激光与光电子学进展, 2016, 53 (3): 031701, 网络出版: 2016-01-22   

广义极大似然估计在OCT 无创血糖监测中的应用 下载: 919次

Application of Maximum Likelihood Type Estimates in Noninvasive Blood Glucose Monitoring in vivo Using Optical Coherence Tomography
作者单位
1 江南大学理学院, 江苏 无锡 214000
2 河北大学物理学院光信息创新中心, 河北 保定 071002
摘要
在光学相干层析术(OCT)无创血糖监测过程中,预测模型的建立容易受异常点的干扰。采用广义极大似然估计(M 估计)建立的预测模型能够有效地通过权函数降低异常点在模型中的权重。通过人体血糖钳夹临床实验和口服葡萄糖耐量测试实验,利用M 估计和最小二乘估计法(OLS 估计)两种方法建立了血糖预测模型,采用交互验证法对两种模型的均方根误差(RMSE)进行了比较。对比结果表明,M 估计能有效地降低血糖预测模型的RMSE 值。此外,利用克拉克误差表格分析法对两个模型的预测结果进行评估,评估结果表明采用M 估计建立的血糖预测模型的准确性和稳定性高于OLS 估计,因此M 估计更适合临床上的OCT 无创血糖监测应用。
Abstract
During the model building process, the blood glucose monitoring model can be easily damaged by abnormal points. Maximum likelihood type estimates (M estimates) introduced in this paper can decrease the weight of abnormal points in the blood glucose model. In glucose clamp experiment and human oral glucose tolerance test, M estimates and ordinary least sum of squares estimates (OLS estimates) are applied to build the blood glucose monitoring models, respectively. Root mean square error (RMSE) of the model built by M estimates is calculated by using interactive verification method. It shows that M estimates can effectively reduce the RMSE value of blood glucose prediction results. In addition, predicted values of blood glucose by the two models are evaluated by Clarke error grid analysis. The results show that the veracity and stability of the blood prediction model built by M estimates are higher than that built by OLS estimates. Thus, the method of M estimates is more suitable for clinical application of noninvasive blood glucose sensing using optical coherence tomography.
参考文献

[1] 石博雅, 孟卓, 刘铁根, 等. OCT 系统对人体牙齿组织的非失真成像深度的研究[J]. 光学学报, 2014, 34(2): 0212001.

    Shi Boya, Meng Zhuo, Liu Tiegen, et al.. Non-distorted imaging depth of optical coherence tomography system in human dental tissues[J]. Acta Optica Sinica, 2014, 34(2): 0212001.

[2] 郭昕, 王向朝, 步鹏, 等. 样品散射对频域光学相干层析成像光谱形状和深度分辨率的影响[J]. 光学学报, 2014, 34(1): 0117001.

    Guo Xin, Wang Xiangzhao, Bu Peng, et al.. Effects of scattering on spectral shape and depth resolution in Fourier domain optical coherence tomography[J]. Acta Optica Sinica, 2014, 34(1): 0117001.

[3] 王玲, 朱海龙, 涂沛, 等. 基于LabVIEW 的高速三维扫频光学相干层析成像系统[J]. 中国激光, 2014, 41(7): 0704001.

    Wang Ling, Zhu Hailong, Tu Pei, et al.. High-speed three-dimensional swept source optical coherence tomography system based on LabVIEW[J]. Chinese J Lasers, 2014, 41(7): 0704001.

[4] 秦玉伟. 光学薄膜缺陷的光学相干层析检测方法研究[J]. 激光与光电子学进展, 2015, 52(7): 071202.

    Qin Yuwei. Study on defect detection of optical thin film using optical coherence tomography[J]. Laser & Optoelectronics Progress, 2015, 52(7): 071202.

[5] 杨珊珊, 朱锐, 米磊, 等. 光学相干层析成像技术对壁画的检测研究[J]. 光学学报, 2015, 35(5): 0511005.

    Yang Shanshan, Zhu Rui, Mi Lei, et al.. Application of optical coherence tomography in the detection of the mural[J]. Acta Optica Sinica, 2015, 35(5): 0511005.

[6] Tuchin V V, Maksimova I L, Zimnyakov D A, et al.. Light propagation in tissues with controlled optical properties[J]. Journal of Biomedical Optics, 1997, 2(4): 401-417.

[7] Larin K V, Ashitkov T V, Larina I V, et al.. Optical coherence tomography and noninvasive blood glucose monitoring: A review[C]. SPIE, 2004, 5474: 285-290.

[8] Huber P J, Ronchetti E M. Robust Statistics (2nd Edition)[M]. USA: Wiley, 2009.

[9] Su Y, Yao X S, Li Z, et al.. Measurements of the thermal coefficient of optical attenuation at different depth regions of in vivo human skins using optical coherence tomography: A pilot study[J].Biomedical Optics Express, 2015, 6(2): 500-513.

[10] Su Y, Yao X S, Meng Z, et al.. Effect of temperature on noninvasive blood glucose monitoring in vivo using optical coherence tomography[J]. Chinese Optics Letters, 2014, 12(11): 111701.

[11] 李庆波, 阎侯赖, 李丽娜, 等. 偏稳健M 回归在人体血糖浓度近红外无创检测中的应用[J]. 光谱学与光谱分析, 2010, 30(8): 2115-2119.

    Li Qingbo, Yan Houlai, Li Lina, et al.. Application of partial robust M-regression in noninvasive measurement of human blood glucose concentration with near-infrared spectroscopy[J]. Spectroscopy and Spectral Analysis, 2010, 30(8): 2115-2119.

[12] 王海娜. 线性回归模型的若干稳健估计方法及应用实例[D]. 济南: 山东大学, 2013.

    Wang Haina. Some Robust Estimation Methods and Application Examples of Linear Regression Models[D]. Jinan: Shandong University, 2013.

[13] 苏亚, 孟卓, 王龙志, 等. 光学相干层析无创血糖检测中相关性分析及标定[J]. 中国激光, 2014, 41(7): 0704002.

    Su Ya, Meng Zhuo, Wang Longzhi, et al.. Correlation analysis and calibration of noninvasive blood glucose monitoring with optical coherence tomography[J]. Chinese J Lasers, 2014, 41(7): 0704002.

[14] Elisseeff A, Pontil M. Leave-one-out error and stability of learning algorithms with applications[M]. //Learning Theory and Practice, 2002: 9640573.

[15] 王龙志. 基于OCT 的皮肤光学特征研究及其在无创血糖检测中的应用[D]. 天津: 天津大学, 2014.

    Wang Longzhi. OCT Based Studies of Skin Features and Their Applications in the Non-Invasive Blood Glucose Test[D].Tianjin: Tianjin University, 2014.

[16] Clarke W L. The original Clarke error grid analysis (Ega)[J]. Diabetes Technology & Therapeutics, 2005, 7(5): 776-779.

[17] Garg S, Zisser H, Schwartz S, et al.. Improvement in glycemic excursions with a transcutaneous, real-time continuous glucose sensor: A randomized controlled trial[J]. Diabetes Care, 2006, 29(1): 44-50.

付磊, 苏亚, 李果华, 姚晓天. 广义极大似然估计在OCT 无创血糖监测中的应用[J]. 激光与光电子学进展, 2016, 53(3): 031701. Fu Lei, Su Ya, Li Guohua, X Steve. Application of Maximum Likelihood Type Estimates in Noninvasive Blood Glucose Monitoring in vivo Using Optical Coherence Tomography[J]. Laser & Optoelectronics Progress, 2016, 53(3): 031701.

本文已被 5 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!