Breast cancer diagnosis using wrapper-based feature selection and artificial neural network

• Autorzy: Naveed Nawazish , Madhloom Hayan T. , Husain Mohd Shahid

Identyfikatory

DOI

10.23743/acs-2021-18

• Języki publikacji: EN

Abstrakty

EN

Breast cancer is commonest type of cancers among women. Early diagnosis plays a significant role in reducing the fatality rate. The main objective of this study is to propose an efficient approach to classify breast cancer tumor into either benign or malignant based on digitized image of a fine needle aspirate (FNA) of a breast mass represented by the Wisconsin Breast Cancer Dataset. Two wrapper-based feature selection methods, namely, sequential forward selection(SFS) and sequential backward selection (SBS) are used to identify the most discriminant features which can contribute to improve the classification performance. The feed forward neural network (FFNN) is used as a classification algorithm. The learning algorithm hyper-parameters are optimized using the grid search process. After selecting the optimal classification model, the data is divided into training set and testing set and the performance was evaluated. The feature space is reduced from nine feature to seven and six features using SFS and SBS respectively. The highest classification accuracy recorded was 99.03% with FFNN using the seven SFS selected features. While accuracy recorded with the six SBS selected features was 98.54%. The obtained results indicate that the proposed approach is effective in terms of feature space reduction leading to better accuracy and efficient classification model.

Słowa kluczowe

EN

breast cancer diagnosis; feature selection; neural network; grid search; machine learning

PL

diagnostyka raka piersi; dobór cech; sieć neuronowa; przeszukiwanie sieci; uczenie maszynowe

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2021
• Tom: Vol. 17, no 3
• Strony: 19--30
• Opis fizyczny: Bibliogr. 33 poz., fig., tab.

Twórcy

autor

Naveed Nawazish

• University of Technology and Applied Sciences, CAS-Ibri, Dept. of IT, Sultanate of Oman

• https://orcid.org/0000-0002-9619-4799

autor

Madhloom Hayan T.

• University of Technology and Applied Sciences, CAS-Ibri, Dept. of IT, Sultanate of Oman

• https://orcid.org/0000-0002-6228-5721

autor

Husain Mohd Shahid

• University of Technology and Applied Sciences, CAS-Ibri, Dept. of IT, Sultanate of Oman

• https://orcid.org/0000-0003-4864-9485

Bibliografia

• [1] Addeh, A., Demirel, H., & Zarbakhsh, P. (2017). Early detection of breast cancer using optimized ANFIS and features selection. 2017 9th International Conference on Computational Intelligence and Communication Networks (CICN) (pp. 39–42). IEEE. http://doi.org/10.1109/CICN.2017.8319352
• [2] Agrawal, S., & Agrawal, J. (2015). Neural network techniques for cancer prediction: A survey. Procedia Computer Science, 60, 769–774. http://doi.org/10.1016/j.procs.2015.08.234
• [3] Ang, J. C., Mirzal, A., Haron, H., & Hamed, H. N. A. (2015). Supervised, unsupervised, and semi-supervised feature selection: a review on gene selection. IEEE/ACM transactions on computational biology and bioinformatics, 13(5), 971–989. http://doi.org/10.1109/TCBB.2015.2478454
• [4] Barna, S. D., & Khan, S. (2019). Performance Evaluation of Classification Learning Models for Wisconsin Breast Cancer Data Repository. 7th International Conference on Data Science and SDGs: Challenges, Opportunities and Realities (EC-50). Bangladesh.
• [5] Bonakdari, H., Moradi, F., Ebtehaj, I., Gharabaghi, B., Sattar, A. A., Azimi, A. H., & Radecki-Pawlik, A. (2020). A Non-Tuned Machine Learning Technique for Abutment Scour Depth in Clear Water Condition. Water, 12(1), 301. http://doi.org/10.3390/w12010301
• [6] Casaubon, J. T., Tomlinson-Hansen, S., & Regan, J.-P. (2020). Fine Needle Aspiration of Breast Masses. StatPearls. StatPearls Publishing.
• [7] Dhungel, N., Carneiro, G., & Bradley, A. P. (2015). Automated Mass Detection in Mammograms Using Cascaded Deep Learning and Random Forests. International Conference on Digital Image Computing: Techniques and Applications (DICTA) (pp. 1–8). IEEE. http://doi.org/10.1109/DICTA.2015.7371234
• [8] Douangnoulack, P., & Boonjing, V. (2018). Building Minimal Classification Rules for Breast Cancer Diagnosis. 2018 10th International Conference on Knowledge and Smart Technology (KST) (pp. 278–281). IEEE. http://doi.org/10.1109/KST.2018.8426198
• [9] Ed-Daoudy, A., & Maalmi, K. (2020). Breast cancer classification with reduced feature set using association rules and support vector machine. Network Modeling Analysis in Health Informatics and Bioinformatics, 9(1), 34. http://doi.org/10.1007/s13721-020-00237-8
• [10] Foithong, S., Srinil, P., & Pinngern, O. (2017). Min-Uncertainty & Max-Certainty Criteria of Neighborhood Rough Mutual Feature Selection. Walailak Journal of Science and Technology, 14(4).
• [11] Guliyev, N. J., & Ismailov, V. E. (2018). On the approximation by single hidden layer feedforward neural networks with fixed weights. Neural Networks, 98, 296-304. http://doi.org/10.1016/j.neunet.2017.12.007
• [12] Guyon, I., Gunn, S., Nikravesh, M., & Zadeh, L. A. (2008). Feature extraction: foundations and applications (Vol. 207). Springer. http://doi.org/10.1007/978-3-540-35488-8
• [13] Hsu, Y.-C., Tsai, Y.-H., Weng, H.-H., Hsu, L.-S., Tsai, Y.-H., Lin, Y.-C., Hung, M.-S., Fang, Y.-H., & Chen, C.-W. (2020). Artificial neural networks improve LDCT lung cancer screening: a comparative validation study. BMC Cancer, 20(1), 1023. https://doi.org/10.1186/s12885-020-07465-1
• [14] Islam, M. M., Haque, M. R., Iqbal, H., Hasan, M. M., Hasan, M., & Kabir, M. N. (2020). Breast Cancer Prediction: A Comparative Study Using Machine Learning Techniques. SN Computer Science, 1(5), 290. https://doi.org/10.1007/s42979-020-00305-w
• [15] Jain, D., & Singh, V. (2018). Feature selection and classification systems for chronic disease prediction: A review. Egyptian Informatics Journal, 19(3), 179–189. https://doi.org/10.1016/j.eij.2018.03.002
• [16] Khan, A., Shah, R., Imran, M., Khan, A., Bangash, J. I., & Shah, K. (2019). An alternative approach to neural network training based on hybrid bio meta-heuristic algorithm. Journal of Ambient Intelligence and Humanized Computing, 10(10), 3821-3830. https://doi.org/10.1007/s12652-019-01373-4
• [17] Kohavi, R., & John, G. H. (1997). Wrappers for feature subset selection. Artificial intelligence, 97(1–2), 273–324. https://doi.org/10.1016/S0004-3702(97)00043-X
• [18] Kumar, V. (2021). Evaluation of computationally intelligent techniques for breast cancer diagnosis. Neural Computing and Applications, 33(8), 3195–3208. https://doi.org/10.1007/s00521-020-05204-y Kumar, V., & Minz, S. (2014). Feature selection: a literature review. SmartCR, 4(3), 211-229.
• [19] Kumari, M., & Singh, V. (2018). Breast Cancer Prediction system. Procedia Computer Science, 132, 371–376. https://doi.org/10.1016/j.procs.2018.05.197
• [20] Liu, X., Li, B., Shen, D., Cao, J., & Mao, B. (2017). Analysis of Grain Storage Loss Based on Decision Tree Algorithm. Procedia Computer Science, 122, 130–137. https://doi.org/10.1016/j.procs.2017.11.351
• [21] Moodley, J., Walter, F., Scott, S., & Mwaka, A. (2018). Towards timely diagnosis of symptomatic breast and cervical cancer in South Africa. South African Medical Journal, 108(10), 803–804. https://doi.org/10.7196/SAMJ.2018.v108i10.13478
• [22] Mushtaq, Z., Yaqub, A., Hassan, A., & Su, S. F. (2019). Performance Analysis of Supervised Classifiers Using PCA Based Techniques on Breast Cancer. 2019 International Conference on Engineering and Emerging Technologies (ICEET) (pp. 1–6). IEEE. https://doi.org/10.1109/CEET1.2019.8711868
• [23] Patsadu, O., Tangchitwilaikun, P., & Lowsuwankul, S. (2021). Liver Cancer Patient Classification on a MultipleStage using Hybrid Classification Methods. Walailak Journal of Science and Technology, 18(10). https://doi.org/10.48048/wjst.2021.9169
• [24] Santos-Pereira, J., Gruenwald, L., & Bernardino, J. (2021). Top data mining tools for the healthcare industry. Journal of King Saud University – Computer and Information Sciences, in press. https://doi.org/https://doi.org/10.1016/j.jksuci.2021.06.002
• [25] Senturk, Z. K., & Kara, R. (2014). Breast Cancer Diagnosis Via Data Mining: Performance Analysis of Seven Different algorithms. Computer Science & Engineering: An International Journal (CSEIJ), 4(1), 35–46. https://doi.org/10.5121/cseij.2014.4104
• [26] Shenouda, E. A. M. A. (2006). A Quantitative Comparison of Different MLP Activation Functions in Classification. In: J. Wang, Z. Yi, J. M. Zurada, B. L. Lu & H. Yin (Eds.), Advances in Neural Networks. Lecture Notes in Computer Science (vol. 3971). Springer. https://doi.org/10.1007/11759966_125
• [27] Tang, J., Alelyani, S., & Liu, H. (2014). Feature selection for classification: A review. In Data classification: Algorithms and applications (chapter 2). Chapman and Hall/CRC. https://doi.org/10.1201/b17320
• [28] Vijayalakshmi, S., & Priyadarshini, J. (2017). Breast Cancer Classification using RBF and BPN Neural Networks. International Journal of Applied Engineering Research, 12(15), 4775–4781.
• [29] Wahhab, H. T. A. (2015). Classification of acute leukemia using image processing and machine learning techniques. University of Malaya.
• [30] WBCD. (1995). Retrieved January 20, 2021 from https://archive.ics.uci.edu/ml/datasets/breast+cancer+wisconsin+(original).
• [31] Wu, J., Zhuang, Q., & Tan, Y. (2020). Auxiliary Medical Decision System for Prostate Cancer Based on Ensemble Method. Computational and Mathematical Methods in Medicine, 2020, 6509596. https://doi.org/10.1155/2020/6509596
• [32] Yi, L., & Yi, W. (2017). Decision Tree Model in the Diagnosis of Breast Cancer. In 2017 International Conference on Computer Technology, Electronics and Communication (ICCTEC) (pp. 176–179). IEEE. https://doi.org/10.1109/ICCTEC.2017.00046
• [33] Zarei, M., Ansari, H., Keshavarz, P., & Zerafat, M. (2020). Prediction of pool boiling heat transfer coefficient for various nano-refrigerants utilizing artificial neural networks. Journal of Thermal Analysis and Calorimetry, 139(6), 3757–3768

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).