Li Xiang, Li Qing-Bo, Zhang Guang-Jun, Xu Yi-Zhuang, Sun Xue-Jun, Shi Jing-Sen, Zhang Yuan-Fu, Wu Jin-Guang
College of Instrument Science and Opto-Electronics Engineering, Beihang University, Beijing 100083, China.
ScientificWorldJournal. 2012;2012:936149. doi: 10.1100/2012/936149. Epub 2012 May 3.
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.
癌症是一种对人类健康危害极大的疾病。傅里叶变换红外光谱（FT-IR）能够识别生物样本在分子水平上的变异性。它是一种快速且非侵入性的方法，可在手术中用于调整手术程序。本文的目的是通过使用FT-IR光谱在内镜下结肠活检中识别并区分癌症与结肠炎。共获取了88份内镜下结肠样本，其中包括41例结肠炎病例和47例结肠癌病例。将样本放置在与配备MCT探测器的FT-IR光谱仪相连的衰减全反射（ATR）附件上，以获得更高的稳定性和灵敏度。之后，将样本送去进行组织学检查，作为光谱分析的参考。对41份结肠炎样本和47份癌症样本进行了比较。使用经过平滑和归一化预处理的光谱进行判别分析。进行主成分分析（PCA）以简化光谱数据集。构建朴素贝叶斯分类器模型进行诊断分类。采用留一法交叉验证方法评估判别结果。FT-IR检测癌症的灵敏度达到97.6%。结果表明，使用FT-IR光谱和化学计量学能够高精度地区分结肠癌与结肠炎。
