Bilal ÜSTÜNDAĞ, Suat TORAMAN, Mustafa GİRGİN, İbrahim TÜRKOĞLU

Classification of the likelihood of colon cancer with machine learning techniques using FTIR signals obtained from plasma

Colon cancer is one of the major causes of human mortality worldwide and the same can be said for Turkey.Various methods are used for the determination of cancer. One of these methods is Fourier transform infrared (FTIR)spectroscopy, which has the ability to reveal biochemical changes. The most common features used to distinguish patientswith cancer and healthy subjects are peak densities, peak height ratios, and peak area ratios. The greatest challenge ofstudies conducted to distinguish cancer patients from healthy subjects using FTIR signals is that the signals of cancerpatients and healthy subjects are similar. In the current study, a method in which the area and height ratios of the FTIRsignal, as well as various statistical features, are proposed in order to overcome this difficulty. Blood samples (plasma)were collected from 30 colon cancer patients and 40 healthy subjects, and FTIR measurements were performed. A totalof 16 features were obtained, including five height ratios, five area ratios, and six statistical features, from each FTIRsignal. The 16 features were classified with a multilayer perceptron neural network and support vector machines usingcross-validation and their performances were then compared. The current study demonstrated that different featuresobtained from plasma FTIR spectra can be used together in order to distinguish colon cancer patients from healthyindividuals.

PDF

___

[1] Bruening W, Sullivan N, Carter Paulson E, Zafar H, Mitchell M et al. Imaging Tests for the Staging of Colorectal Cancer. Rockville, MD, USA: Agency for Healthcare Research and Quality, 2014.
[2] Lech G, Słotwiński R, Słodkowski M, Krasnodeffbski IW. Colorectal cancer tumour markers and biomarkers: recent therapeutic advances. World Journal of Gastroenterology 2016; 22: 1745-1755.
[3] Ostrovsky E, Zelig U, Gusakova I, Ariad S, Mordechai S et al. Detection of cancer using advanced computerized analysis of infrared spectra of peripheral blood. IEEE Transactions on Biomedical Engineering 2012; 60: 343-353.
[4] Barlev E, Zelig U, Bar O, Segev C, Mordechai S et al. A novel method for screening colorectal cancer by infrared spectroscopy of peripheral blood mononuclear cells and plasma. Journal of Gastroenterology 2015; 51: 56-78.
[5] Baker MJ, Gazi E, Brown MD, Shanks JH, Gardner P et al. FTIR-based spectroscopic analysis in the identification of clinically aggressive prostate cancer. British Journal of Cancer 2008; 99: 1859-1866.
[6] Sindhuphak R, Issaravanich S, Udomprasertgul V, Srisookho P, Warakamin S et al. A new approach for the detection of cervical cancer in Thai women. Gynecologic Oncology 2003; 90: 10-14.
[7] Jusman Y, Sulaiman SN, Isa NAM, Yusoff IA, Adnan R et al. Capability of new features from FTIR spectral of cervical cells for cervical precancerous diagnostic system using MLP networks. In: Tencon 2009 IEEE Region 10 Annual International Conference; 23–26 January 2009; Singapore. New York, NY, USA: IEEE. pp. 1-6.
[8] Njoroge E, Alty SR, Gani MR, Alkatib M. Classification of cervical cancer cells using FTIR data. In: EMBS 2006 Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 30 August–3 September 2006; New York, NY, USA: IEEE. pp. 5338-5341.
[9] Wan C, Cao W, Cheng C. Research of recognition method of discrete wavelet feature extraction and PNN classification of rats FT-IR pancreatic cancer data. Journal of Analytical Methods in Chemistry 2014; 2014: 564801.
[10] Li QB, Sun XJ, Xu YZ, Yang LM, Zhang YF et al. Diagnosis of gastric inflammation and malignancy in endoscopic biopsies based on Fourier transform infrared spectroscopy. Clinical Chemistry 2005; 51: 346-350.
[11] Li QB, Sun XJ, Xu YZ, Yang LM, Zhang YF et al. Use of Fourier-transform infrared spectroscopy to rapidly diagnose gastric endoscopic biopsies. World Journal of Gastroenterology 2005; 11: 3842-3845.
[12] Fujioka N, Morimoto Y, Arai T, Kikuchi M. Discrimination between normal and malignant human gastric tissues by Fourier transform infrared spectroscopy. Cancer Detection and Prevention 2004; 28: 32-36.
[13] Maziak DE, Do MT, Shamji FM, Sundaresan SR, Perkins DG et al. Fourier-transform infrared spectroscopic study of characteristic molecular structure in cancer cells of esophagus: an exploratory study. Cancer Detection and Prevention 2007; 31: 244-253.
[14] Eckel R, Huo H, Guan HW, Hu X, Che X et al. Characteristic infrared spectroscopic patterns in the protein bands of human breast cancer tissue. Vibrational Spectroscopy 2001; 27: 165-173.
[15] Fabian H, Thi NAN, Eiden M, Lasch P, Schmitt J et al. Diagnosing benign and malignant lesions in breast tissue sections by using IR-microspectroscopy. Biochimica et Biophysica Acta 2006; 1758: 874-882.
[16] Andronie L, Pânzaru SC, Cozar O, Domşa I. FT-IR spectroscopy for human colon tissue diagnostic. Romanian Journal of Biophysics 2011; 21: 85-91.
[17] Cheng C, Xiong W, Tian Y. Classification of rat FTIR colon cancer data using wavelets and BPNN. Chinese Journal of Chemistry 2009; 27: 911-914.
[18] Dong L, Sun X, Chao Z, Zhang S, Zheng J et al. Evaluation of FTIR spectroscopy as diagnostic tool for colorectal cancer using spectral analysis. Spectrochimica Acta A 2014; 122: 288-294.
[19] Xie YB, Liu Q, He F, Guo CG, Wang CF et al. Diagnosis of colon cancer with Fourier transform infrared spectroscopy on the malignant colon tissue samples. Chinese Medical Journal 2011; 124: 2517-2521.
[20] Erukhimovitch V, Talyshinsky M, Souprun Y, Huleihel M. FTIR spectroscopy examination of leukemia patients plasma. Vibrational Spectroscopy 2006; 40: 40-46.
[21] Sheng D, Liu X, Li W, Wang Y, Chen X et al. Distinction of leukemia patients’ and healthy persons’ serum using FTIR spectroscopy. Spectrochimica Acta A 2013; 101: 228-232.
[22] Ahmed SSSJ, Santosh W, Kumar S, Thanka Christlet TH. Neural network algorithm for the early detection of Parkinson’s disease from blood plasma by FTIR micro-spectroscopy. Vibrational Spectroscopy 2010; 53: 181-188.
[23] Sheng D, Wu Y, Wang X, Huang D, Chen X et al. Comparison of serum from gastric cancer patients and from healthy persons using FTIR spectroscopy. Spectrochimica Acta A 2013; 116: 365-369.
[24] Wang X, Shen X, Sheng D, Chen X, Liu X. FTIR spectroscopic comparison of serum from lung cancer patients and healthy persons. Spectrochimica Acta A 2014; 122: 193-197.
[25] Toraman S, Türkoğlu I. A new automatic recognition method for determine colon cancer from FTIR sign patterns. In: ICNASE 2016 International Conference on Natural Science and Engineering; 19–20 March 2016; Kilis, Turkey. pp. 2354-2361 (in Turkish with an abstract in English).
[26] Sun X, Xu Y, Wu J, Zhang Y, Sun K. Detection of lung cancer tissue by attenuated total reflection-Fourier transform infrared spectroscopy - a pilot study of 60 samples. Journal of Surgical Research 2013; 179: 33-38.
[27] Hands JR, Dorling KM, Abel P, Ashton KM, Brodbelt A et al. Attenuated total reflection Fourier transform infrared (ATR-FTIR) spectral discrimination of brain tumour severity from serum samples. Journal of Biophotonics 2014; 7: 189-199.
[28] Toraman S. Feature extraction using infrared spectroscopy from blood samples related to colon cancer. PhD, Fırat University, Elazığ, Turkey, 2016 (in Turkish with an abstract in English).
[29] Poston WL, Marchette DJ. Recursive dimensionality reduction using Fisher’s linear discriminant. Pattern Recognition 1998; 31: 881-888.
[30] Toraman S, Türkoğlu I. Automatic determination of desired cell fields on histopathologic images. In: IATS 2009 5th International Advanced Technologies Symposium; 13–15 May 2009; Karabük, Turkey. pp. 83-85 (in Turkish with an abstract in English).
[31] Phinyomark A, Limsakul C, Phukpattaranont P. A novel feature extraction for robust EMG pattern recognition. Journal of Computing 2009; 1: 71-80.
[32] Phinyomark A, Hirunviriya S, Limsakul C, Phukpattaranont P. Evaluation of EMG feature extraction for hand movement recognition based on Euclidean distance and standard deviation. In: ECTI-CON 2010 Electrical Engineering/Electronics Computer Telecommunications and Information Technology; 19–21 May 2010; Chiang Mai, Thailand. pp. 856-860.
[33] Phinyomark A, Nuidod A, Phukpattaranont P, Limsakul C. Feature extraction and reduction of wavelet transform coefficients for EMG pattern classification. Elektronika ir Elektrotechnika 2012; 122: 27-32.
[34] Vigneshwari C, Vimala V, Vignesh SV, Sumithra G. Analysis of finger movements using EEG signal. International Journal of Emerging Technology and Advanced Engineering 2013; 3: 583-588.
[35] Kharat PA, Dudul SV. Daubechies wavelet neural network classifier for the diagnosis of epilepsy. WSEAS Transactions on Biology and Biomedicine 2012; 9: 103-113.
[36] Hu X, Miller C, Vespa P, Bergsneider M. Adaptive computation of approximate entropy and its application in integrative analysis of irregularity of heart rate variability and intracranial pressure signals. Medical Engineering and Physics 2008; 30: 631-639.
[37] Martinez WL, Martinez AR. Computational Statistics Handbook with MATLAB. Boca Raton, FL, USA: CRC Press, 2002.
[38] Toraman S, Türkoğlu I. Efficient feature selection using sequential backward selection algorithm in the classification of histopathological images. In: ISERD 2015 16th International Society for Engineering Research and Development International Conference; 10 November 2015; Prague, Czech Republic. pp. 10-13.
[39] Yano K, Ohoshima S, Gotou Y, Kumaido K, Moriguchi T et al. Direct measurement of human lung cancerous and noncancerous tissues by Fourier transform infrared microscopy: can an infrared microscope be used as a clinical tool? Analytical Biochemistry 2000; 287: 218-225.
[40] Movasaghi Z, Rehman S, Rehman IU. Fourier transform infrared (FTIR) spectroscopy of biological tissues. Applied Spectroscopy Reviews 2008; 43: 134-179.
[41] Khazaee A, Ebrahimzadeh A. Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features. Biomedical Signal Processing and Control 2010; 5: 252-263.
[42] Arjmandi MK, Pooyan M. An optimum algorithm in pathological voice quality assessment using wavelet-packetbased features, linear discriminant analysis and support vector machine. Biomedical Signal Processing and Control 2012; 7: 3-19.
[43] Kavzoğlu T, |l|ffölkesen İ. Investigation of the effects of kernel functions in satellite image classification using support vector machines. Harita Dergisi 2010; 144: 73-82 (in Turkish with an abstract in English).
[44] Elhaj FA, Salim N, Harris AR, Swee TT, Ahmed T. Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals. Computer Methods and Programs in Biomedicine 2016; 127: 52-63.
[45] Colak C, Karaman E, Turtay MG. Application of knowledge discovery process on the prediction of stroke. Computer Methods and Programs in Biomedicine 2015; 119: 181-185.
[46] Acır N, Öztura I, Kuntalp M, Baklan B, Güzelis C. Automatic detection of epileptiform events in EEG by a three-stage procedure based on artificial neural networks. IEEE Transactions on Biomedical Engineering 2005; 52: 30-40.
[47] Selver MA, Taygur MM, Seçmen M, Zoral EY. Hierarchical reconstruction and structural waveform analysis for target classification. IEEE Transactions on Antennas and Propagation 2016; 67: 3120-3129.
[48] Duda RO, Hart PE, Stork DG. Pattern Classification. New York, NY, USA: Wiley-Interscience Publication, 2001.
[49] Visa S, Ramsay B, Ralescu A, Knaap EVD. Confusion matrix-based feature selection. CEUR Workshop Proceedings 2011; 710: 120-127.
[50] Cheng CG, Tian YM, Jin WY. A study on the early detection of colon cancer using the methods of wavelet feature extraction and SVM classifications of FTIR. Spectroscopy 2008; 22: 397-404.