Study of Near Infrared Spectral Preprocessing and Wavelength Selection Methods for Endometrial Cancer Tissue
ZHAO Li-ting1, XIANG Yu-hong1, DAI Yin-mei2, ZHANG Zhuo-yong1*
1. Department of Chemistry, Capital Normal University, Beijing 100048, China 2. Beijing Obstetrics and Gynecology Hospital, Affiliated Capital University of Medical Science, Beijing 100006, China
Abstract：Near infrared spectroscopy was applied to measure the tissue slice of endometrial tissues for collecting the spectra. A total of 154 spectra were obtained from 154 samples. The number of normal, hyperplasia, and malignant samples was 36, 60, and 58, respectively. Original near infrared spectra are composed of many variables, for example, interference information including instrument errors and physical effects such as particle size and light scatter. In order to reduce these influences, original spectra data should be performed with different spectral preprocessing methods to compress variables and extract useful information. So the methods of spectral preprocessing and wavelength selection have played an important role in near infrared spectroscopy technique. In the present paper the raw spectra were processed using various preprocessing methods including first derivative, multiplication scatter correction, Savitzky-Golay first derivative algorithm, standard normal variate, smoothing, and moving-window median. Standard deviation was used to select the optimal spectral region of 4 000-6 000 cm-1. Then principal component analysis was used for classification. Principal component analysis results showed that three types of samples could be discriminated completely and the accuracy almost achieved 100%. This study demonstrated that near infrared spectroscopy technology and chemometrics method could be a fast, efficient, and novel means to diagnose cancer. The proposed methods would be a promising and significant diagnosis technique of early stage cancer.
赵立婷1，相玉红1，代荫梅2，张卓勇1* . 子宫内膜癌组织近红外光谱预处理与波段选择研究[J]. 光谱学与光谱分析, 2010, 30(04): 901-905.
ZHAO Li-ting1, XIANG Yu-hong1, DAI Yin-mei2, ZHANG Zhuo-yong1* . Study of Near Infrared Spectral Preprocessing and Wavelength Selection Methods for Endometrial Cancer Tissue . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(04): 901-905.
[1] Duska L R, Garrett A, Rueda B R, et al. Gynecologic Oncology, 2001, 83(2): 388. [2] XU Jian-rong, YANG Shi-xun, WANG Wan, et al(许建荣, 杨世埙, 王 皖, 等). Chinese Journal of Medical Computed Imaging(中国医学计算机成像杂志), 1997, 3(2): 105. [3] Huang Z W, McWilliams A, Lui H, et al. Int. J. Cancer, 2003, 107(6): 1047. [4] Kondepati V R, Keese M, Mueller R, et al. Vibrational Spectroscopy, 2007, 44(2): 236. [5] Hornung R, Pham T H, Keefel K A, et al. Human Reproduction, 1999, 14(11) : 2908. [6] Asgari S, Rohrborn H J, Engelhorn T, et al. Acta Neurochirurgica, 2003, 145(6): 453. [7] McIntosh L M, Summers R, Jackson M, et al. The Journal of Investigative Dermatology, 2001, 116(1): 175. [8] Ali J H, Wang W B, Zevallos M, et al. Technology in Cancer Research & Treatment, 2004, 3(5): 491. [9] Bard M P L, Amelink A, Hegt V N, et al. American Journal of Respiratory and Critical Care Medicine, 2005, 171(10): 1178. [10] Sunar U, Quon H, Durduran T, et al. Journal of Biomedical Optics, 2006, 11(6): 064021. [11] Kondepati V R, Zimmermann J, Keese M, et al. Journal of Biomedical Optics, 2005, 10(5): 054016. [12] Schmitz C H, Klemer D P, Hardin R, et al. Applied Optics, 2005, 44(11): 2140. [13] CHU Xiao-li, YUAN Hong-fu, LU Wan-zhen(褚小立, 袁洪福, 陆婉珍). Progress in Chemistry(化学进展), 2004, 16(4): 528. [14] Geladi P, MacDougall D, Martens H. Appied Spectroscopy, 1985, 39(3): 491. [15] Gorry P A. Anal. Chem., 1990, 62(6): 570.
