access icon openaccess Classification of mammogram using two-dimensional discrete orthonormal S-transform for breast cancer detection

An efficient approach for classification of mammograms for detection of breast cancer is presented. The approach utilises the two-dimensional discrete orthonormal S-transform (DOST) to extract the coefficients from the digital mammograms. A feature selection algorithm based the on null-hypothesis test with statistical ‘two-sample t-test’ method has been suggested to select most significant coefficients from a large number of DOST coefficients. The selected coefficients are used as features in the classification of mammographic images as benign or malignant. This scheme utilises an AdaBoost algorithm with random forest as its base classifier. Two standard databases Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM) are used for the validation of the proposed scheme. Simulation results show an optimal classification performance with respect to accuracies of 98.3 and 98.8% and AUC (receiver operating characteristic) values of 0.9985 and 0.9992 for MIAS and DDSM, respectively. Comparative analysis shows that the proposed scheme outperforms its competent schemes.

Inspec keywords: mammography; image classification; medical image processing; learning (artificial intelligence); feature selection; statistical testing; feature extraction; cancer

Other keywords: image classification; Digital Database for Screening Mammography database; mammogram classification; statistical two-sample t-test method; null-hypothesis test; AdaBoost algorithm; two-dimensional discrete orthonormal S-transform; breast cancer detection; feature selection; Mammographic Image Analysis Society database

Subjects: Image recognition; Other topics in statistics; X-ray techniques: radiography and computed tomography (biomedical imaging/measurement); Knowledge engineering techniques; Patient diagnostic methods and instrumentation; Probability theory, stochastic processes, and statistics; X-rays and particle beams (medical uses); Biology and medical computing; Computer vision and image processing techniques; Other topics in statistics

References

    1. 1)
    2. 2)
    3. 3)
    4. 4)
    5. 5)
    6. 6)
      • 9. Liu, X., Tang, J.: ‘Classification in mammograms using selected geometry and texture features, and a new SVM-based feature selection method’, IEEE Syst. J., 2013, 8, (3), pp. 111.
    7. 7)
      • 8. Prathibha, B., Sadasivam, V.: ‘Hybrid transforms domain-based mammogram analysis using c-svm classifier’, Int. J. Med. Eng. Inf., 2012, 4, (2), pp. 146156.
    8. 8)
      • 19. Duda, R.O., Hart, P.E., Stork, D.G.: ‘Pattern classification’ (John Wiley & Sons, 2012).
    9. 9)
    10. 10)
      • 15. Groebner, D.F., Shannon, P.W., Fry, P.C., Smith, K.D.: ‘Business statistics: a decision-making approach’, 2005.
    11. 11)
    12. 12)
      • 21. Deserno, T.M., Soiron, M., de Oliveir, J.E.: ‘Texture patterns extracted from digitizes mammograms of different BI-RADS classes’, Image Retrieval in Medical Applications project, release: V1.0, 2012, http://www.ganymed.imib.rwth-aachen.de/irma/datasets_en.php.
    13. 13)
      • 20. Suckling, J., Parker, J., Dance, D., et al: ‘The mammographic image analysis society digital mammogram database’, 1994.
    14. 14)
    15. 15)
    16. 16)
    17. 17)
      • 12. Kumar, S.M., Balakrishnan, G.: ‘Multi resolution analysis for mass classification in digital mammogram using stochastic neighbor embedding’. Int. Conf. on Communications and Signal Processing (ICCSP), Melmaruvathur, India, April2013, pp. 101105.
    18. 18)
    19. 19)
    20. 20)
      • 17. Freund, Y., Schapire, R.E.: ‘Experiments with a new boosting algorithm’, ICML, 1996, 39, pp. 148156.
    21. 21)
http://iet.metastore.ingenta.com/content/journals/10.1049/htl.2014.0108
Loading

Related content

content/journals/10.1049/htl.2014.0108
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading