Journal of Digital Imaging

, Volume 24, Issue 3, pp 411–423 | Cite as

An Automated Neural-Fuzzy Approach to Malignant Tumor Localization in 2D Ultrasonic Images of the Prostate

  • Samar Samir Mohamed
  • J. M. Li
  • M. M. A. Salama
  • G. H. Freeman
  • H. R. Tizhoosh
  • A. Fenster
  • K. Rizkalla
Article
First Online:
  • 88 Downloads

Abstract

In this paper, a new neural-fuzzy approach is proposed for automated region segmentation in transrectal ultrasound images of the prostate. The goal of region segmentation is to identify suspicious regions in the prostate in order to provide decision support for the diagnosis of prostate cancer. The new automated region segmentation system uses expert knowledge as well as both textural and spatial features in the image to accomplish the segmentation. The textural information is extracted by two recurrent random pulsed neural networks trained by two sets of data (a suspicious tissues’ data set and a normal tissues’ data set). Spatial information is captured by the atlas-based reference approach and is represented as fuzzy membership functions. The textural and spatial features are synthesized by a fuzzy inference system, which provides a binary classification of the region to be evaluated.

Key words

TRUS prostate cancer RNN fuzzy inference tissue segmentation textural feature spatial feature malignant tumor localization 
This is a preview of subscription content, log in to check access.

References

  1. 1.
    National Cancer Institute of Canada. Canadian cancer statistics 2008. Toronto, Canada, 2009Google Scholar
  2. 2.
    Heidenreich A, Bolla M, Joniau S, van der Kwast TH, Matveev V, Mason, Mottet N, Schmid H-P, Wiegel T, Zattoni F. Guidelines on Prostate Cancer. Eur Urol 53(1):68–80, 2008Google Scholar
  3. 3.
    Presti Jr, JC, Chang JJ, Bhargava V, Shinohara K: The optimal systematic prostate biopsy scheme should include 8 rather than 6 biopsies: results of a prospective clinical trial. J Urol 163(1):163–167, 2000PubMedCrossRefGoogle Scholar
  4. 4.
    Presti Jr, JC, O’Dowd GJ, Miller MC, Mattu R, Veltri RW: Extended peripheral zone biopsy schemes increase cancer detection rates and minimize variance in prostate specific antigen and age related cancer rates: results of a community multi-practice study. J Urol 169(1):125–129, 2003PubMedCrossRefGoogle Scholar
  5. 5.
    Ethan J. Halpern, Stephen E. Strup. Using gray-scale and color and power doppler sonography to detect prostatic cancer. Am J Roentgenol 174:623–627, 2000Google Scholar
  6. 6.
    Turgut AT, Olcucuoglu E, Kosar P, Geyik PO, Kosar U, Dogra V: Power doppler ultrasonography of the feeding arteries of the prostate gland: a novel approach to the diagnosis of prostate cancer. J Ultrasound Med 26(7):875–883, 2007PubMedGoogle Scholar
  7. 7.
    Halpern EJ, Frauscher F, Rosenberg M, Gomella LG: Directed biopsy during contrast-enhanced sonography of the prostate. Am J Roentgenol 178(4):915–919, 2002Google Scholar
  8. 8.
    Schwartz L: Imaging and prostate cancer. J Radiation Oncology 36(1-supplement):118, 1996CrossRefGoogle Scholar
  9. 9.
    Clements R: Has ultrasonography a role for screening for prostatic cancer? Eur Radiol 7:217–223, 1997PubMedCrossRefGoogle Scholar
  10. 10.
    Bushberg JT, Seibert JA, Leidholdt Jr, EM, Boone JM: The essential physics of medical imaging, 2nd edition. Lippincott, Williams & Wilkins, Philadelphia, 2002, pp 469–553Google Scholar
  11. 11.
    Chiu B, Freeman GH, Salama MMA, Fenster A: Prostate segmentation algorithm using dyadic wavelet transform and discrete dynamic contour. Phys Med Biol 49(21):4943–4960, 2004PubMedCrossRefGoogle Scholar
  12. 12.
    Scheipers U, Ermert H, Sommerfeld H-J, Garcia-Schurmann M, Senge T, Philippou S: Ultrasonic multifeature tissue characterization for prostate diagnostics. Ultrasound Med Biol 29(8):1137–1149, 2003PubMedCrossRefGoogle Scholar
  13. 13.
    Mohamed SS, Salama MMA, Kamel M, El-Sadaany EF, Rizkalla K, Chin J: Prostate cancer multi-feature analysis using TRUS images. Phys Med Biol 50(15):N175–N185, 2005PubMedCrossRefGoogle Scholar
  14. 14.
    Mohamed SS, Li J, Salama MMA, Freeman G: Prostate tissue texture feature extraction for suspicious regions identification on TRUS images. J Digit Imaging 22(5):503–518 (doi  10.1007/s10278-008-9124-1), 2009.Google Scholar
  15. 15.
    Mohamed SS, Salama MMA: Spectral clustering for TRUS images. in BioMedical Engineering OnLine, 2007, 6:10 (15 March 2007)Google Scholar
  16. 16.
    Chen ME, Johnston DA, Tang K, Babaian RJ, Troncoso P: Detailed mapping of prostate carcinoma foci. Cancer 89(8):1800–1809, 2000PubMedCrossRefGoogle Scholar
  17. 17.
    Loch T, Leuschner I, Genberg C, Weichert-Jacobsen K, Kuppers F, Retz M, Lehmann J, Yfantis E, Evans M, Tsarev V, Stockle M: Future trends in transrectal ultrasound. Artificial Neural Network Analysis (ANNA) in the detection and staging of prostate cancer. Der Urologe A 39(4):341–347, 2000CrossRefGoogle Scholar
  18. 18.
    McNitt-Gray MF, Huang HK, Sayre JW: Feature selection in the pattern classification problem of digital chest radiograph segmentation. IEEE Trans Med Imaging 14:537–547, 1995PubMedCrossRefGoogle Scholar
  19. 19.
    Hassanien Aboul Ella: Intelligence techniques for prostate ultrasound image analysis. International Journal of Hybrid Intelligent Systems 6(3):155–167, 2009Google Scholar
  20. 20.
    Mohamed SS, Salama MMA: Prostate cancer spectral multi-feature analysis using TRUS images. IEEE Trans Med Imag 27(4):548–556, 2008CrossRefGoogle Scholar
  21. 21.
    Gelenbe E, Feng YT, Ranga K, Krishnan R: Neural network methods for volumetric magnetic resonance imaging of the human brain. Proc IEEE 84:1488–1496, 1996CrossRefGoogle Scholar
  22. 22.
    Gelenbe E: Random neural networks with negative and positive signals and product form solution. Neural Comput 1(4):502–510, 1989CrossRefGoogle Scholar
  23. 23.
    Gelenbe E: Stability of the random neural network model. Neural Comput 2(2):239–247, 1990CrossRefGoogle Scholar
  24. 24.
    Gelenbe E: Learning in the recurrent random neural network. Neural Comput 5:154–164, 1993CrossRefGoogle Scholar
  25. 25.
    Gelenbe E, Mao ZH, Li YD: Function approximation by random neural networks with a bounded number of layers. J Differ Equ Dyn Syst 12(1–2):143–170, 2004Google Scholar
  26. 26.
    Gelenbe E, Hussain K: Learning in the multiple class random neural network. IEEE Trans Neural Netw 13(6):1257–1267, 2002PubMedCrossRefGoogle Scholar
  27. 27.
    Zadeh LA: Outline of a new approach to the analysis of complex systems and decision processes. IEEE Trans Syst Man Cybern 3:28–44, 1973CrossRefGoogle Scholar
  28. 28.
    Zadeh LA: Knowledge representation in fuzzy logic. IEEE Trans Knowl Data Eng 1:89–100, 1989CrossRefGoogle Scholar
  29. 29.
    Obuchowski NA, McClish DK: Sample size determination for diagnostic accuracy studies involving binomial ROC curve indices. Stastics in Medicine 16(13):1529–1542, 1997CrossRefGoogle Scholar
  30. 30.
    Hanley JA, McNeil BJ: The meaning and use of the area under the receiver operation characteristic (ROC) curve. Radiology 143:29–36, 1982PubMedGoogle Scholar
  31. 31.
    Choi BC: Slopes of a receiver operating characteristic curve and likelihood ratios for a diagnostic test. Am J Epidemiol 148(11):1127–1132, 1998PubMedGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2010

Authors and Affiliations

  • Samar Samir Mohamed
    • 1
  • J. M. Li
    • 1
  • M. M. A. Salama
    • 1
  • G. H. Freeman
    • 1
  • H. R. Tizhoosh
    • 2
  • A. Fenster
    • 3
  • K. Rizkalla
    • 4
  1. 1.Department of Electrical and Computer EngineeringUniversity of WaterlooWaterlooCanada
  2. 2.Department of Systems Design EngineeringUniversity of WaterlooWaterlooCanada
  3. 3.Department of Diagnostic Radiology and Nuclear MedicineUniversity of Western OntarioLondonCanada
  4. 4.Department of PathologyUniversity of Western OntarioLondonCanada

Personalised recommendations