Ovarian Tumor Characterization and Classification Using Ultrasound: A New Online Paradigm

  • U. Rajendra Acharya
  • Luca Saba
  • Filippo Molinari
  • Stefano Guerriero
  • Jasjit S. Suri


Among gynecological malignancies, ovarian cancer is the most frequent cause of death. Image mining algorithms have been predominantly used to give the physicians a more objective, fast, and accurate second opinion on the initial diagnosis made from medical images. The objective of this work is to develop an adjunct Computer-Aided Diagnostic (CAD) technique that uses 3D ultrasound images of the ovary to accurately characterize and classify benign and malignant ovarian tumors. In this algorithm, we first extract features based on the textural changes and higher-order spectra (HOS) information. The significant features are then selected and used to train and evaluate the decision tree (DT) classifier. The proposed technique was validated using 1,000 benign and 1,000 malignant images, obtained from ten patients with benign and ten with malignant disease, respectively. On evaluating the classifier with tenfold stratified cross validation, the DT classifier presented a high accuracy of 97 %, sensitivity of 94.3 %, and specificity of 99.7 %. This high accuracy was achieved because of the use of the novel combination of the four features which adequately quantify the subtle changes and the nonlinearities in the pixel intensity variations. The rules output by the DT classifier are comprehensible to the end user and, hence, allow the physicians to more confidently accept the results. The preliminary results show that the features are discriminative enough to yield good accuracy. Moreover, the proposed technique is completely automated and accurate and can be easily written as a software application for use in any computer.


Ovarian tumor Texture features Higher-order spectra Characterization Classification Computer-aided diagnosis 


  1. 1.
    NCI (National Cancer Institute) on ovarian cancer. Information website Accessed 4 Oct 2011.
  2. 2.
    Bast Jr RC, Badgwell D, Lu Z, et al. New tumor markers: CA125 and beyond. Int J Gynecol Cancer. 2005;15:274–81.PubMedCrossRefGoogle Scholar
  3. 3.
    Zaidi SI. Fifty years of progress in gynecologic ultrasound. Int J Gynaecol Obstet. 2007;99:195–7.PubMedCrossRefGoogle Scholar
  4. 4.
    Menon U, Talaat A, Rosenthal AN, et al. Performance of ultrasound as a second line test to serum CA125 in ovarian cancer screening. BJOG. 2000;107:165–9.PubMedCrossRefGoogle Scholar
  5. 5.
    Kim KA, Park CM, Lee JH, et al. Benign ovarian tumors with solid and cystic components that mimic malignancy. AJR Am J Roentgenol. 2004;182:1259–65.PubMedCrossRefGoogle Scholar
  6. 6.
    Lenic M, Zazula D, Cigale B. Segmentation of ovarian ultrasound images using single template cellular neural networks trained with support vector machines. In: Proceedings of 20th IEEE international symposium on Computer-Based Medical Systems, Maribor, 2007, 205–12.Google Scholar
  7. 7.
    Hiremath PS, Tegnoor JR. Recognition of follicles in ultrasound images of ovaries using geometric features. In: Proceedings of international conference on Biomedical and Pharmaceutical Engineering, Singapore, 2009, 1–8.Google Scholar
  8. 8.
    Deng Y, Wang Y, Chen P. Automated detection of polycystic ovary syndrome from ultrasound images. In: Proceedings of the 30th annual international IEEE Engineering in Medicine and Biology Society conference, Vancouver, 2008, p. 4772–5.Google Scholar
  9. 9.
    Sohail ASM, Rahman MM, Bhattacharya P, Krishnamurthy S, Mudur SP. Retrieval and classification of ultrasound images of ovarian cysts combining texture features and histogram moments. In: IEEE international symposium on Biomedical Imaging: From Nano to Macro, Rotterdam, 2010, p. 288–91.Google Scholar
  10. 10.
    Sohail ASM, Bhattacharya P, Mudur SP, Krishnamurthy S. Selection of optimal texture descriptors for retrieving ultrasound medical images. In: IEEE international symposium on Biomedical Imaging: From Nano to Macro, Chicago, 2011, p. 10–6.Google Scholar
  11. 11.
    Renz C, Rajapakse JC, Razvi K, Liang SKC. Ovarian cancer classification with missing data. In: Proceedings of 9th international conference on Neural Information Processing, Singapore, 2002, vol. 2, p. 809–13.Google Scholar
  12. 12.
    Assareh A, Moradi MH. Extracting efficient fuzzy if-then rules from mass spectra of blood samples to early diagnosis of ovarian cancer. In: IEEE symposium on Computational Intelligence and Bioinformatics and Computational Biology, Honolulu, 2007, p. 502–6.Google Scholar
  13. 13.
    Tan TZ, Quek C, Ng GS, Razvi K. Ovarian cancer diagnosis with complementary learning fuzzy neural network. Artif Intell Med. 2008;43:207–22.PubMedCrossRefGoogle Scholar
  14. 14.
    Meng H, Hong W, Song J, Wang L. Feature extraction and analysis of ovarian cancer proteomic mass spectra. In: 2nd international conference on Bioinformatics and Biomedical Engineering, Shanghai, 2008, p. 668–71.Google Scholar
  15. 15.
    Tang KL, Li TH, Xiong WW, Chen K. Ovarian cancer classification based on dimensionality reduction for SELDI-TOF data. BMC Bioinformatics. 2010;11:109.PubMedCentralPubMedCrossRefGoogle Scholar
  16. 16.
    Petricoin F. Use of proteomic patterns serum to identify ovarian cancer. Lancet. 2002;359:572–7.PubMedCrossRefGoogle Scholar
  17. 17.
    Tailor A, Jurkovic D, Bourne TH, Collins WP, Campbell S. Sonographic prediction of malignancy in adnexal masses using an artificial neural network. Br J Obstet Gynaecol. 1999;106:21–30.PubMedCrossRefGoogle Scholar
  18. 18.
    Brüning J, Becker R, Entezami M, Loy V, Vonk R, Weitzel H, et al. Knowledge-based system ADNEXPERT to assist the sonographic diagnosis of adnexal tumors. Methods Inf Med. 1997;36:201–6.PubMedGoogle Scholar
  19. 19.
    Biagiotti R, Desii C, Vanzi E, Gacci G. Predicting ovarian malignancy: application of artificial neural networks to transvaginal and color Doppler flow US. Radiology. 1999;210:399–403.PubMedCrossRefGoogle Scholar
  20. 20.
    Zimmer Y, Tepper R, Akselrod S. An automatic approach for morphological analysis and malignancy evaluation of ovarian masses using B-scans. Ultrasound Med Biol. 2003;29:1561–70.PubMedCrossRefGoogle Scholar
  21. 21.
    Lucidarme O, Akakpo JP, Granberg S, et al. A new computer-aided diagnostic tool for non-invasive characterisation of malignant ovarian masses: results of a multicentre validation study. Eur Radiol. 2010;20:1822–30.PubMedCrossRefGoogle Scholar
  22. 22.
    Bellman RE. Dynamic programming. Mineola: Courier Dover Publications; 2003.Google Scholar
  23. 23.
    Hata T, Yanagihara T, Hayashi K, Yamashiro C, et al. Three-dimensional ultrasonographic evaluation of ovarian tumours: a preliminary study. Hum Reprod. 1999;14:858–61.PubMedCrossRefGoogle Scholar
  24. 24.
    Laban M, Metawee H, Elyan A, Kamal M, Kamel M, Mansour G. Three-dimensional ultrasound and three-dimensional power Doppler in the assessment of ovarian tumors. Int J Gynaecol Obstet. 2007;99:201–5.PubMedCrossRefGoogle Scholar
  25. 25.
    Cohen LS, Escobar PF, Scharm C, Glimco B, Fishman DA. Three-dimensional power Doppler ultrasound improves the diagnostic accuracy for ovarian cancer prediction. Gynecol Oncol. 2001;82:40–8.PubMedCrossRefGoogle Scholar
  26. 26.
    Okugawa K, Hirakawa T, Fukushima K, Kamura T, Amada S, Nakano H. Relationship between age, histological type, and size of ovarian tumors. Int J Gynaecol Obstet. 2001;74:45–50.PubMedCrossRefGoogle Scholar
  27. 27.
    Webb JAW. Ultrasound in ovarian carcinoma. In: Reznek R, editor. Cancer of the ovary. Cambridge: Cambridge University Press; 2006. p. 94–111.CrossRefGoogle Scholar
  28. 28.
    Guerriero S, Alcazar JL, Pascual MA, Ajossa S, Gerada M, Bargellini R, Virgilio B, Melis GB. Intraobserver and interobserver agreement of grayscale typical ultrasonographic patterns for the diagnosis of ovarian cancer. Ultrasound Med Biol. 2008;34:1711–6.PubMedCrossRefGoogle Scholar
  29. 29.
    Testa AC, Gaurilcikas A, Licameli A, Mancari R, Di Legge A, Malaggese M, Mascilini F, Zannoni GF, Scambia G, Ferrandina G. Sonographic features of primary ovarian fibrosarcoma: a report of two cases. Ultrasound Obstet Gynecol. 2009;33:112–5.PubMedCrossRefGoogle Scholar
  30. 30.
    Park SB, Lee JW, Kim SK. Content-based image classification using a neural network. Pattern Recogn Letters. 2004;25:287–300.CrossRefGoogle Scholar
  31. 31.
    Gonzalez C, Woods RE. Digital image processing. Upper Saddle River: Prentice Hall; 2001.Google Scholar
  32. 32.
    Fortin C. Fractal dimension in the analysis of medical images. IEEE Eng Med Biol. 1992;11:65–71.CrossRefGoogle Scholar
  33. 33.
    Mandelbrot BB. The fractal geometry of nature. New York: WH Freeman Ed; 1982.Google Scholar
  34. 34.
    Biswas MK, Ghose T, Guha S, Biswas PK. Fractal dimension estimation for texture images: a parallel approach. Pattern Recogn Letters. 1998;19:309–13.CrossRefGoogle Scholar
  35. 35.
    Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern. 1973;SMC-3:610–21.CrossRefGoogle Scholar
  36. 36.
    Ramana KV, Ramamoorthy B. Statistical methods to compare the texture features of machined surfaces. Pattern Recogn. 1996;29:1447–59.CrossRefGoogle Scholar
  37. 37.
    Galloway MM. Texture classification using gray level run length. Comput Graph Image Process. 1975;4:172–9.CrossRefGoogle Scholar
  38. 38.
    Nikias C, Petropulu A. Higher-order spectral analysis. Englewood Cliffs: Prentice-Hall; 1997.Google Scholar
  39. 39.
    Chua KC, Chandran V, Acharya UR, Lim C. Application of higher order spectra to identify epileptic EEG. J Med Syst. 2011;35(6):1563–71. doi: 10.1007/s10916-010-9433-z.PubMedCrossRefGoogle Scholar
  40. 40.
    Acharya UR, Chua KC, Lim TC, Dorithy DL, Suri JS. Automatic identification of epileptic EEG signals using nonlinear parameters. J Med Mech Biol. 2009;9:539–53.CrossRefGoogle Scholar
  41. 41.
    Chua KC, Chandran V, Acharya UR, Lim CM. Analysis of epileptic EEG signals using higher order spectra. J Med Eng Technol. 2009;33:42–50.PubMedCrossRefGoogle Scholar
  42. 42.
    Ramm A, Katsevich A. The radon transform and local tomography. Boca Raton: CRC Press; 1996.Google Scholar
  43. 43.
    Box JF. Guinness, gosset, fisher, and small samples. Stat Sci. 1987;2:45–52.CrossRefGoogle Scholar
  44. 44.
    Larose DT. Decision trees. In: Discovering knowledge in data: an introduction to data mining. Hoboken: Wiley Interscience; 2004. p. 108–26.CrossRefGoogle Scholar
  45. 45.
    Acharya UR, Sree SV, Krishnan MM, Saba L, Molinari F, Guerriero S, Suri JS. Ovarian tumor characterization using 3D ultrasound. Technol Cancer Res Treat. 2012;11(6):543–52.PubMedGoogle Scholar
  46. 46.
    Philpotts LE. Can computer-aided detection be detrimental to mammographic interpretation? Radiology. 2009;253(1):17–22.PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • U. Rajendra Acharya
    • 1
    • 2
  • Luca Saba
    • 3
  • Filippo Molinari
    • 4
  • Stefano Guerriero
    • 5
  • Jasjit S. Suri
    • 6
    • 7
  1. 1.Department of Electronics and Computer EngineeringNgee Ann PolytechnicSingaporeSingapore
  2. 2.Department of Biomedical Engineering, Faculty of EngineeringUniversity of MalayaKuala LumpurMalaysia
  3. 3.Department of RadiologyAzienda Ospedaliero Universitaria di CagliariCagliariItaly
  4. 4.Biolab, Department of Electronics and TelecommunicationsPolitecnico di TorinoTorinoItaly
  5. 5.Department of Obstetrics and GynecologyUniversity of Cagliari, Ospedale San Giovanni di DioCagliariItaly
  6. 6.Department of Biomedical EngineeringCTO, Global Biomedical TechnologiesRosevilleUSA
  7. 7.Department of Biomedical EngineeringIdaho State University (Aff.)PocatelloUSA

Personalised recommendations