Advertisement

PAC Bayesian Classifier with Finite Mixture Model for Oral Cancer Classification

  • S. K. PrabhakarEmail author
  • H. Rajaguru
Conference paper
Part of the IFMBE Proceedings book series (IFMBE, volume 71)

Abstract

One of the most commonly reported malignancy with serious health hazards in the world is oral cancer. In developing countries, the estimated cases of oral cancer are much higher when compared to the developed countries. The easiest way to detect and classify the oral cancer is by means of visual inspection and it is followed by the biopsy procedure. The inspection of oral cancer in a visual manner is not always reliable and it is based mainly on the analysis of clinical features and sometimes during its initial stage it may go unnoticed by highly trained specialists too. Therefore, there is an absolute necessity to screen and classify the oral cancer that should be quite accurate, reliable and with less human manual intervention. Here, in this paper, classification of oral cancer is given prior importance and so Probably Approximate Correct (PAC) Bayesian Classifier is used a first level classifier and then it is further optimized with the Finite Mixture Model (FMM) which is used as a second level classifier. Results show that when PAC Bayesian is used, an average classification accuracy of 96.23% is obtained for all the stages and when it is further optimized with FMM, it gives a classification accuracy of 100%.

Keywords

Oral cancer PAC Bayesian FMM 

Notes

Conflict of Interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Hanahan, D., Weinberg, R.A.: Hallmarks of cancer: the next generation. Cell 144, 646–674 (2011)CrossRefGoogle Scholar
  2. 2.
    Exarchos, K.P., Goletsis, Y., Fotiadis, D.I.: Multiparametric decision support system for the prediction of oral cancer reoccurrence. IEEE Trans. Inf. Technol. Biomed. 16, 1127–1134 (2012)CrossRefGoogle Scholar
  3. 3.
    Chuang, L.-Y., Wu, K.-C., Chang, H.-W., Yang, C.-H.: Support vector machine-based prediction for oral cancer using four snps in DNA repair genes, pp. 16–18 (2011)Google Scholar
  4. 4.
    Exarchos, K.P., Goletsis, Y., Fotiadis, D.I.: A multiscale and multiparametric approach for modeling the progression of oral cancer. BMC Med. Inform. Decis. Mak. 12, 136 (2012)CrossRefGoogle Scholar
  5. 5.
    Rosado, P., Lequerica-Fernández, P., Villallaín, L., Peña, I., Sanchez-Lasheras, F., de Vicente, J.C.: Survival model in oral squamous cell carcinoma based on clinicopathological parameters, molecular markers and support vector machines. Expert Syst. Appl. 40(4770), 4776 (2013)Google Scholar
  6. 6.
    Kamath, S.D., Mahato, K.K.: Optical pathology using oral tissue fluorescence spectra: classification by principal component analysis and k-means nearest neighbor analysis. J. Biomed. Opt. 12(1), 014028 (2007)CrossRefGoogle Scholar
  7. 7.
    Rajaguru, H., Prabhakar, S.K.: Oral cancer classification from hybrid ABC-PSO and Bayesian LDA. In: 2nd IEEE ICCES, IEEE Xplore, Coimbatore, India, 19–20 Oct (2017)Google Scholar
  8. 8.
    Galib, S., Islam, F., Abir, M., Lee, H.-K.: Computer aided detection of oral lesions on CT images. J. Instrum. 10(12) (2015)Google Scholar
  9. 9.
    Rajaguru, H., Prabhakar, S.K.: Performance comparison of oral cancer classification with Gaussian mixture measures and multi layer Perceptron. In: 16th International Conference on Biomedical Engineering (ICBME), pp. 123–129 (2016)Google Scholar
  10. 10.
    Alsmadi, M.K.: A hybrid Fuzzy C-Means and Neutrosophic for jaw lesions segmentation (2016)Google Scholar
  11. 11.
    Sharma, N., Om, H.: Predictive data mining for oral cancer (Chap. 15). In: Case Studies in Intelligent Computing—Achievements and Trends, pp. 303–328. CRC Press, Taylor and Francis Group (2014)Google Scholar
  12. 12.
    Arulchinnappan, S., Karunakaran, K., Rajendran, G.: Deduction of oral cancer using fuzzy linear regression. J. Comput. Sci. 7(8), 1141–1145 (2011)CrossRefGoogle Scholar
  13. 13.
    Rajaguru, H., Prabhakar, S.K.: An approach to classification of oral cancer using Softmax discriminant classifier. In: 2nd ICCES, IEEE Xplore, Coimbatore, India (2017)Google Scholar
  14. 14.
    Rosmai, M.D., Sameemii, A.K., Basir, A., Mazlipahiv, I.S., Norzaidi, M.D.: The use of artificial intelligence to identify people at risk of oral cancer: empirical evidence in Malaysian University. Int. J. Sci. Res. Educ. 3(1), 10–20 (2010)Google Scholar
  15. 15.
    Chang, S.W., Abdul-Kareem, S., Merican, A.F., Zainv, R.B.: Oral cancer prognosis based on clinicopathologic and genomic markers using a hybrid of feature selection and machine learning methods. BMC Bioinform. 14(1) (2013)Google Scholar
  16. 16.
    Shawe-Taylor, J., Williamson, R.C.: A PAC analysis of a Bayesian estimator. Technical report, Royal Holloway, University of London, NC2-TR-1997-013 (1997)Google Scholar
  17. 17.
    McLachlan, G., Peel, D.: Finite Mixture Models. Wiley, New York (2000)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of ECEBannari Amman Institute of TechnologySathyamangalamIndia

Personalised recommendations