, Lu G. Review of shape representation and description techniques. Pat Rec. 2004;37:1–19
  22. Gonzalez RC, Woods RE. Digital image processing. 3rd ed.. New Jersey: Prentice-Hall; 2006;
  23. Zhang DS, Lu G. A comparative study of Fourier descriptors for shape representation and retrieval. In: Proceedings of the 5th Asian conference on computer vision (ACCV02), Melbourne, Australia, January 22–25; 2002. p. 646–51.
  24. Theodoridis S, Koutroumbas K. Pattern recognition. 3rd ed.. San Diego, USA: Academic Press; 2006;
  25. Traina C, Jr, Traina AJM, Wu L, Faloutsos C. Fast feature selection using fractal dimension. In: XV Brazilian database symposium, Joao Pessoa, PA Brazil, vol. 1; 2000. p. 158–71.
  26. Cooley WW, Lohnes PR. Multivariate data analysis. New York: John Willey & Sons; 1971;
  27. Leeden R, Vrijburg K, Leeuw J. A review of two different approaches for the analysis of growth data using longitudinal mixed linear models: comparing hierarchical linear regression (ML3, HLM) and repeated measures designs with structured covariance matrices (BMDP5V). The statistical software newsletter, computational statistics and data analysis (SSNinCSDA), 21 (5). Amsterdam: Elsevier Science; 1996. p. 583–605.
  28. Mavroforakis M, Georgiou H, Dimitropoulos N, Cavouras D, Theodoridis S. Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers. Artif Intell Med. 2006;37(2):145–162
  29. D’Orsi CJ, Getty DJ, Swets JA, Pickett RM, Seltzer SE, McNeil BJ. Reading and decision aids for improved accuracy and standardization of mammographic diagnosis. Radiology. 1992;184:619–622
  30. Wu Y, Giger ML, Doi K, Vyborny CJ, Schmidt RA, Metz CE. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology. 1993;187:81–87
  31. Ackerman LV, Mucciardi AN, Gose EE, Alcorn FS. Classification of benign and malignant breast tumors on the basis of 36 radiographic properties. Cancer. 1973;31:342–352
  32. Suckling J, Parker J, Dance DR, Astley S, Hutt I, Doggis CRM, et al. The mammographic image analysis society digital mammogram database. Exerpta Med Int Congr Ser 1994;1069:375–8.
  33. Li H, Wang Y, Liu KJR, Lo S-CB, Freedman MT. Computerized radiographic mass detection. Part I. Lesion site selection by morphological enhancement and contextual segmentation. IEEE Trans Med Imag. 2001;20(4):289–301
  34. Sahiner B, Petrick N, Chan HP, Hadjiiski LM, Paramagul C, Helvie MA, et al. Computer-aided characterization of mammographic masses: accuracy of mass segmentation and its effects on characterization. IEEE Trans Med Imag. 2001;20(12):1275–1284
  35. Hatanaka Y, Hara T, Fujita H, Kasai S, Endo T, Iwase T. Development of an automated method for detecting mammographic masses with a partial loss of region. IEEE Trans Med Imag. 2001;20(12):1209–1214
  36. Cheng HD, Cui M. Mass lesion detection with fuzzy neural network. Pat Rec. 2004;37:1189–1900
  37. MathWorks Inc. Matlab 7.0 documentation: signal processing toolbox. Massachusetts: MathWorks; 2004.
  38. Bruce LM, Adhami RR, Bruce JW. Appropriate scales when using wavelets for feature extraction. In: Dagli, et al., editors. Proceedings of the artificial neural networks in engineering ’96. St. Louis, MO; 1996. p. 507–12.
  39. Mallat SG. Zero-crossings of a wavelet transform. IEEE Trans Inf Theo. 1991;37(4):1019–1033
  40. Cheng HD, Shi XJ, Min R, Hu LM, Cai XP, Du HN. Approaches for automated detection and classification of masses in mammograms. Pat Rec. 2006;39:646–668
  41. Petrick N, Chan HP, Sahiner B, Helvic MA. Combined adaptive enhancement and region-growing segmentation of breast masses on digitized mammograms. Med Phys. 1999;26:1642–1654
  42. Sahiner B, Chan HP, Petrick N, Helvic MA, Hadjiiski LM. Improvement of mammographic mass characterization using spiculation measures and morphological features. Med Phys. 2001;28(7):1455–1465
  43. El-Faramawy NM, Rangayyan RM, Desautels JEL, Alim OA. Shape factors for analysis of breast tumors in mammograms. Canadian conference on electrical and computer engineering ’96, Calgary, Canada. New Jersey: Elsevier Science; 1996. p. 355–8.
  44. van Otterloo PJ. A contour-oriented approach to shape analysis. New Jersey: Prentice-Hall; 1991;
  45. Tieng QM, Boles WW. Recognition of 2D object contours using wavelet transform zero-crossing representation. IEEE Trans PAMI. 1997;19(8):910–916
  46. Zhang DS, Lu G. A comparison of shape retrieval using Fourier descriptors and short-time Fourier descriptors. In: Shum H-Y, Liao M, Chang S-F, editors. Proceedings of the 2nd IEEE Pacific-Rim conference on multimedia (PCM01), Beijing, China, October 24–26. Lecture notes in computer science, vol. 2195. Springer; 2001. p. 855–60.
  47. (a)Chen CC, Daponte JS, Fox MD. Fractal feature analysis and classification in medical imaging. IEEE Trans Med Imag. 1989;8(2):133–142(b)Moore AW, Lee MS. Efficient algorithm for minimizing cross validation error. In: Proceedings of the 11th international conference on machine learning (ML-94), July 10–13, 1994, New Brunswick, New Jersey. San Francisco: Morgan Kaufmann; 1994.
  48. Abrahao B, Barbosa L. Characterizing datasets using fractal methods. Technical report. MG Brazil: Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte; 2003.
  49. Pierre S, Rivest JF. On the validity of fractal dimension measurements in image analysis. J Vis Com Imag Proc. 1996;7(3):217–229
  50. Devroye L, Gyorfi L, Lugosi G. A probabilistic theory of pattern recognition. New York: Springer-Verlag Inc.; 1996;
  51. Poggio T, Girosi F. Networks for approximation and learning. Proc IEEE. 1990;78(9):1481–1497
  52. Haykin S. Neural networks: a comprehensive foundation. 2nd ed.. New Jersey: Prentice Hall; 1999;
  53. Christianini N, Shawe-Taylor J. An introduction to support vector machines. UK: Cambridge University Press; 2000;
  54. Vapnik VN. Statistical learning theory. New York: John Wiley & Sons; 1998;
  55. Mavroforakis M, Theodoridis S. Reduced convex hulls: a geometric approach to support vector machines. IEEE Sig Proc Mag. 2007;24(3):120–123
  56. Stone M. Cross-validatory choice and assessment of statistical predictions. J R Stat Soc. 1974;21(1):111–147
  57. Lachenbruch PA, Mickey RM. Estimation of error rates in discriminant analysis. Technometrics. 1968;10:1–11
  58. Reed R. Pruning algorithms—a survey. IEEE Trans Neural Netw. 1998;4(5):740–747
  59. Jung CR, Scharcanski J. Adaptive image denoising and edge enhancement in scale-space using the wavelet transform. Pat Rec Lett. 2003;24:965–971
  60. Swets JA, Pickett RM. Evaluation of diagnostic systems: methods from signal detection theory. New York: Academic Press; 1982;
  61. Fawcett T. An introduction to ROC analysis. Pat Rec Lett. 2006;27:861–874
  62. Adams NM, Hand DJ. Comparing classifiers when the misallocation costs are uncertain. Pat Rec. 1999;32:1139–1147
  63. Fieldsend JE, Everson RM. Formulation and comparison of multi-class ROC surfaces. In: Proceedings of ROCML 2005, part of the 22nd international conference on machine learning (ICML 2005). p. 41–8.
  64. Srinivasan A. Note on the location of optimal classifiers in n-dimensional ROC space. Technical report PRG-TR-2-99. UK: Oxford University Computing Laboratory, Oxford University; 1999.
  65. Fawcett T. ROC graphs: notes and practical considerations for data mining researchers. Intelligent Enterprise Technologies Laboratory, HP Laboratories Palo Alto, HPL-2003-4.
  66. Agarwal S, Graepel T, Har-Peled S, Herbrich R, Roth D. Generalization bounds for the area under the ROC curve. J Mach Learn Res. 2005;6:393–425
  67. Cortes C, Mohri M. AUC optimization vs. error rate minimization. Technical Report. AT&T, New Jersey: AT&T Labs Research; 2003.

PII: S0933-3657(07)00072-3

doi: 10.1016/j.artmed.2007.06.004

Artificial Intelligence in Medicine
Volume 41, Issue 1 , Pages 39-55 , September 2007

Article Tools

* Image Usage & Resolution