论文部分内容阅读
使用激光共聚焦显微拉曼光谱仪测取膀胱肿瘤和正常膀胱组织的拉曼特征谱,应用主成分分析/支持向量机(principal component analysis,PCA/support vector machines,SVM)分类器对数据进行判别分析,最后使用弃一交叉验证法(leave-one-out cross validation,LOOCV)测试判别结果的准确度。结果发现膀胱肿瘤组织与正常膀胱组织的拉曼光谱存在明显差异,肿瘤组织在782和1 583cm-1等核酸特征谱带处峰高显著增强,而正常组织在1 061,1 295,2 849,2 881cm-1等蛋白质和脂质特征谱带处峰高显著增强。PCA/SVM可良好区分膀胱肿瘤组织和正常膀胱组织的拉曼光谱,LOOCV测试分类器显示肿瘤诊断的敏感度86.7%、特异度87.5%、阳性预测值92.9%、阴性预测值77.8%。由此得出结论:拉曼光谱可以良好诊断膀胱肿瘤的体外组织,展现了优越的临床应用前景。
Raman profiles of bladder tumor and normal bladder tissue were measured by laser confocal microscopy and Raman spectroscopy. The principal component analysis (PCA / support vector machines, SVM) classifier was used to discriminate the data Analysis, and finally use the leave-one-out cross validation (LOOCV) test to determine the accuracy of the results. The results showed that the Raman spectra of bladder tumor tissue and normal bladder tissue were significantly different. The tumor tissue at 782 and 1 583cm-1 and other nucleic acid characteristic bands at the peak significantly increased, while the normal tissue in 1061, 2955, 2849, 2 881cm-1 and other protein and lipid characteristic bands at the peak height increased significantly. PCA / SVM could well distinguish Raman spectra of bladder tumor and normal bladder tissue. The LOOCV test classifier showed 86.7% sensitivity, 87.5% specificity, 92.9% positive predictive value, and 77.8% negative predictive value. This concludes that: Raman spectroscopy can be a good diagnosis of bladder tumor in vitro tissue, showing a superior clinical application.