| Cite this article: |
| QIN Mengting,CUI Weiliang,REN Xiaoying,LI Huifen,DONG Yuning,SANG Mengjiao,WANG Bing,LIN Yongqiang.Hyperspectral Imaging for Rapid In-Situ Quantification of Multi-index Components in Salvia miltiorrhiza Slices[J].Journal Of Pharmaceutical Research,2026,45(2):163-169[Click to copy] |
|
| |
|
|
| This article has been viewed: 2829times Download 877次 |
 Scan with your phone! |
| 基于高光谱成像的丹参饮片多指标成分原位快速定量方法 |
| 秦梦廷1,2,崔伟亮2,3,任小英1,2,李慧芬3,董钰宁1,2,桑梦娇4,汪冰2,3,林永强1,5 |
|
|
| (1.天津中医药大学,天津 301617;2.山东省食品药品检验研究院,中药标准创新与质量评价山东省工程研究中心,中药配方颗粒共性技术山东省工程研究中心,产业技术公共服务平台,山东 济南 250101;3.山东中医药大学,山东 济南 250355;4.山东大学,山东 济南 250012;5.中国食品药品检定研究院,药品监管科学全国重点实验室,北京 100061) |
|
| 摘要: |
| 目的 本研究旨在构建一种基于高光谱成像技术的丹参饮片5种指标成分原位快速定量分析方法,并深入探究不同波段范围及特征选择策略对偏最小二乘回归(PLSR)模型预测性能的影响。方法 采集115批次丹参饮片在可见近红外和近红外波段的高光谱图像数据,并测定丹酚酸B、丹参酮Ⅰ、隐丹参酮、丹参酮ⅡA及总丹参酮的含量。基于高光谱分析平台中的分类算法,分别提取VNIR、NIR及融合全波段的光谱数据,采用多元散射校正、标准正态变换等6种方法对光谱进行预处理,再结合竞争性自适应重加权算法(CARS)、连续投影算法(SPA)和无信息变量消除法(UVE)进行特征筛选,构建PLSR预测模型,并通过验证集相关系数、验证集均方根误差和剩余预测偏差综合评估模型性能。结果 基于全波段光谱并结合CARS特征选择所建立的PLSR模型预测性能最优,5种指标的RV值均达到0.92~0.96,RPD值均高于3.5,展现出更强的模型稳健性和预测可靠性。结论 全波段高光谱数据融合CARS特征选择策略可实现丹参饮片5种指标成分的快速、无损、精准定量分析,可为中药饮片智能化质量控制体系的建立和现场快速检测提供理论基础和科学支撑。 |
| 关键词: 高光谱成像 丹参 指标成分 预测模型 原位定量 |
| DOI:10.13506/j.cnki.jpr.2026.02.007 |
| 基金项目:国家重点研发计划-中医药现代化专项(No.2023YFC3504102);药品监管科学全国重点实验室课题(No.2025SKLDRS0338);中药监管科学研究项目(No.ZYJGKX202410);山东省自然科学基金项目(No.ZR2020MH374) |
|
Publication Date:February 25, 2026
|
|
| Hyperspectral Imaging for Rapid In-Situ Quantification of Multi-index Components in Salvia miltiorrhiza Slices |
| QIN Mengting1,2,CUI Weiliang2,3,REN Xiaoying1,2,LI Huifen3,DONG Yuning1,2,SANG Mengjiao4,WANG Bing2,3,LIN Yongqiang1,5 |
| (1.Tianjin University of Traditional Chinese Medicine, Tianjin 301617, China; 2.National Institutes for Food and Drug Control,State Key Laboratory of Drug Regulatory Science, Beijing 100061, China;3.NMPA Key Laboratory for Quality Evaluation of Gelatin Products, Shandong Engineering Research Center for Traditional Chinese Medicine Standard Innovation and Quality Evaluation, Shandong Engineering Research Center of Generic Technologies for Traditional Chinese Medicine Formula Granules, Shandong Provincial Institute for Food and Drug Control, Jinan 250101, China; 4.Shandong University of Traditional Chinese Medicine, Jinan 250355, China; 5.Shandong University, Jinan 200512, China) |
| Abstract: |
| Objective This study aimed to develop an in-situ and rapid quantitative analytical method for five key components of Salvia miltiorrhiza slices using hyperspectral imaging (HSI), and to systematically evaluate the impact of different spectral band selections and feature wavelength screening strategies on the performance of partial least squares regression (PLSR) models.Methods Hyperspectral images in the visible-near-infrared and near-infrared bands were acquired from 115 batches of Salvia miltiorrhiza slices. The contents of five key components — salvianolic acid B, tanshinone I, cryptotanshinone, tanshinone IIA, and total tanshinones — were quantified. Spectral data from the VNIR, NIR, and fused full-band ranges were extracted. These spectra were preprocessed using six methods, including multiplicative scatter correction and standard normal variate transformation. Feature wavelengths were then selected by competitive adaptive reweighted sampling, successive projections algorithm, and uninformative variable elimination. Finally, partial least squares regression models were developed and evaluated based on the correlation coefficient, root mean square error of the validation set, and residual predictive deviation.Results The partial least squares regression model, built using full‑band spectra and refined by competitive adaptive reweighted sampling, achieved optimal predictive performance. For all five analytes, the validation correlation coefficients (Rv) ranged from 0.92 to 0.96, and the residual predictive deviation values exceeded 3.5, demonstrating enhanced model robustness and reliable predictive capability. Conclusion The integration of full-band hyperspectral data with CARS feature selection enables rapid, nondestructive, and accurate quantification of five key components in Salvia miltiorrhiza slices. This approach provides a scientific basis and technical support for intelligent quality control and rapid on-site testing of traditional Chinese medicinal slices. |
| Key words: Hyperspectral imaging Salvia miltiorrhiza Marker compounds Prediction model In-situ quantification |
|
|
|
|
|