Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 3, pp 3991–4010 | Cite as

Predictive and probabilistic model for cancer detection using computer tomography images

Article
  • 94 Downloads

Abstract

This paper presents one predictive and two probabilistic models for detecting cancer in human liver using computed tomography image. Two probabilistic models are built using Logistic Regression (LR) and Linear Discriminant Analysis (LDA). Multilayer Perceptron (MLP) is used to make a predictive model. The proposed method consists of three basic steps. Initially, fuzzy c-means (FCM) clustering algorithm is used to segment the lesions from the human liver. Among all the segmented lesions, some of them are marked as abnormal (malignant) and others are marked as normal (benign) by the radiologist. It has been observed experimentally that the marked normal and abnormal lesions are distinguishable by their textures. Gray Level Co-occurrence Matrices (GLCMs) are one of the earliest methods for texture analysis. Thirteen Haralick features are extracted from the GLCMs of abnormal and normal lesions, which are further employed to build two probabilistic models using LR, LDA and a predictive model using MLP to determine the probability that the patient has cancer in his liver or not. A comparative study has been made based on the prediction accuracies of these three models. Moreover, LR and LDA are used to identify some of the features out of those thirteen features which play a statistically significant role in decision making by these probabilistic models. On the other hand, MLP doesn’t have the ability to select such significant features. It is proved that logistic regression (96.67%) gives better accuracy as compared to LDA (95%) and MLP (94.4%).

Keywords

LR LDA MLP GLCMs 

References

  1. 1.
    Agreti A Categorical data analysis, (2nd ed.). New York: Wiley, 2002Google Scholar
  2. 2.
    Al-Kadi OS, Watson D (2008) Texture Analysis of Aggressive and Nonaggressive Lung Tumor CE CT Images. IEEE Trans Biomed Eng 55(7):1822–1830CrossRefGoogle Scholar
  3. 3.
    Al-Tarawneh MS (2012) Lung cancer detection using image processing techniques. Leonardo Electron J Pract Technol 20:147–158ISSN 1583-1078Google Scholar
  4. 4.
    Bandhita P, Noparat T, Ordinal regression analysis in factors related to sensorial hearing loss of the employee in industrial factory in Lampang Thailand. Mathematic, Statistics and Their Application, Penang, 2006Google Scholar
  5. 5.
    Bezdek JC (ed) (1981) Pattern recognition with fuzzy objective function algorithms. Springer Publishers, New YorkMATHGoogle Scholar
  6. 6.
    Bezdek JC, Ehrlich R, Full W (1984) J Comput Geosci 10:2–3CrossRefGoogle Scholar
  7. 7.
    Bhattacharjee D, Seal A, Ganguly S, Nasipuri M and Basu DK, A comparative study of human thermal face recognition based on Haar wavelet transform (HWT) and local binary pattern (LBP), Computational Intelligence and Neuroscience, 2012Google Scholar
  8. 8.
    Bryan S Morse, lecture 2: Image processing review, neighbors, connected components, and distance, 1998-2004Google Scholar
  9. 9.
    Cannon RL, Dave JV and Bezdek JC J. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, no. 2, 1986Google Scholar
  10. 10.
    Dunn JC J. Cybernetics, vol. 3, no. 3, 1974Google Scholar
  11. 11.
    Foruzana AH, Zoroofia RA, Horib M, Satoc Y (2009) A knowledge-based technique for liver segmentation in CT data. Comput Med Imaging Graph 33:567–587CrossRefGoogle Scholar
  12. 12.
    Freund Y, Schapire RE (1997) A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. J Comput Syst Sci 55:119–139Google Scholar
  13. 13.
    Gonzalez RC and Woods RE (2002) Digital Image Processing, 3rd edition. Prentice Hall, Upper Saddle River, NJGoogle Scholar
  14. 14.
    Haralick R, Shanmugam K, Dinstein I (1973) Textural Features for Image Classification. IEEE Trans Syst Man Cybern 3(6):610–621CrossRefGoogle Scholar
  15. 15.
    Kuruvilla J, Gunavathi K (2014) Lung cancer classification using neural networks for CT images.Comput Methods Prog Biomed 113(1):202–209CrossRefGoogle Scholar
  16. 16.
    Lee Y, Hara T, Fujita H, Itoh S, Ishigaki T (2001) Automated Detection of Pulmonary Lesions in Helical CT Images Based on an Improved Template-Matching Technique. IEEE Trans Med Imaging 20(7):595–604CrossRefGoogle Scholar
  17. 17.
    Liang X, Lin L, Cao Q, Huang R, Wang Y (2016) Recognizing focal liver lesions in ceus with dynamically trained latent structured models. IEEE Trans Med Imaging 35(3):713–727CrossRefGoogle Scholar
  18. 18.
    Lin L., Yang W., Li C., Tang J., Cao X., Inference with collaborative model for interactive tumor segmentation in medical image sequences, IEEE Transactions on Cybernetics, 2015.Google Scholar
  19. 19.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  20. 20.
    Martinez-Escobar M, Leng Foo J, Winer E (2012) Colorization of CT images to improve tissue contrast for tumor segmentation. Comput Biol Med 42:1170–1178CrossRefGoogle Scholar
  21. 21.
    Ruspini EH J. Information Sciences, vol. 2, no. 3, 1970Google Scholar
  22. 22.
    Sharma D, Jindal G Identifying lung cancer using image processing techniques, International Conference on Computational Techniques and Artificial Intelligence, 2011Google Scholar
  23. 23.
    Vogel WV, Oyen WJG, Barentsz JO, Kaanders JHAM, Corstens FHM PET/CT: Panacea, Redundancy, or Something in Between? J Nucl Med 45(1):15S–24S January 1, 2004Google Scholar
  24. 24.
    Zhang X, Tian J, Deng K, Wu Y, Li X (2010) Automatic Liver Segmentation Using a Statistical Shape Model With Optimal Surface Detection. IEEE Trans Biomed Eng 57(10):2622–2626CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.PDPM IIITDM JabalpurJabalpurIndia
  2. 2.Jadavpur UniversityKolkataIndia

Personalised recommendations