Advertisement

Prediction and Estimation of Dominant Factors Contributing to Lesion Malignancy Using Neural Network

  • Kumud TiwariEmail author
  • Sachin Kumar
  • R. K. Tiwari
Conference paper
  • 30 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1087)

Abstract

Cancer is among one of the major causes of death worldwide. Any region when infected experiences uncontrollable growth of cells, resulting in unstoppable growth of protrusions or lesions. Lesions are categorized as benign or malignant. Imaging techniques have gained a potential rise over last two decades in diagnosis and detection of cancer cells. Automated classifiers could upgrade the diagnosis process substantially, in terms of both time consumption and accuracy by automatically distinguishing benign and malignant patterns. The paper presents a statistical conclusion clubbed with artificial neural network (ANN) tool for early detection of disease, problem addressed is of breast lesions; however, the same can be addressed to any category of lesions appearing in any region of body. The statistical analysis on sample data of 699 values was evaluated for the purpose of establishing the dependence on selected microscopic attributes having a higher percentage contribution on cell malignancy, further a technique for prediction of breast lesion into benign and malignant categories using ANN is performed, that achieved sensitivity, specificity and classification accuracy as 96.94%, 98.75% and 97.70% for complete nine microscopic attributes and 96.70, 96.72 and 96.68 for selected microscopic attributes, respectively, having a higher percentage contribution on cell malignancy. Reduction in features resulted in lesser number of epoch’s and hence reduction in processing time for identification of infection and thus early detection.

Keywords

Breast cancer ANN Lesion Dominant attributes Epoch 

References

  1. 1.
    R.L. Siegel, K.D. Miller, A. Jemal, Cancer statistics: A cancer journal for clinicians (2015)Google Scholar
  2. 2.
  3. 3.
    L. Hadjiiski, B. Sahiner, M.A. Helvie, et al., Breast masses: Computer-aided diagnosis with serial mammograms. Radiology. 240(2), 343–356 (2006)Google Scholar
  4. 4.
    F.A. Cardillo, A. Starita, D. Caramella, A. Cillotti, A neural tool for breast cancer detection and classification in MRI. in Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 3 (2011) pp. 2733–2736Google Scholar
  5. 5.
    T. Jayaraj, V. Sanjana, V.P. Darshini, A review on neural network and its implementation on Breast cancer detection. IEEE (2016)Google Scholar
  6. 6.
    P.S. Pawar, D.R. Patil, Breast Cancer detection using neural network model. IEEE (2013)Google Scholar
  7. 7.
    A.A. Tzacheva, K. Najarian, J.P. Brockway, Breast cancer detection in gadolinium-enhanced MRI images by static region descriptors and neural networks. J. Magn. Reson. Imaging 17(3), 337–342 (2003)CrossRefGoogle Scholar
  8. 8.
    V.D. Khairnar, et al., Primary healthcare using artificial intelligence. in International conference on innovative computing and communication (2018) pp. 243–251Google Scholar
  9. 9.
    L.N. Shulman, W. Willett, A. Sievers, F.M. Knaul, Breast cancer in developing countries: Opportunities for improved survival. J. Oncol. (2010)Google Scholar
  10. 10.
    N.M. Lutimath, et al., Regression analysis for liver disease using R: A case study. in International conference on innovative computing and communication (2018) pp. 421–429Google Scholar
  11. 11.
    A.E. Hassanien, N. El-Bendary, Breast cancer detection and classification using support vector machines and pulse coupled neural network. in Advances in Intelligent Systems and Computing, (Springer, Berlin, Germany, 2013), pp. 269–279Google Scholar
  12. 12.
    G. Ertas, D. Demirgunes, O. Erogul Conventional and multi-state cellular neural networks in segmenting breast region from MR images: Performance comparison. in Proceedings of the International Symposium on Innovations in Intelligent Systems and Applications (INISTA ’12) (2014) pp. 1–4Google Scholar
  13. 13.
    J. Dheeba, N.A. Singh, S.T. Selvi, Computer-aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach. J. Biomed. Inform. 49, 45–52 (2014)CrossRefGoogle Scholar
  14. 14.
    T. Balakumaran, I.L.A. Vennila, C.G. Shankar, Detection of micro-calcification in mammograms using wavelet transform and fuzzy shell clustering. Int. J. Comput. Sci. Info. Technol. 7(1), 121–125 (2010)Google Scholar
  15. 15.
    A.M. ElNawasany, A.F. Ali, M.E. Waheed, A novel hybrid perceptron neural network algorithm for classifying breast MRI tumors. in Proceedings of the International Conference on Advanced Machine Learning Technologies and Applications (Cairo, Egypt, 2014) pp. 357–366Google Scholar
  16. 16.
    M. Kowal, P. Filipczuk, A. Obuchowicz, J. Korbicz, R. Monczak, Computer-aided diagnosis of breast cancer based on fine needle biopsy microscopic images. Comput. Biol. Med. 43(10), 1563–1572 (2013)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Amity School of Engineering and TechnologyAmity UniversityLucknowIndia
  2. 2.Department of Physics and ElectronicsDr. RML Avadh UniversityFaizabadIndia

Personalised recommendations