Artificial Intelligence in Medicine
Volume 38, Issue 3 , Pages 291-303 , November 2006

Cell-nuclear data reduction and prognostic model selection in bladder tumor recurrence

  • Dimitris K. Tasoulis

      Affiliations

    • Computational Intelligence Laboratory, Department of Mathematics, University of Patras, GR–26110 Patras, Greece
    • University of Patras Artificial Intelligence Research Center (UPAIRC), University of Patras, GR–26110 Patras, Greece
    • ,
  • Panagiota Spyridonos

      Affiliations

    • Computer Laboratory, School of Medicine, University of Patras, GR–26110 Patras, Greece
    • ,
  • Nicos G. Pavlidis

      Affiliations

    • Computational Intelligence Laboratory, Department of Mathematics, University of Patras, GR–26110 Patras, Greece
    • University of Patras Artificial Intelligence Research Center (UPAIRC), University of Patras, GR–26110 Patras, Greece
    • ,
  • Vassilis P. Plagianakos

      Affiliations

    • Computational Intelligence Laboratory, Department of Mathematics, University of Patras, GR–26110 Patras, Greece
    • University of Patras Artificial Intelligence Research Center (UPAIRC), University of Patras, GR–26110 Patras, Greece
    • ,
  • Panagiota Ravazoula

      Affiliations

    • Department of Pathology, University Hospital, University of Patras, GR–26110 Patras, Greece
    • ,
  • Georgios Nikiforidis

      Affiliations

    • Computer Laboratory, School of Medicine, University of Patras, GR–26110 Patras, Greece
    • ,
  • Michael N. Vrahatis

      Affiliations

    • Computational Intelligence Laboratory, Department of Mathematics, University of Patras, GR–26110 Patras, Greece
    • University of Patras Artificial Intelligence Research Center (UPAIRC), University of Patras, GR–26110 Patras, Greece
    • Corresponding Author InformationCorresponding author. Tel.: +30 2610 997374; fax: +30 2610 992965.

Received 5 September 2005 ,Revised 24 July 2006 ,Accepted 25 July 2006.

References 

  1. Kelloniemi E, Rintala E, Finne UHTFG, Stenman P. Tumor-associated trypsin inhibitor as a prognostic factor during follow-up of bladder cancer. Adult Urol. 2003;62(2):249–253
  2. Witjes J, Kiemeney L, Wheeless L, Grossman H. The value of histopathological prognostic factors in superficial bladder cancer: Do we need more. Urol Oncol. 2000;5(5):185–190
  3. Qureshi K, Naguib R, Hamdy F, Neal D, Mellon K. Neural network analysis of clinicopathological and molecular markers in bladder cancer. J Urol. 2000;163:630–633
  4. Badalament R, Kimmel M, Gay H, Cibas E, Whitmore W, Herr H, et al. The sensitivity of flow cytometry compared with conventional cytology in the detection of superficial bladder carcinoma. Cancer. 1987;59(12):2078–2085
  5. Devonec M, Darzynkiewicz Z, Claps MK, Collste L, Whitmore W, Melamed M. Flow cytometry of low stage bladder tumors: correlation with cytologic and cystoscopic diagnosis. Cancer. 1982;49(1):109–118
  6. Gschwendtner A, Hoffmann-Weltin Y, Mikuz G, Mairinger T. Quantitative assessment of bladder cancer by nuclear texture analysis using automated high resolution image cytometry. Mod Pathol. 1999;12(8):806–813
  7. Gschwendtner A, Mairinger T. Quantitative assessment of bladder carcinoma by acid labile dna assay. Cancer. 1999;86(1):105–113
  8. Oosterlink W, Lobel B, Jakse G, Malmstrom P-U, Stokle M, Sternberg C. Guidelines on bladder cancer. Eur Urol. 2002;41:105–112
  9. Lynn N, Shapiro J, Lynn M, Waymont B, Inglis J, Philp N. Use of artificial neural network to predict the early recurrence of superficial bladder cascer. Eur Urol Suppl. 2003;2(1):193
  10. Naguib R, Qureshi F, Hamdy K, Neal D. Neural network analysis of prognostic markers in bladder cancer. p. 1007–9 In: Proceedings of the 19th international conference-IEEE/EMBS. Chicago. 1997;
  11. Spyridonos P, Cavouras D, Ravazoula P, Nikiforidis G. A computer-based diagnostic and prognostic system for assessing urinary bladder tumour grade and predicting cancer recurrence. Med Inform Internet Med. 2002;27(2):111–122
  12. Miller J, Geisler J, Manahan K, Geisler H, Miller G, Zhou Z, et al. Nuclear size, shape and density in endometrial carcinoma: relationship to survival at over 5 years of follow-up. Does analyzing only cells occupying the peak and useful information?. Int J Gynecol Cancer. 2004;14(1):138–144
  13. Weyn B, Tjalma W, Wouver GVD, Daele AV, Scheunders P, Jacob W, et al. Validation of nuclear texture, density, morphometry and tissue syntactic structure analysis as prognosticators of cervical carcinoma. Anal Quant Cytol Histol. 2000;22(5):373–382
  14. van de Wouwer G, Weyn B, Scheunders P, Jacob W, van Marck E, van Dyck D. Wavelets as chromatin texture descriptors for the automated identification of neoplastic nuclei. J Microsc. 2000;197(1):25–35
  15. van Velthoven R, Petein P, Oosterlinck W, Wilde T, Mattelaer J, Hardeman M, et al. Identification by quantitative chromatin pattern analysis of patients at risk for recurrence of superficial transitional bladder carcinoma. J Urol. 2000;164:2134–2137
  16. Mobley B, Schechter E, Moore W, McKee P, Eichner J. Neural network predictions of significant coronary artery stenosis in men. Artif Intell Med. 2005;34(2):151–161
  17. Papik K, Molnar B, Schaefer R, Dombovari Z, Tulassay Z, Feher J. Application of neural networks in medicine—a review. Med Sci Monitor. 1998;4(3):538–546
  18. Street W. A neural network model for prognostic prediction. In:  Shavlik J editors. Machine learning: proceedings of the 15th international conference. San Francisco, CA: Morgan Kaufmann; 1998;p. 540–46
  19. Boon M, Kok L, Nygaard-Nielsen M, Holm K, Holund B. Neural network processing of cervical smears can lead to a decrease in diagnostic variability and an increase in screening efficacy: a study of 63 false-negative smears. Mod Pathol. 1994;7(9):957–961
  20. Kolles H, Von-Wangenheim A, Vince GH, Niedermayer I, Feiden W. Automated grading of astrocytomas based on histomorphometric analysis of ki-67 and feulgen stained paraffin sections. classsification results of neuronal and discriminant analysis. Anal Cell Pathol. 1995;8(2):101–116
  21. Downs J, Harrison R, Cross S. Evaluating a neural network decision-support tool for the diagnosis of breast cancer. In:  Barahona P,  Stefanelli M,  Wyatt J editor. Lecture notes in artificial intelligence, vol. 943. Springer-Verlag; 1995;
  22. Sharkey A, Sharkey N, Cross S. Adapting an ensemble approach for the diagnosis of breast cancer. In:  Niklasson L,  Bodn M,  Ziemke T editor. Eighth international conference on artificial neural networks. Springer-Verlag; 1998;
  23. Wolberg W, Street W, Mangasarian O. Image analysis and machine learning applied to breast cancer diagnosis and prognosis. Anal Quant Cytol Histol. 1995;17(2):77–87
  24. Downs J, Harrison R, Kennedy R, Cross S. Application of the fuzzy artmap neural network model to medical pattern classification tasks. Artif Intell Med. 1996;8(4):403–428
  25. Bezdek JC. Pattern recognition with fuzzy objective function algorithms. Kluwer Academic Publishers; 1981;
  26. Tasoulis DK, Vrahatis MN. Unsupervised distributed clustering. In: The IASTED international conference on parallel and distributed computing and networks. Innsbruck, Austria. 2004;
  27. Vrahatis MN, Boutsinas B, Alevizos P, Pavlides G. The new k-windows algorithm for improving the k-means clustering algorithm. J Complexity. 2002;18:375–391
  28. Spyridonos P, Ravazoula P, Cavouras D, Berberidis K, Nikiforidis G. Computer-based grading of heamatoxylin-eosin stained tissue sections of urinary bladder carcinomas. Med Inform Internet Med. 2001;26(3):179–190
  29. Harralick R, Shanmugam K. Textural features for image classification. IEEE Trans Syst, Man Cybernet. 1973;3(6):610–621
  30. der Poel HV, Schaafsma HE, Vooijs PG, Debruyne FM, Schalken JA. Review article. Quantitative light microscopy in urological oncology. J Urol. 1992;148:1–13
  31. van Velthoven R, Petein M, Zlotta A, Oosterlinck W, Meijden A, Zandona C, et al. Computer-assisted chromatin texture characterization of feulgen-stained nuclei in a series of 331 transitional bladder cell carcinomas. J Pathol. 1994;173:235–242
  32. Walker RF, Jackway PT, Lovell B. Cervical cell classification via co-occurrence and markov random field features. In: Proceedings of digital image computing: techniques and applications. 1995;
  33. Ohanian P, Dubes R. Performance evaluation for four classes of textural features. Pattern Recogn. 1992;25(8):819–833
  34. Choi H-K, Vasko J, Bengtsson E, Jarkrans T, Malmstrom U, Wester K, et al. Grading of transitional cell bladder carcinoma by texture analysis of histological sections. Anal Cell Pathol. 1994;6:327–343
  35. Walker R, Jackway P, Longstaff I. Improving co-occurrence matrix feature discrimination. In: Maeder A, Lovell B, editors. Digital image computing: techniques and applications. Brisbane, Australia; 1995, p. 643–8.
  36. Chen P, Pavlidis T. Segmentation by texture using a co-occurrence matrix and a split-and-merge algorithm. Comp Graphics Image Process. 1979;10:172–182
  37. Riedmiller M, Braun H. A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: Proceedings of the IEEE international conference on neural networks. San Francisco, CA. 1993;
  38. Igel C, Hüsken M. Improving the Rprop learning algorithm. In:  Bothe H,  Rojas R editor. Proceedings of the second international ICSC symposium on neural computation (NC 2000). ICSC Academic Press; 2000;
  39. Moller MF. A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks. 1993;6:525–533
  40. Magoulas GD, Vrahatis MN, Androulakis GS. Effective backpropagation training with variable stepsize. Neural Netw. 1997;10(1):69–82
  41. Magoulas GD, Plagianakos VP, Vrahatis MN. Adaptive stepsize algorithms for on-line training of neural networks. Nonlinear Anal TMA. 2001;47(5):3425–3430
  42. Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by error propagation. In:  Rumelhart DE,  McClelland JL editor. Parallel distributed processing: explorations in the microstructure of cognition: foundations. MIT Press; 1986;p. 318–62
  43. Hornik K. Multilayer feedforward networks are universal approximators. Neural Netw. 1989;2:359–366
  44. White H. Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings. Neural Netw. 1990;3:535–549
  45. Raudys SJ, Jain AK. Small sample size effects in statistical pattern recognition: Recommendations for practitioners. IEEE Trans Pattern Anal Mach Intell. 1991;252–264
  46. John GH, Kohavi R, Pfleger K, Irrelevant features and the subset selection problem. In: International conference on machine learning; 1994, p. 121–29, journal version in AIJ, available at http://citeseer.nj.nec.com/13663.html.
  47. Dasgupta S. Experiments with random projection. In: 16th conference on uncertainty in artificial intelligence (UAI 2000). 2000;
  48. Drineas P, Frieze A, Kannan R, Vempala S, Vinay V. Clustering in large graphs and matrices. In: SODA: ACM-SIAM symposium on discrete algorithms (a conference on theoretical and experimental analysis of discrete algorithms). 1999;
  49. Aggarwal CC, Procopiuc C, Wolf JL, Yu PS, Park JS. Fast algorithms for projected clustering. In: 1999 ACM SIGMOD international conference on management of data. New York. NY, USA: ACM Press; 1999;
  50. Agrawal R, Gehrke J, Gunopulos D, Raghavan P. Automatic subspace clustering of high dimensional data for data mining applications. In: SIGMOD ’98: proceedings of the 1998 ACM SIGMOD international conference on management of data. New York. NY, USA: ACM Press; 1998;p. 94–105
  51. Hartigan JA, Wong MA. A k-means clustering algorithm. Appl Stat. 1979;28:100–108
  52. Alevizos P, Boutsinas B, Tasoulis DK, Vrahatis MN. Improving the orthogonal range search k-windows clustering algorithm. In: Proceedings of the 14th IEEE International Conference on Tools with Artificial Intelligence. Washington, DC; 2002. p. 239-45.
  53. Alevizos P, Tasoulis DK, Vrahatis MN. Parallelizing the unsupervised k-windows clustering algorithm. In:  Wyrzykowski R editors. Lecture notes in computer science, vol. 3019. Springer-Verlag; 2004;
  54. Tasoulis DK, Alevizos P, Boutsinas B, Vrahatis MN. Parallel unsupervised k-windows: an efficient parallel clustering algorithm. In:  Malyshkin V editors. Lecture notes in computer science, LNCS 2763. Berlin, Heidelberg: Springer-Verlag; 2003;
  55. Tasoulis DK, Vrahatis MN. Novel approaches to unsupervised clustering through the k-windows algorithm. In:  Sirmakessis S editors. Knowledge mining: series studies in fuzziness and soft computing, vol. 185. Berlin, Heidelberg: Springer-Verlag; 2005;
  56. Tasoulis DK, Vrahatis MN. Unsupervised clustering on dynamic databases. Pattern Recogn Lett. 2005;26(13):2116–2127
  57. Hanley J, McNeil B. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology. 1982;143(1):29–36
  58. Friedman N, Kohavi R. Data mining tasks and methods: classification: Bayesian classification. Handbook of data mining and knowledge discovery. Oxford University Press, Inc.; 2002;p. 282–8
  59. Specht DF. Probabilistic neural networks. Neural Netw. 1990;3(1):109–118
  60. Tasoulis DK, Spyridonos P, Pavlidis NG, Cavouras D, Ravazoula P, Nikiforidis G, et al. A neural network approach to the comparative evaluation of physician’s subjective assessment versus quantitative nuclear features in grading urine bladder tumors. In:  Howlett VRJ,  Jain LC editor. Lecture notes in computer science, (LNAI), vol. 2774. Berlin, Heidelberg: Springer-Verlag; 2003;

PII: S0933-3657(06)00110-2

doi: 10.1016/j.artmed.2006.07.008

Artificial Intelligence in Medicine
Volume 38, Issue 3 , Pages 291-303 , November 2006

Article Tools

* Image Usage & Resolution