Abstract
Purpose
Early and correct diagnosis of a disease is vital for the success of treatment. Medical diagnostic decision support system can be used to improve the accuracy of the traditional diagnosis. As such, various pattern recognition methods are studied and applied to develop medical diagnostic decision support system. In this study, the effects of dimensionality reduction techniques with probabilistic neural network (PNN) on breast cancer classification are examined.
Methods
A hybrid method is proposed using the independent component analysis (ICA) and the discrete wavelet transform (DWT) to reduce feature vectors of Wisconsin diagnostic breast cancer (WDBC) data set. Two independent components (ICs), and one approximation coefficient of the DWT are used as a reduced feature vector to classify breast cancer using PNN. Performance measures such as accuracy, sensitivity, specificity, Youden’s index and the receiver operating characteristics (ROC) curve are computed to indicate the advantages of the hybrid feature reduction.
Results
The proposed feature reduction approach using ICA and DWT improves the diagnostic capability of the PNN classifier. The hybrid feature reduction has a higher diagnostic capability than the original thirty features using PNN as a classifier. Accuracy and sensitivity are 96.31% and 98.88%, while the results of the classification using the original thirty features are 92.09% and 95.52%.
Conclusions
Feature reduction approach using ICA and DWT together increases the performance measures of breast cancer classification using PNN, while reducing computational complexity.
Similar content being viewed by others
References
Akay MF. Support vector machines combined with feature selection for breast cancer diagnosis. Expert Syst Appl. 2009; 36 (2):3240–7.
Subashini TS, Ramalingam V, Palanivel S. Breast mass classification based on cytological pattern using RBFNN and SVM. Expert Syst Appl. 2009; 36(3):5284–90.
Christoyianni I, Dermatas E, Kokkinakis G. Fast detection of masses in computer-aided mammography. IEEE Signal Proc Mag. 2000; 17(1):54–64.
Salim N. Medical diagnosis using neural network. Faculty of Information Technology University. 2004. http://www.generation5.org/content/2004/MedicalDiagnosis.asp, Accessed 05 June 20–3.
Ubeyli ED. Implementing automated diagnostic systems for breast cancer detection. Expert Syst Appl. 2007; 33(4):1054–62.
Brause RW. Medical analysis and diagnosis by neural networks. Conf Proc Int Symp Med Data Anal. 2001; 2199:1–13.
Kiyana T, Yildirim T. Breast cancer diagnosis using statistical neural networks. Conf Proc 12th TAINN. 2003; 1–6.
Kilic N, Ucan ON, Osman O. Colonic polyp detection in CT colonography with fuzzy rule based 3D template Matching. J Med Syst. 2009; 33(1):9–18.
Mert A, Kilic N, Akan A. Evaluation of bagging ensemble method with time-domain feature extraction for diagnosing of arrhythmia beats. Neural Comput Appl. 2014; 24(2):317–26.
Maglogiannis I, Zafiropoulos E, Anagnostopoulos I. An intelligent system for automated breast cancer diagnosisand prognosis using SVM based classifiers. Appl Intell. 2009; 30(1):24–36.
Gurcan MN, Chan HP, Sahiner B, Hadjiiski L, Petrick N, Helvie MA. Optimal neural network architecture selection: Improvement in computerized detection of microcalcifications. Acad Radiol. 2002; 9(4):420–9.
Gomez-Ruiz JA, Jerez-Aragones JM, Munoz-Perez J. A neural network based model for prognosis of early breast cancer. Appl Intell. 2004; 20(3):231–8.
Cho SB, Won HH. Cancer classification using ensemble of neural networks with multiple significant gene subsets. Appl Intell. 2007; 26(3):243–50.
Ibnkahla M. Applications of neural networks to digital communications- a survey. Signal Process. 2000; 80(7):1185–215.
Jia M, Zhao C, Wang F, Niu D. A new method for decision on the structure of RBF neural network. Conf Proc Comp Intell Secur. 2006; 147–50.
Huang R, Law L, Cheung Y. An experimental study: on reducing RBF input dimension by ICA and PCA. Conf Proc Mach Learn Cybern. 2002; 4:1941–5.
Theodoridis S, Koutroumbas K. Pattern Recognition. 4th edition. San Diego: Academic Press; 2008.
Hyvärinen A, Oja E. Independent component analysis: algorithms and applications. Neural Netw. 2000; 13(4–5):411–30.
Gumus E, Kilic N, Sertbas A, Ucan ON. Evaluation of face recognition techniques using PCA, wavelets and SVM. Expert Syst Appl. 2010; 37(9):6404–8.
Kim MS, Cho YC, Seo ST, Son CS, Kim YN. A new method of ECG feature detection based on combined wavelet transform for u-health service. Biomed Eng Lett. 2011; 1(2):108–15.
Bache K, Lichman M. UCI Machine Learning Repository. http://archive.ics.uci.edu/ml, Accessed 05 January 2013.
Krishnan MMR, Banerjee S, Chakraborty C, Chakraborty C, Ray AK. Statistical analysis of mammographic features and its classification using support vector machine. Expert Syst Appl. 2010; 37(1): 470–8.
Kwon O, Lee T. Phoneme recognition using ICA-based feature extraction and transformation. Signal Process. 2004; 84(6):1005–19.
http://research.ics.tkk.fi/ica/fastica/, Accessed 05 January 2013.
Hyvärinen A. The fixed-point algorithm and maximum likelihood estimation for independent component analysis. Neural Process Lett. 1999; 10:1–5.
Ocak H. Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy. Expert Syst Appl. 2009; 36(2):2027–36.
Mallat SG. A theory for multiresolution signal decomposition: The wavelet representation. IEEE T Pattern Anal. 1989; 11(7):674–93.
Specht DF. Probabilistic neural networks. Neural Networks. 1990; 3(1):109–18.
Youden WJ. Index for rating diagnostic tests. Cancer. 1950; 3:32–5.
Amaral JLM, Lopes AJ, Jansen JM, Faria ACD, Melo PL. Machine learning algorithms and forced oscillation measurements applied to the automatic identification of chronic obstructive pulmonary disease. Comput Meth Prog Bio. 2012; 105(3):183–93.
Zweik MH, Campell G. Receiver-operating characteristic (ROC) plots: A fundamental evaluation tool in clinical medicine. Clin Chem. 1993; 39(4):561–77.
Sweliam NH, Tharwat AA, Moniem NKA. Support vector machine for diagnosis cancer disease: A comparative study. Egyp Inf J. 2010; 11(2):81–92.
Bagui SC, Bagui S, Pal K, Pal NR. Breast cancer detection using rank nearest neighbor classification rules. Pattern Recogn. 2003; 36(1):25–34.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mert, A., Kılıç, N. & Akan, A. An improved hybrid feature reduction for increased breast cancer diagnostic performance. Biomed. Eng. Lett. 4, 285–291 (2014). https://doi.org/10.1007/s13534-014-0148-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13534-014-0148-9