本文關(guān)鍵詞： 近紅外光譜 無(wú)創(chuàng)生化分析 血流容積光譜相減法 模型穩(wěn)健性　出處：《中國(guó)科學(xué)院研究生院（長(zhǎng)春光學(xué)精密機(jī)械與物理研究所）》2012年碩士論文　論文類型：學(xué)位論文

【摘要】：血液不斷流動(dòng)于人體循環(huán)系統(tǒng)之中,對(duì)于維持機(jī)體新陳代謝、功能調(diào)節(jié),以及內(nèi)外環(huán)境間的平衡等方面都起著十分重要的作用。血液生化成分檢測(cè)作為健康診斷與疾病監(jiān)控的有效手段,在臨床診療領(lǐng)域具有非常重要的意義。 然而,臨床常規(guī)采用的血液檢驗(yàn)方法多為有創(chuàng)方法,檢測(cè)周期較長(zhǎng)且需用試劑。近紅外無(wú)創(chuàng)生化檢測(cè)技術(shù)具有無(wú)創(chuàng)傷、無(wú)感染、無(wú)需試劑、便于實(shí)時(shí)監(jiān)測(cè)等特點(diǎn),已成為目前國(guó)際上的研究熱點(diǎn)。目前近紅外無(wú)創(chuàng)生化分析技術(shù)主要面臨的問(wèn)題包括：血液有效信息微弱；人體組織背景干擾嚴(yán)重；血流容積隨心臟搏動(dòng)不斷變化。為消除組織背景及脈搏的干擾,課題組提出血流容積光譜相減方法。通過(guò)將不同血流容積下測(cè)得的兩幅光譜相減,可有效扣除皮膚、肌肉等組織背景的干擾,從而提取血流容積變化量對(duì)應(yīng)于血液成分信息的純凈光譜。 本論文圍繞近紅外無(wú)創(chuàng)生化分析中的模型穩(wěn)健性問(wèn)題展開(kāi)了研究。為提高血流容積光譜相減法的數(shù)據(jù)信噪比,考察了人體容積脈搏信號(hào)的噪聲干擾問(wèn)題,分析了噪聲的主要來(lái)源并提出解決方案；為提高血液生化成分定標(biāo)模型的預(yù)測(cè)能力,對(duì)比分析了不同數(shù)據(jù)預(yù)處理算法、建模方法及其組合下的定標(biāo)結(jié)果,優(yōu)化模型,提高穩(wěn)健性。主要研究?jī)?nèi)容與取得的成果有： 1)應(yīng)用課題組自行設(shè)計(jì)的近紅外血液無(wú)創(chuàng)生化檢測(cè)系統(tǒng),通過(guò)臨床測(cè)量實(shí)驗(yàn),無(wú)創(chuàng)采集到不同年齡、不同性別志愿者的食指指端容積脈搏波光譜數(shù)據(jù),對(duì)比分析不同人群的光譜信號(hào)差異； 2)分析總結(jié)了人體容積脈搏光譜信號(hào)的主要噪聲來(lái)源并提出多種光譜去噪方法,分別采用移動(dòng)平均平滑、Savitzky-Galay卷積平滑、經(jīng)驗(yàn)?zāi)B(tài)分解、小波變換濾波等算法處理脈搏信號(hào),有效地抑制了數(shù)據(jù)噪聲,提升了光譜性能； 3)結(jié)合不同數(shù)據(jù)預(yù)處理算法及建模方法建立血液生化成分定量校正模型,對(duì)比分析不同定標(biāo)模型的預(yù)測(cè)精度,通過(guò)優(yōu)選算法優(yōu)化模型提高模型穩(wěn)健性。經(jīng)實(shí)驗(yàn)驗(yàn)證,BP-ANN模型結(jié)合經(jīng)驗(yàn)?zāi)B(tài)分解方法對(duì)HCT及血紅蛋白的預(yù)測(cè)能力較優(yōu),預(yù)測(cè)相關(guān)系數(shù)可分別達(dá)到0.92和0.87,預(yù)測(cè)標(biāo)準(zhǔn)差分別為1.66%和8.08g/L-1。 本文深入分析了近紅外無(wú)創(chuàng)生化檢測(cè)中的模型穩(wěn)健性問(wèn)題,研究了血流容積光譜相減方法中信噪比的提升方法并優(yōu)選了血液生化成分建模算法,為近紅外無(wú)創(chuàng)生化檢測(cè)技術(shù)的實(shí)際應(yīng)用提供了理論和實(shí)驗(yàn)基礎(chǔ)。
[Abstract]:Blood flow in the human circulatory system, for the maintenance of the body metabolism, function regulation. As an effective means of health diagnosis and disease monitoring, the detection of blood biochemical components plays a very important role in the field of clinical diagnosis and treatment. However, most of the routine blood testing methods are invasive, and the detection period is longer and reagent is needed. Near-infrared non-invasive biochemical detection technology has no trauma, no infection, no reagent. The advantages of real-time monitoring have become an international research hotspot. At present, NIR non-invasive biochemical analysis technology is mainly faced with the following problems: weak effective blood information; The interference of human tissue background is serious; In order to eliminate the interference of tissue background and pulse, the method of blood flow volume spectral subtraction was put forward. Two spectra were subtracted from different blood flow volumes. It can effectively deduct the interference of skin, muscle and other tissue background, so as to extract the pure spectrum of the volume change of blood flow corresponding to the information of blood composition. In order to improve the signal-to-noise ratio (SNR) of blood flow volume spectral subtraction, the noise interference of human volumetric pulse signal was investigated. The main sources of noise are analyzed and solutions are put forward. In order to improve the prediction ability of the blood biochemical component calibration model, different data preprocessing algorithms, modeling methods and their combination of calibration results, optimization model were compared and analyzed. Improving robustness. The main research contents and achievements are as follows: 1) using the NIR blood noninvasive biochemical detection system designed by our research group, we collected the pulse wave spectrum data of index finger volume of volunteers of different ages and different genders through the clinical measurement experiment. The spectral signals of different populations were compared and analyzed. 2) the main noise sources of human body volumetric pulse spectral signal are analyzed and summarized, and a variety of spectral denoising methods are proposed. The moving average smoothing method is used to smooth Savitzky-Galay convolution. Some algorithms such as empirical mode decomposition and wavelet transform filter are used to process pulse signal, which can effectively suppress the data noise and improve the spectral performance. 3) combined with different data preprocessing algorithms and modeling methods, the quantitative calibration model of blood biochemical components was established, and the prediction accuracy of different calibration models was compared and analyzed. The model robustness is improved by optimizing the model by optimal selection algorithm. The prediction ability of BP-ANN model combined with empirical mode decomposition method for HCT and hemoglobin is proved to be better. The predictive correlation coefficient is 0.92 and 0.87, respectively, and the predicted standard deviation is 1.66% and 8.08 g / L ~ (-1), respectively. In this paper, the model robustness in NIR noninvasive biochemical detection is analyzed in depth, and the enhancement method of SNR in blood volume spectral subtraction method is studied, and the modeling algorithm of blood biochemical composition is selected. It provides a theoretical and experimental basis for the practical application of NIR noninvasive biochemical detection technology.
【學(xué)位授予單位】：中國(guó)科學(xué)院研究生院（長(zhǎng)春光學(xué)精密機(jī)械與物理研究所）
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：R-332

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張俊利;藺嫦燕;;容積脈搏波的檢測(cè)方法及其在評(píng)價(jià)心血管功能方面的應(yīng)用[J];北京生物醫(yī)學(xué)工程;2007年02期

2 張彬;張業(yè)宏;李明彩;;小波變換與形態(tài)學(xué)運(yùn)算相結(jié)合的脈搏波檢測(cè)算法[J];電子測(cè)量技術(shù);2011年06期

3 謝軍;潘濤;陳潔梅;陳華舟;任小煥;;血糖近紅外光譜分析的Savitzky-Golay平滑模式與偏最小二乘法因子數(shù)的聯(lián)合優(yōu)選[J];分析化學(xué);2010年03期

4 陳華才,楊仲國(guó),陳星旦,蔣迎;傅里葉變換近紅外光譜法快速檢測(cè)人血清生化成分[J];分析試驗(yàn)室;2005年07期

5 齊小明,張錄達(dá),杜曉林,宋昭娟,張一,徐淑燕;PLS-BP法近紅外光譜定量分析研究[J];光譜學(xué)與光譜分析;2003年05期

6 李剛;門劍龍;孫兆敏;王慧泉;林凌;佟穎;張寶菊;;小波變換提高動(dòng)態(tài)光譜法血液成分無(wú)創(chuàng)檢測(cè)的精度[J];光譜學(xué)與光譜分析;2011年02期

7 陳星旦;;近紅外光譜無(wú)創(chuàng)生化檢驗(yàn)的可能性[J];光學(xué)精密工程;2008年05期

8 張寶菊;賈萍;張志勇;林凌;門劍龍;李剛;;PLS在基于動(dòng)態(tài)光譜的人體血液中性粒細(xì)胞無(wú)創(chuàng)測(cè)量中的應(yīng)用[J];光譜學(xué)與光譜分析;2010年02期

9 褚小立,袁洪福,陸婉珍;近紅外分析中光譜預(yù)處理及波長(zhǎng)選擇方法進(jìn)展與應(yīng)用[J];化學(xué)進(jìn)展;2004年04期

10 梁逸曾;吳海龍;沈國(guó)勵(lì);蔣健暉;陳增萍;梁晟;俞汝勤;;分析化學(xué)計(jì)量學(xué)的若干新進(jìn)展[J];中國(guó)科學(xué)(B輯 化學(xué));2006年02期

相關(guān)博士學(xué)位論文 前5條

1 黃富榮;人體血液膽固醇、甘油三酯近紅外光譜無(wú)試劑分析方法研究[D];暨南大學(xué);2010年

2 徐惠榮;基于可見(jiàn)/近紅外光譜的水果糖度檢測(cè)模型優(yōu)化及應(yīng)用研究[D];浙江大學(xué);2010年

3 楊皓e，

本文編號(hào)：1481061