Kaartinen J, Mierisová S, Oja J M, Usenius J P, Kauppinen R A, Hiltunen Y
Pehr Brahe Laboratory, The Raahe Institute of Computer Engineering, Raahe, Finland.
J Magn Reson. 1998 Sep;134(1):176-9. doi: 10.1006/jmre.1998.1477.
A real-time automated way of quantifying metabolites from in vivo NMR spectra using an artificial neural network (ANN) analysis is presented. The spectral training and test sets for ANN containing peaks at the chemical shift ranges resembling long echo time proton NMR spectra from human brain were simulated. The performance of the ANN constructed was compared with an established lineshape fitting (LF) analysis using both simulated and experimental spectral data as inputs. The correspondence between the ANN and LF analyses showed correlation coefficients of order of 0.915-0.997 for spectra with large variations in both signal-to-noise and peak areas. Water suppressed 1H NMR spectra from 24 healthy subjects were collected and choline-containing compounds (Cho), total creatine (Cr), and N-acetyl aspartate (NAA) were quantified with both methods. The ANN quantified these spectra with an accuracy similar to LF analysis (correlation coefficients of 0.915-0.951). These results show that LF and ANN are equally good quantifiers; however, the ANN analyses are more easily automated than LF analyses.
本文提出了一种使用人工神经网络（ANN）分析对体内核磁共振波谱中的代谢物进行定量的实时自动化方法。模拟了人工神经网络的光谱训练集和测试集，其包含的峰的化学位移范围类似于来自人脑的长回波时间质子核磁共振波谱。将构建的人工神经网络的性能与使用模拟和实验光谱数据作为输入的既定线形拟合（LF）分析进行比较。对于信噪比和峰面积变化较大的光谱，人工神经网络分析与线形拟合分析之间的对应关系显示相关系数在0.915 - 0.997之间。收集了24名健康受试者的水抑制1H核磁共振波谱，并使用这两种方法对含胆碱化合物（Cho）、总肌酸（Cr）和N - 乙酰天门冬氨酸（NAA）进行定量。人工神经网络对这些光谱的定量精度与线形拟合分析相似（相关系数为0.915 - 0.951）。这些结果表明，线形拟合分析和人工神经网络分析在定量方面同样出色；然而，人工神经网络分析比线形拟合分析更容易实现自动化。
