基于X射线吸收谱的不同生物组织的辨识

Biological Tissue Recognition Based on X-Ray Absorption Spectral Detection

为了验证X射线吸收光谱法对生物组织的辨识能力,选取猪的心脏、肝、肾、胃、瘦肉以及肥肉作为实验样本,以55 k V的电压激发X射线管,利用X射线探测器获取这6类生物组织样本的X射线吸收光谱.将采集到的光谱数据分为测试集与训练集,利用主成分分析法提取光谱主成分,以训练集为输入建立径向基函数(RBF)神经网络分类预测模型,对测试集样本进行分类预测.通过交叉验证法对所有样本进行辨识的识别正确率达到90.22%.实验结果表明,X射线光谱技术结合主成分分析法和RBF神经网络能够很好地用于猪的组织分类,对将X射线光谱技术应用于生物组织辨识具有重要的指导意义.

In order to verify the ability of X-ray absorption spectroscopy to recognize biological tissues,porcine heart,liver,kidney,stomach,lean meat and fat are selected as specimens. The X-ray absorption spectra of these specimens are obtained by X-ray detector at the excitation voltage of 55 kV. The collected spectra are divided into training set and test set,and principal component analysis is used to extract spectral principal component. Using the training set as input,a radial basis function（ RBF） neural network model is established to predict the samples of the test set. The recognition rate of all samples through cross-validation method reached 90. 22%. The experimental results show that X-ray spectral technique coupled with statistical analysis methods can be used for the classification of pig tissue,which is of great significance to the application of X-ray spectral technique in organism identification.