WANG Xue-min1, SHAO Na1, WANG Rui-yun1, SUN Ying-ying1, YU Zhi-feng2, JIANG Zhi-hao2, ZHOU Peng1
（1. School of Precision Instruments and Optical Electronics Engineering， Tianjin University， Tianjin 300072， China； 2. College of Traditional Chinese Medicine, Tianjin University of Traditional Chinese Medicine， Tianjin 300193， China）
Abstract： Since traditional nail diagnosis is susceptible to objective factors such as illumination, medical experience, etc., a nail diagnosis system of traditional Chinese medicine which combines objective nail image acquisition with information analysis is proposed and applied to the clinical research of nail diagnosis of uremia patients. Fifteen nail pictures of uremic patients were collected and segmented. The color information of nails was extracted. The relationship between the hemoglobin values of uremic patients and the values of color space before and after maintenance hemodialysis was analyzed by correlation analysis and multiple regression analysis. The experimental results show that the hemoglobin value of uremic patients have certain correlations with multiple color channels; before and after dialysis, there are significant changes in multiple channels; and the related multiple regression equation is established.
Key words： nail classification; nail color; uremia; correlation analysis; paired t test; multiple regression
CLD number： TP391 doi： 10.3969/j.issn.1674-8042.2020.01.005
References
［1］Lu X Z, Chen L T. Look at your nails and know your health. Tianjin: Tianjin Science and Technology Press, 2009: 16-21.
［2］Chen H, Zhong A M, Liu Y M, et al. Diagnostic significance of methylcreatinine in acute renal injury in chronic kidney disease. Jiangxi Medicine, 2008, 43(12): 1350-1352.
［3］Dong Q, Liu G, Liu T H, et al. Infrared spectroscopy of nails of nasopharyngeal carcinoma patients. Spectroscopy and Spectroscopy Analysis, 2004, 24(12): 1543-1545.
［4］Wei H, Jin S Y, Chen K, et al. Comparative observation of nail image and trace elements in patients with malignant tumors. Guangdong Trace Elements Science, 2001, 8(1): 32-34.
［5］Chen J J. Research on gesture recognition algorithms based on harris corner detection and optical flow. Jilin: Jilin University, 2017: 61.
［6］Zheng J. Image segmentation for nail diagnosis in traditional chinese medicine. Xi'an: Xi'an University of Electronic Science and Technology, 2014: 60.
［7］Zhao Y J, Yao J W, Zhao Y M, et al. Digital image color space conversion and application based on matlab. Electronic Technology and Software Engineering, 2015, (5): 113.
［8］Wang J X, Zhang Y H, Wang Z W, et al. A single image defogging algorithm based on HSI color space. Computer Application, 2014, 34(10): 2990-2995.
［9］Liu Q，Shi N. Farmland image segmentation method based on Lab and YUV color space. Foreign Electronic Measurement Technology, 2015, 34(4): 39-41.
［10］Shi D C, Ni K. Background modeling and gesture shadow elimination based on YCbCr color space. China Optics, 2015, 8(4): 589-595.
［11］Zhang X M, Zhu Y B, Wu N Q, et al. Correlation analysis between obesity diagnosed by different indexes and constitution of traditional Chinese medicine. Journal of Traditional Chinese Medicine, 2015, 56(3): 212-215.
［12］Dong X Y. Matched t-test and group t-test optimization. Journal of Mathematical Medicine, 2010, 23(1): 11-14.
［13］Wang P, Li R J, Xu H Y. Forecast of peony flowering period based on multivariate regression. Agricultural Network Information, 2008, (3): 139-142.
基于颜色空间的尿毒症诊断研究
王学民1， 邵 娜1， 王瑞云1， 孙莹莹1， 于志峰2， 姜智浩2， 周 鹏1
（1. 天津大学 精密仪器与光电子工程学院， 天津 300072； 2. 天津中医药大学 中医工程学院， 天津 300193）
摘 要：由于传统甲诊易受到外界客观因素以及医生主观因素的影响， 提出了一套甲象客观采集与信息分析相结合的中医甲诊系统用于尿毒症患者甲象客观化研究。采集并分割了15例尿毒症患者甲象正面照和侧面照， 探究维持性血液透析前后甲色变化以及血红蛋白值与各色彩空间数值之间的关系等问题。利用相关分析和多元回归分析等统计学手段， 对尿毒症患者血红蛋白值与维持性血液透析前后色彩空间值的关系进行了分析。实验结果表明， 尿毒症患者血红蛋白值与多个色彩通道数值有一定的相关性， 透析前后多个通道有显著变化， 并建立了相关的多元回归方程。
关键词： 指甲分类； 指甲颜色； 尿毒症； 相关分析； 配对t检验； 多元回归
引用格式： WANG Xue-min, SHAO Na, WANG Rui-yun, et al. Diagnosis of uremia patients based on color space. Journal of Measurement Science and Instrumentation, 2020, 11（1）： 38-44. ［doi： 10.3969／j.issn.1674-8042.2020.01.005］
[full text view]
