Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science, Xi'an Jiaotong University, Xi'an 710049, China; Innovation Laboratory of Terahertz Biophysics, National Innovation Institute of Defense Technology, Beijing 100071, China.
Innovation Laboratory of Terahertz Biophysics, National Innovation Institute of Defense Technology, Beijing 100071, China.
Spectrochim Acta A Mol Biomol Spectrosc. 2021 Nov 5;260:119946. doi: 10.1016/j.saa.2021.119946. Epub 2021 May 11.
The World Health Organization (WHO) grade diagnosis of cancer is essential for surgical outcomes and patient treatment. Traditional pathological grading diagnosis depends on dyes or other histological approaches, and the result interpretation highly relies on the pathologists, making the process time-consuming (>60 min, including the steps of dewaxing to water and H&E staining), resource-wasting, and labor-intensive. In the present study, we report an alternative workflow that combines the Fourier transform infrared (FTIR) microscopy and artificial neural network (ANN) to diagnose the grade of human glioma in a way that is faster (~20 min, including the processes of sample dewaxing, spectra acquisition and analysis), accurate (the prediction accuracy, specificity and sensitivity can reach above 99%), and without reagent. Moreover, this method is much superior to the common classification method of principal component analysis-linear discriminate analysis (PCA-LDA) (the prediction accuracy, specificity and sensitivity are only 87%, 89% and 86%, respectively). The ANN mainly learned the characteristic region of 800-1800 cm to classify the major histopathologic classes of human glioma. These results demonstrate that the grade diagnosis of human glioma by FTIR microscopy plus ANN can be streamlined, and could serve as a complementary pathway that is independent of the traditional pathology laboratory.
世界卫生组织（WHO）的癌症分级诊断对手术结果和患者治疗至关重要。传统的病理分级诊断依赖于染料或其他组织学方法，结果解释高度依赖病理学家，因此这个过程既耗时（>60 分钟，包括脱蜡到水和 H&E 染色的步骤），又浪费资源，且劳动强度大。在本研究中，我们报告了一种替代工作流程，该流程将傅里叶变换红外（FTIR）显微镜和人工神经网络（ANN）结合起来，以更快的速度（~20 分钟，包括样品脱蜡、光谱采集和分析过程）、更准确的方式（预测准确率、特异性和灵敏度均可达到 99%以上）和无需试剂的方式来诊断人类脑胶质瘤的分级。此外，这种方法明显优于常见的主成分分析-线性判别分析（PCA-LDA）分类方法（预测准确率、特异性和灵敏度分别仅为 87%、89%和 86%）。ANN 主要学习 800-1800cm 的特征区域，以对人类脑胶质瘤的主要组织病理学类型进行分类。这些结果表明，FTIR 显微镜加 ANN 对人类脑胶质瘤的分级诊断可以得到简化，并可作为一种独立于传统病理实验室的补充途径。
