Maxwell R J, Martínez-Pérez I, Cerdán S, Cabañas M E, Arús C, Moreno A, Capdevila A, Ferrer E, Bartomeus F, Aparicio A, Conesa G, Roda J M, Carceller F, Pascual J M, Howells S L, Mazucco R, Griffiths J R
Arhus University Hospitals NMR Research Centre, Skejby Sygehus, Denmark.
Magn Reson Med. 1998 Jun;39(6):869-77. doi: 10.1002/mrm.1910390604.
Pattern recognition techniques (factor analysis and neural networks) were used to investigate and classify human brain tumors based on the 1H NMR spectra of chemically extracted biopsies (n = 118). After removing information from lactate (because of variable ischemia times), unsupervised learning suggested that the spectra separated naturally into two groups: meningiomas and other tumors. Principal component analysis reduced the dimensionality of the data. A back-propagation neural network using the first 30 principal components gave 85% correct classification of meningiomas and nonmeningiomas. Simplification by vector rotation gave vectors that could be assigned to various metabolites, making it possible to use or to reject their information for neural network classification. Using scores calculated from the four rotated vectors due to creatine and glutamine gave the best classification into meningiomas and nonmeningiomas (89% correct). Classification of gliomas (n = 47) gave 62% correct within one grade. Only inositol showed a significant correlation with glioma grade.
基于化学提取活检组织（n = 118）的氢核磁共振波谱，运用模式识别技术（因子分析和神经网络）对人脑肿瘤进行研究和分类。去除乳酸的信息（由于缺血时间可变）后，无监督学习表明波谱自然分为两组：脑膜瘤和其他肿瘤。主成分分析降低了数据的维度。使用前30个主成分的反向传播神经网络对脑膜瘤和非脑膜瘤的分类正确率为85%。通过向量旋转简化得到了可分配给各种代谢物的向量，从而能够使用或舍弃其信息用于神经网络分类。利用由肌酸和谷氨酰胺产生的四个旋转向量计算的得分，对脑膜瘤和非脑膜瘤的分类效果最佳（正确率89%）。对胶质瘤（n = 47）进行分级分类时，一级内的正确率为62%。只有肌醇与胶质瘤分级存在显著相关性。
