概率神经网络在胃镜样品红外光谱检测中的应用

将人工神经网络方法应用于人体胃镜样品红外光谱检测,以克服常规线性判别分析方法的局限性,从而提高了胃镜样品判别的准确率。概率神经网络是一种适用模式分类的径向基神经网络,采用样本的先验概率和最优判定原则对新的样本进行分类,具有识别率高、训练速度快、不会陷入局部极值等优点。文章采用概率神经网络进行胃镜样品红外光谱模式识别,将预处理后的胃镜样品光谱进行主成分分析,将得分值作为输入,建立概率神经网络判别模型。文中选取118例胃镜离体样品进行红外光谱判别分析,其中正常胃组织19例,胃炎组织64例,胃癌35例,选取其中59例样品建立概率神经网络校正模型,其余样品作为预测集来检验模型。实验结果表明,正常、炎症及癌症胃镜样品检测的总体准确率达到81.4%,对胃镜样品的判别取得了较好的结果。     

结合组织芯片技术的人体胃管状腺癌组织太赫兹光谱检测

太赫兹波技术在生物医学领域具有广泛应用前景,结合人体胃管状腺癌组织检测,针对太赫兹时域光谱（THz-TDS）组织检测点位与实际病理难以配准的问题,在处理石蜡包埋的胃组织的过程中引入组织芯片技术,为实验样本的精准定位检测提供了可行方法。开展了人体胃正常组织和癌变组织太赫兹检测实验,结合主成分分析方法,对比分析了组织芯片技术配准的实验组与未配准的对照组的太赫兹吸收系数和折射率谱。此外对比研究了采用支持向量机和逻辑回归的太赫兹胃管状腺癌判别方法。研究结果表明,使用组织芯片方法有助于提升组织取材的精准性从而提高癌变样本和正常样本光谱数据的区分效果。     

傅里叶红外光谱法用于体表检测涎腺多形性腺瘤的研究

应用中红外光纤法检测了20例涎腺多形性腺瘤患者腺体部位的体表皮肤,对得到的红外光谱进行分析比较,发现多形性腺瘤、多形性腺瘤癌变及正常腺体体表皮肤红外光谱的主要特征吸收峰存在差异,可以从各特征吸收峰的峰位、峰形及不同谱峰的强度比的变化来初步判定肿瘤的性质。根据红外光谱判断其中2例已经发生癌变,与病理结果一致。从红外光谱的特征来看,多形性腺瘤是正常涎腺组织向多形性腺瘤癌变转变的中间过程。     

不同产地双色牛肝菌FTIR光谱鉴别研究

同一种蕈菌子实体,由于外观形貌相似,凭传统外观形貌特征难以鉴别产地来源。应用傅里叶变换红外光谱(FTIR)法测定了云南省5个不同地区58个野生双色牛肝菌子实体样品的红外光谱。借助于红外光谱具有的指纹特性,利用SPSS 13.0统计软件对1 350~750 cm-1范围光谱数据进行主成分分析(PCA),根据前三个主成分累积贡献率已达到88.87%以及主成分载荷分析,表明前三个主成分能够反映样品在该段光谱的主要信息。对前三个主成分作投影显示并进行比较,发现以主成分1和主成分2作二维线形投影,对不同产地的双色牛肝菌有较好的聚类和鉴别作用,所有样品被划分为5个区域,98.3%的样品被正确归类。研究结果提示,傅里叶变换红外光谱结合主成分分析方法可以快速、方便地对不同产地的同一种野生双色牛肝菌进行鉴别分类。     

SIMCA法在中红外癌症检测技术中的应用

人体肿瘤的中红外光谱法早期检测是生物医学领域的前沿课题之一。研究了中红外FTIR光谱技术与化学计量方法 (模式识别技术 )相结合对人体恶性肿瘤进行检测的方法 ,并讨论了如何通过采用光谱预处理方法以及波长范围的选择来提高模式识别技术 (SIMCA法 )分类判别效果。研究了 6 3个胃癌病人的癌变组织和癌旁正常组织光谱 ,选择有代表性的 4 0个样品作为训练集 ,剩余的 2 3个样品作为预测集 ,该方法的准确率为 91%。这一研究结果表明傅里叶变换红外光谱法与化学计量学方法相结合可以对良、恶性组织进行鉴别诊断 ,有希望发展成为一种肿瘤快速诊断的新方法。     

KNN方法在癌症中红外光谱检测中的应用

红外光谱主要是研究分子中以化学键联结的原子之间的振动光谱,它能够在分子水平上揭示正常组织和癌组织之间存在的差异。文章利用化学计量学中的有关知识通过计算机自动对未知样本光谱进行判别分析。首先应用平滑处理,基线校正(SNV方法),奇异值剔除(RHM方法)等算法对光谱数据进行预处理,然后采用K-最近邻法(简称KNN法)实现未知样本的自动判别,提高了癌症红外光谱检测的准确度。文章对63例胃组织样品进行了傅里叶变换红外光谱判别分析,与病理检验结果比较,准确度达到91.7%。     

基于多变量光谱数据分析方法的乳腺癌血清拉曼光谱特征研究

相比于细胞、组织等其他病理诊断样品，血液样本更易临床采集，其生化构成变化常表现于医学影像学检测到的临床症状出现之前，更有利于实现恶性疾病的早期筛查与诊断。拉曼光谱(RS)技术，具有快速、无标记、无损、非侵入等检测优势，且可获得特异性的生物分子结构和物质组成信息，在临床血液样品(血浆、血清)的癌变诊断检测中具有重大的应用前景。本工作采用显微拉曼光谱检测技术，在分析不同病变阶段(健康，早期癌变和晚期癌变)乳腺癌血清样品生化组成信息基础上，结合主成分分析(PCA)与线性判别分析(LDA)、支持向量机(SVM)和偏最小二乘算法(PLS-DA)等多变量光谱分析手段，构建光谱特征归类鉴别模型；并采用留一交叉验证方法(LOOCV)评估、比较这些模型的灵敏度、特异性和准确率，探索基于血清拉曼光谱的乳腺癌诊断方法。研究工作在观察血清类胡罗卜素成分共振拉曼光谱现象基础上，进一步分析了乳腺癌病理演进过程中血清样品蛋白质与脂类光谱特征变化。此外，利用多种光谱数据模型，在提取、识别更具代表性的分子光谱特征信息后，实现了较为准确的血清特征光谱信息鉴别分析。其中，PCA-LDA模型的分类准确率达99%; PCA-S...     

膀胱肿瘤离体组织的拉曼光谱学研究

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。     

FTIR结合主成分分析对棕榈科植物鉴别研究

采用傅里叶变换红外光谱(FTIR)结合主成分分析(PCA)对棕榈科植物2个亚科4个族的植物叶片进行了光谱研究。结果显示,棕榈科同族不同种和同科不同族的植物在红外光谱上表现出差异。用二阶导数光谱进行主成分分析,显示可以将样品进行正确分类。研究表明傅里叶变换红外光谱在鉴别分类植物方面具有应用潜力。     

应用血红蛋白的拉曼光谱进行食管癌诊断的研究

早期诊断对食管癌患者的治疗具有重要意义。通过对21例食管癌患者和20例健康人的血红蛋白溶液进行拉曼光谱的检测和研究,发现食管癌患者与健康人血红蛋白的拉曼光谱有较明显的区别。与健康人相比,食管癌患者血红蛋白中处于低自旋态的铁离子增多,而处于高自旋态的铁离子减少,说明癌变导致食管癌患者血红蛋白中部分处于高自旋态的铁离子转移到了低自旋态,这与癌症患者血样较易溶血的现象相吻合。采用主成分分析(PCA)方法,对所得拉曼光谱建立多元统计模型进行计算,得到的光谱峰值的PCA得分三维散点图可以良好的区分食管癌患者与健康人。利用判别分析方法得出该算法诊断食管癌的灵敏度和特异性分别为90.5%和95%,总判别正确率为92.7%。结果表明,对血红蛋白的拉曼光谱进行检测和分析有可能成为食管癌早期诊断的有效工具之一。     

Differentiation between human normal colon mucosa and colon cancer tissue using ToF-SIMS imaging technique and principal component analysis

Human normal colon mucosa and colon cancer tissue were studied using the time-of-flight secondary ion mass spectroscopy (ToF-SIMS) and principal component analysis (PCA) techniques. The surfaces of the tissues were successfully cleaned by C₆₀²⁺ cluster-ion beams before the ToF-SIMS images were obtained. A PCA on the spectra and images were performed to compare differences in the peaks and images of normal and cancer tissues. Significant differences in principal component 1 (PC 1) score values for normal and cancer tissues were observed, and each PC 1 loadings had a specific peak profile of proteins. In addition, the PC images obtained from the ToF-SIMS images for normal and cancer tissues were clearly distinguishable, and the amino acid fragments associated with normal and cancer tissues were found to have originated from the lamina propria region and the epithelium cells, respectively. Based on the PCA results, structural distortion of the crypts in the cancer colon tissue could be attributed to the proliferation of the cancerous epithelium cells. This work shows that the application of the ToF-SIMS imaging technique with PCA could be a useful method of obtaining valuable information for cancer analysis.     

Time-resolved fluorescence polarization anisotropy and optical imaging of Cybesin in cancerous and normal prostate tissues

Time-resolved polarization-dependent fluorescence of Cybesin in solution and in cancerous and normal prostate tissues were measured. The polarization preservation property of Cybesin in tissue was observed. The fluorescence intensity emitted from a Cybesin-stained cancerous tissue area was found to be much stronger than that from a Cybesin-stained normal tissue area indicating that cancerous prostate tissue takes-up more Cybesin than normal tissue. The polarization anisotropy of Cybesin contained in cancerous prostate tissue was found to be larger than that of Cybesin in normal prostate tissue indicating that a larger degree of polarization was preserved in the Cybesin-stained cancerous tissue due to structures. A static anisotropy component from the emission of cell-bonded Cybesin molecules in tissue and a time-dependent anisotropy component from the emission of un-bonded Cybesin molecules were determined and discussed. The static anisotropy value of Cybesin in stained cancerous tissue was found to be much larger than that in stained normal tissue. The fluorescence polarization difference imaging technique based on the polarization preservation of Cybesin was used to enhance the image contrast between cancerous and normal prostate tissue areas.     

傅里叶变换红外光谱法研究肺组织切片

采用傅里叶变换红外光谱(FTIR)仪并借助OMNI采样器直接、快速地测定了正常肺组织及肺癌组织的红外光谱,通过研究表明,正常肺组织与肺癌组织样品的红外光谱在峰位、峰强及峰形等方面均存在明显而有规律的红外光谱差异,这反映了组织中的蛋白质、核酸和脂类等生物分子在不同性质的组织中含量上的差异。研究表明,FTIR可从分子水平上揭示正常肺组织和肺癌组织的特性,能对正常肺组织和肺癌组织的良、恶性的鉴别提供丰富而可靠的结构信息。     

Time-resolved spectral wing emission kinetics and optical imaging of human cancerous and normal prostate tissues

Time-resolved polarization-dependent kinetics of near infrared (NIR) spectral wing (SW) emission from human cancerous and normal prostate tissues was investigated. The differences between the temporal profiles, intensities and polarization properties of SW emission from cancerous and normal prostate tissues were observed. The intensity of SW emission from cancerous prostate tissue at peak position was found ∼2 times stronger than the normal prostate tissue indicating changes of fluorophores contained in the cancerous tissue compared with normal tissue. The decay time of anisotropy of SW emission from cancerous tissue was found ∼1.4 times longer than that of normal tissue reflecting changes of the micro-environment of fluorophores in the cancerous tissue as compared with the normal tissue. The stronger intensity of SW emission from cancerous tissue was used to image and identify cancerous areas surrounded by normal tissue.     

Polarized spectral features of human breast tissues through wavelet transform and principal component analysis

Fluorescence characteristics of human breast tissues are investigated through wavelet transform and principal component analysis (PCA). Wavelet transform of polarized fluorescence spectra of human breast tissues is found to localize spectral features that can reliably differentiate different tissue types. The emission range in the visible wavelength regime of 500–700 nm is analysed, with the excitation wavelength at 488 nm using laser as an excitation source, where flavin and porphyrin are some of the active fluorophores. A number of global and local parameters from principal component analysis of both high- and low-pass coefficients extracted in the wavelet domain, capturing spectral variations and subtle changes in the diseased tissues are clearly identifiable.     

Raman spectroscopy at different excitation wavelengths (1064, 785 and 532 nm) as a tool for diagnosis of colon cancer

Raman spectroscopy is structure sensitive non‐destructive method that allows observing the status of biological tissues with minimal impact. This method has a great potential in the diagnosis of various types of degenerative diseases including cancer damages. Near‐infrared Fourier transform (NIR‐FT)‐Raman (λ_ex ~1064 nm), NIR‐visible (Vis)‐Raman (λ_ex ~785 nm) and Vis‐Raman (λ_ex ~532 nm) spectra of normal and colorectal carcinoma colon tissue samples were recorded in macroscopic mode at 10–20 randomly chosen independent sites. In the cases of NIR‐Vis‐ and Vis‐Raman spectra, enhanced resonance effects were observed for tissue chromophores absorbing in the visible area. Evident spectral differences were noticed for Raman spectra of normal colon tissue samples in comparison with abnormal samples. The average Raman spectra of colon tissue samples were analysed by principal component analysis (PCA) to discriminate normal and abnormal tissues. PCA of combined dataset containing Raman intensities of chosen NIR‐FT, NIR‐Vis or Vis‐Raman bands led to discrimination of normal and abnormal colon tissue samples. Therefore, combination of these three Raman methods can be helpful for recognizing cancer lesions in colon for diagnostic purposes. Copyright © 2014 John Wiley & Sons, Ltd.     

Study of both fingerprint and high wavenumber Raman spectroscopy of pathological nasopharyngeal tissues

High wavenumber (HW) Raman spectroscopy has weaker fluorescence background compared with fingerprint (FP) region. This study aims to evaluate the discrimination feasibility of nasopharyngeal non‐cancerous and nasopharyngeal cancer (NPC) tissue with both FP and HW Raman spectroscopy. HW Raman spectra of nasopharyngeal tissue were obtained for the first time. Raman spectra were collected to differentiate nasopharyngeal non‐cancerous (n = 37) from NPC (n = 41) tissues in FP (800–1800cm⁻¹), HW (2700–3100cm⁻¹), and integrated FP/HW region. First, to assess the utility of this method, the averaged Raman spectral intensities and intensity ratios of corresponding Raman bands were analyzed in HW and FP regions, respectively. The results show that intensities as well as the ratios of specific Raman peaks might be helpful in distinguishing nasopharyngeal non‐cancerous from NPC tissue with the HW Raman spectroscopy, as with FP Raman reported before. The multivariate statistical method based on the combination of principal component analysis–liner discriminant analysis (PCA‐LDA), together with leave‐one‐patient‐out, cross‐validation diagnostic algorithm, was used for discriminating nasopharyngeal non‐cancerous from NPC tissue, generating sensitivities of 87.8%, 85.4%, and 95.1% and specificities of 86.5%, 91.9%, and 89.2%, respectively, with Raman spectroscopy in the FP, HW, and integrated FP/HW regions. The posterior probability of classification results and receiver operating characteristic curves were utilized to evaluate the discrimination of PCA‐LDA algorithm, verifying that HW Raman spectroscopy has a positive effect on the differentiation for the diagnosis of NPC tissue by integrated FP/HW Raman spectroscopy. What's more, the potential of Raman spectroscopy used for differentiating different pathology NPC tissues was also discussed. The results demonstrate that both FP and HW Raman spectroscopy have the potential for diagnosis and detection in early nasopharyngeal carcinoma, and HW Raman spectroscopy may improve the discrimination of NPC tissue compared with FP region alone, providing a promising diagnostic tool for the diagnosis of NPC tissue. Copyright © 2015 John Wiley & Sons, Ltd.     

Raman spectral properties of squamous cell carcinoma of oral tissues and cells

Early diagnosis is the key of the improved survival rates of oral cancer. Raman spectroscopy is sensitive to the early changes of molecular composition and structure that occur in benign lesion during carcinogenesis. In this study, in situ Raman analysis provided distinct spectra that can be used to discriminate between normal and malignant tissues, as well as normal and cancer cells. The biochemical variations between different groups were analyzed by the characteristic bands by comparing the normalized mean spectra. Spectral profiles of normal, malignant conditions show pronounced differences between one another, and multiple Raman markers associated with DNA and protein vibrational modes have been identified that exhibit excellent discrimination power for cancer sample identification. Statistical analyses of the Raman data and classification using principal component analysis (PCA) are shown to be effective for the Raman spectral diagnosis of oral mucosal diseases. The results indicate that the biomolecular differences between normal and malignant conditions are more obviously at the cellular level. This technique could provide a research foundation for the Raman spectral diagnosis of oral mucosal diseases.     

Raman spectroscopic identification of normal and malignant hepatocytes

Raman spectroscopy has strong potential for providing non-invasion diagnosis of cancers. In this paper, micro-Raman spectroscopy is used to diagnose one most common liver cancer, hepatocellular carcinoma （HCC）. The statistical analyzes, including t-test, principal component analysis （PCA）, and linear discriminant analysis （LDA）, are performed on the Raman spectra of malignant and normal hepatocytes. The t-test-LDA results show that the 786- and 1004-cm^-1 bands of the malignant and normal hepatocytes are significantly different, and PCA-LDA results show an overall accuracy of 100% for the Raman spectroscopic identification of normal and malignant hepatocytes in our experiment.     

FAAS与化学计量学方法用于食品分类及相关性

采用火焰原子吸收光谱法测定常见谷物及红枣中5种金属元素含量。运用化学计量学方法中聚类分析（HCA）、主成分分析（PCA）及对应分析（CA）对其进行分类对比研究,结果表明FAA S结合化学计量学方法用于食品分类研究,为食品类别分析工作提供简单、科学的数据处理方法。