Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, the Netherlands; Data Science Department, Software Competence Center Hagenberg, Hagenberg, Austria.
Department of Neurology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands.
Comput Methods Programs Biomed. 2022 Oct;225:107042. doi: 10.1016/j.cmpb.2022.107042. Epub 2022 Jul 28.
F-fluorodeoxyglucose (FDG) positron emission tomography (PET) combined with principal component analysis (PCA) has been applied to identify disease-related brain patterns in neurodegenerative disorders such as Parkinson's disease (PD), Dementia with Lewy Bodies (DLB) and Alzheimer's disease (AD). These patterns are used to quantify functional brain changes at the single subject level. This is especially relevant in determining disease progression in idiopathic REM sleep behavior disorder (iRBD), a prodromal stage of PD and DLB. However, the PCA method is limited in discriminating between neurodegenerative conditions. More advanced machine learning algorithms may provide a solution. In this study, we apply Generalized Matrix Learning Vector Quantization (GMLVQ) to FDG-PET scans of healthy controls, and patients with AD, PD and DLB. Scans of iRBD patients, scanned twice with an approximate 4 year interval, were projected into GMLVQ space to visualize their trajectory.
We applied a combination of SSM/PCA and GMLVQ as a classifier on FDG-PET data of healthy controls, AD, DLB, and PD patients. We determined the diagnostic performance by performing a ten times repeated ten fold cross validation. We analyzed the validity of the classification system by inspecting the GMLVQ space. First by the projection of the patients into this space. Second by representing the axis, that span this decision space, into a voxel map. Furthermore, we projected a cohort of RBD patients, whom have been scanned twice (approximately 4 years apart), into the same decision space and visualized their trajectories.
The GMLVQ prototypes, relevance diagonal, and decision space voxel maps showed metabolic patterns that agree with previously identified disease-related brain patterns. The GMLVQ decision space showed a plausible quantification of FDG-PET data. Distance traveled by iRBD subjects through GMLVQ space per year (i.e. velocity) was correlated with the change in motor symptoms per year (Spearman's rho =0.62, P=0.004).
In this proof-of-concept study, we show that GMLVQ provides a classification of patients with neurodegenerative disorders, and may be useful in future studies investigating speed of progression in prodromal disease stages.
氟代脱氧葡萄糖（FDG）正电子发射断层扫描（PET）与主成分分析（PCA）相结合，已被应用于识别帕金森病（PD）、路易体痴呆（DLB）和阿尔茨海默病（AD）等神经退行性疾病相关的大脑模式。这些模式用于量化个体水平的功能脑变化。这在确定特发性 REM 睡眠行为障碍（iRBD）的疾病进展中尤为重要，iRBD 是 PD 和 DLB 的前驱阶段。然而，PCA 方法在区分神经退行性疾病方面存在局限性。更先进的机器学习算法可能是一种解决方案。在这项研究中，我们将广义矩阵学习向量量化（GMLVQ）应用于健康对照者、AD、PD 和 DLB 患者的 FDG-PET 扫描。我们将 iRBD 患者的扫描结果（两次扫描，间隔约 4 年）投影到 GMLVQ 空间，以可视化其轨迹。
我们将 SSM/PCA 和 GMLVQ 的组合应用于健康对照者、AD、DLB 和 PD 患者的 FDG-PET 数据，作为分类器。我们通过进行十次重复十折交叉验证来确定诊断性能。我们通过检查 GMLVQ 空间来分析分类系统的有效性。首先，通过将患者投影到该空间中。其次，通过将跨越此决策空间的轴表示为体素图。此外，我们将一组 RBD 患者（两次扫描，间隔约 4 年）投影到相同的决策空间，并可视化其轨迹。
GMLVQ 原型、相关对角和决策空间体素图显示了与先前确定的疾病相关大脑模式一致的代谢模式。GMLVQ 决策空间对 FDG-PET 数据进行了合理的量化。iRBD 患者通过 GMLVQ 空间的年移动距离（即速度）与每年运动症状的变化相关（Spearman 相关系数=0.62，P=0.004）。
在这项概念验证研究中，我们表明 GMLVQ 可对神经退行性疾病患者进行分类，并且可能对研究前驱期疾病进展速度的未来研究有用。
