Artificial neural network classifier for the diagnosis of Parkinson's disease using [99mTc] TRODAT-1 and SPECT
Artificial neural network classifier for the diagnosis of Parkinson's disease using [99mTc] TRODAT-1 and SPECT
复制标题
DOI：
10.1088/0031-9155/51/12/004
复制
发表时间：
2006-06-21
影响因子：
3.5
通讯作者：
Newberg, Andrew
中科院分区：
文献类型：
--
作者：
Acton, Paul D.;Newberg, Andrew
使用正电子发射断层扫描 (PET) 或单光子发射断层扫描 (SPECT) 对多巴胺能神经递质系统进行成像是诊断帕金森病 (PD) 的有力工具。先前的研究表明，人类观察者的诊断准确性与 SPECT 成像数据的传统 ROI 分析相似。因此，人们假设人工神经网络（ANN）可以模仿人类观察者的模式识别技能，可以提供类似的结果。使用多巴胺转运蛋白示踪剂 [Tc-99m] TRODAT-1 和 SPECT 对一组 PD 患者和正常健康对照受试者进行了研究。样本由 81 名患者（平均年龄 +/- SD：63.4 +/- 10.4 岁；年龄范围：39.0 - 84.2 岁）和 94 名健康对照（平均年龄 +/- SD：61.8 +/- 11.0 岁；年龄范围：40.9 - 83.3 岁）组成。对图像进行处理以提取纹状体，并将纹状体像素值用作三层人工神经网络的输入。在“留一”程序中，使用同一组数据来训练和测试人工神经网络。 ANN 的诊断准确性高于之前应用于相同数据的任何分析方法（总准确度为 94.4%，特异性为 97.5%，灵敏度为 91.4%）。然而，应该强调的是，与人工神经网络的所有应用一样，很难准确解释网络检测到图像中的哪些触发因素。
Imaging the dopaminergic neurotransmitter system with positron emission tomography (PET) or single photon emission tomography (SPECT) is a powerful tool for the diagnosis of Parkinson's disease (PD). Previous studies have indicated that human observers have a diagnostic accuracy similar to conventional ROI analysis of SPECT imaging data. Consequently, it has been hypothesized that an artificial neural network (ANN), which can mimic the pattern recognition skills of human observers, may provide similar results. A set of patients with PD, and normal healthy control subjects, were studied using the dopamine transporter tracer [Tc-99m] TRODAT-1 and SPECT. The sample was comprised of 81 patients (mean age +/- SD: 63.4 +/- 10.4 years; age range: 39.0 - 84.2 years) and 94 healthy controls (mean age +/- SD: 61.8 +/- 11.0 years; age range: 40.9 - 83.3 years). The images were processed to extract the striatum and the striatal pixel values were used as inputs to a three-layer ANN. The same set of data was used to both train and test the ANN, in a 'leave one out' procedure. The diagnostic accuracy of the ANN was higher than any previous analysis method applied to the same data (94.4% total accuracy, 97.5% specificity and 91.4% sensitivity). However, it should be stressed that, as with all applications of an ANN, it was difficult to interpret precisely what triggers in the images were being detected by the network.