基于近红外高光谱成像的蛋白质饲料中抗生素菌丝体残留评价新方法

摘要：抗生素菌丝体残留物（（ AMR）含有抗生素残留物。如果牲畜摄入过量的AMR，可能会导致健康问题。针对目前近 红外-高分辨率成像中像素级掺杂浓度未知的问题，本文创新性地提出了一种新的光谱模拟方法用于蛋白质饲料中 AMR 的评价。以4种常见蛋白质饲料（（ 豆粕、酒糟、棉籽粕、核苷酸渣）和土霉素渣（（ OR）为研究对象。该方法的第一步是 使用线性混合模型（（LMM）模拟具有不同掺杂浓度的像素的光谱。在此基础上，结合基于全局PLS得分的局部PLS（（LPLS- S），建立了基于模拟像素光谱的像素级OR定量模型（解决了校正集含量为0%~ 100%时预测结果的非线性分布问题）。 最后利用该模型对高光谱图像中各像元的 OR 含量进行了定量预测。计算每个像素的平均值作为该样品的 OR 含量。该 方法的实施有效地克服了 PLS-DA 无法对 2%-20%掺杂样品中的 OR 进行定性鉴别的问题。与通过对感兴趣区域上的光 谱进行平均而建立的PLS模型相比，该方法利用了每个像素的精确信息，从而提高了掺假样品检测的准确性。结果表明， 模拟光谱法与LPLS-S相结合，为近红外-高分辨光谱法检测和分析非法饲料添加剂提供了一种新的方法。

关键词：蛋白饲料；土霉素残留；近红外高光谱成像；线性混合模型；定量检测。

期刊：Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy

DOI：https://doi.org/10.1016/j.saa.2024.124536

设备：GaiaSorter

A new spectral simulating method based on near-infrared hyperspectral imaging for evaluation of antibiotic mycelia residues in protein feeds

Abstract：Antibiotic mycelia residues (AMRs) contain antibiotic residues. If AMRs are ingested in excess by livestock, it may cause health problems. To address the current problem of unknown pixel-scale adulteration concentration in NIR-HSI, this paper innovatively proposes a new spectral simulation method for the evaluation of AMRs in protein feeds. Four common protein feeds (soybean meal (SM), distillers dried grains with solubles (DDGS), cottonseed meal (CM), and nucleotide residue (NR)) and oxytetracycline residue (OR) were selected as study materials. The first step of the method is to simulate the spectra of pixels with different adulteration concen trations using a linear mixing model (LMM). Then, a pixel-scale OR quantitative model was developed based on the simulated pixel spectra combined with local PLS based on global PLS scores (LPLS-S) (which solves the problem of nonlinear distribution of the prediction results due to the 0%-100% content of the correction set). Finally, the model was used to quantitatively predict the OR content of each pixel in hyperspectral image. The average value of each pixel was calculated as the OR content of that sample. The implementation of this method can effectively overcome the inability of PLS-DA to achieve qualitative identification of OR in 2%-20% adul terated samples. In compared to the PLS model built by averaging the spectra over the region of interest, this method utilizes the precise information of each pixel, thereby enhancing the accuracy of the detection of adulterated samples. The results demonstrate that the combination of the method of simulated spectroscopy and LPLS-S provides a novel method for the detection and analysis of illegal feed additives by NIR-HSI..

Keywords：Protein feeds, Oxytetracycline residues, Near-infrared hyperspectral imaging, Linear mixing model, Quantitative detection.