Identification of Colitis and Cancer in Colon Biopsies by Fourier Transform Infrared Spectroscopy and Chemometrics

Cancer is a disease that does great harms to the health of human beings. FT-IR spectroscopy could identify variability at the molecular level in biological specimens. It is a rapid and noninvasive method, which could be used intraoperatively to modify surgical procedures. The aim of this paper is to identify and separate cancer from colitis in endoscopic colon biopsies through the use of FT-IR spectroscopy. A total of 88 endoscopic colon samples, including 41 cases of colitis and 47 cases of colon cancer, were obtained. Specimens were placed on an ATR accessory linked to FT-IR spectrometer with a MCT detector for greater stability and sensitivity. Later, specimens were sent for the histological examination as the reference in the spectral analysis. 41 colitis and 47 cancer specimens were compared. Spectra preprocessed with smoothing and normalization were used for discrimination analysis. PCA was processed to simplify the spectrum data set. Naive Bayes classifier model was constructed for diagnostic classification. Leave-one-out cross-validation method was utilized to assess the discrimination results. The sensitivity of FT-IR detection for cancer achieves 97.6%. The results showed that colon cancer could be distinguished from colitis with high accuracy using FT-IR spectroscopy and chemometrics.

[1]  H P Wang,et al.  Microscopic FTIR studies of lung cancer cells in pleural fluid. , 1997, The Science of the total environment.

[2]  H. Heise,et al.  Glucose and other constituents of blood determined by ATR-FTIR-spectroscopy. , 1990, Clinical chemistry.

[3]  Yi-zhuang Xu,et al.  Discrimination of normal and malignant gastric tissues with FTIR spectroscopy and principal component analysis. , 2004, Guang pu xue yu guang pu fen xi = Guang pu.

[4]  R. Soloway,et al.  Distinguishing malignant from normal oral tissues using FTIR fiber-optic techniques. , 2001, Biopolymers.

[5]  N. Dusitsin,et al.  A new approach for the detection of cervical cancer in Thai women. , 2003, Gynecologic oncology.

[6]  Jing Wang,et al.  FT-IR spectroscopic analysis of normal and cancerous tissues of esophagus. , 2003, World journal of gastroenterology.

[7]  Li Zhang,et al.  In vivo and in situ detection of colorectal cancer using Fourier transform infrared spectroscopy. , 2005, World journal of gastroenterology.

[8]  Martin Mozina,et al.  Nomograms for Visualization of Naive Bayesian Classifier , 2004, PKDD.

[9]  Tsunenori Arai,et al.  Discrimination between normal and malignant human gastric tissues by Fourier transform infrared spectroscopy. , 2004, Cancer detection and prevention.

[10]  P. Nabet,et al.  Rapid determination of fecal fat by Fourier transform infrared analysis (FTIR) with partial least-squares regression and an attenuated total reflectance accessory. , 1996, Clinical chemistry.

[11]  Chris H. Q. Ding,et al.  K-means clustering via principal component analysis , 2004, ICML.

[12]  Yi-Zhuang Xu,et al.  Diagnosis of gastric inflammation and malignancy in endoscopic biopsies based on Fourier transform infrared spectroscopy. , 2005, Clinical chemistry.

[13]  Geoffrey I. Webb,et al.  Not So Naive Bayes: Aggregating One-Dependence Estimators , 2005, Machine Learning.

[14]  Gianluca Bontempi,et al.  New Routes from Minimal Approximation Error to Principal Components , 2008, Neural Processing Letters.

[15]  B. Rigas,et al.  Human colorectal cancers display abnormal Fourier-transform infrared spectra. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[16]  D. Hand,et al.  Idiot's Bayes—Not So Stupid After All? , 2001 .