Department of Radiology and Hotchkiss Brain Institute, Faculty of Medicine, University of Calgary, 3330 Hospital Drive NW, AB T2N 4N1, Calgary, Canada.
Departments of Psychiatry, Clinical Neurosciences, and Community Health Sciences, and Hotchkiss Brain Institute, University of Calgary, Calgary, Canada.
Clin Neuroradiol. 2019 Dec;29(4):605-614. doi: 10.1007/s00062-018-0727-8. Epub 2018 Sep 14.
The overlapping symptoms of Parkinson's disease (PD) and progressive supranuclear palsy-Richardson's syndrome (PSP-RS) often make a correct clinical diagnosis difficult. The volume of subcortical brain structures derived from high-resolution T1-weighted magnetic resonance imaging (MRI) datasets is frequently used for individual level classification of PD and PSP-RS patients. The aim of this study was to evaluate the benefit of including additional morphological features beyond the simple regional volume, as well as clinical features, and morphological features of cortical structures for an automatic classification of PD and PSP-RS patients.
A total of 98 high-resolution T1-weighted MRI datasets from 76 PD patients, and 22 PSP-RS patients were available for this study. Using an atlas-based approach, the volume, surface area, and surface-area-to-volume ratio (SA:V) of 21 subcortical and 48 cortical brain regions were calculated and used as features for a support vector machine classification after application of a RELIEF feature selection method.
The comparison of the classification results suggests that including all three morphological parameters (volume, surface area and SA:V) can considerably improve classification accuracy compared to using volume or surface area alone. Likewise, including clinical patient features in addition to morphological parameters also considerably increases the classification accuracy. In contrast to this, integrating morphological features of other cortical structures did not lead to improved classification accuracy. Using this optimal set-up, an accuracy of 98% was achieved with only one falsely classified PD and one falsely classified PSP-RS patient.
The results of this study suggest that clinical features as well as more advanced morphological features should be used for future computer-aided diagnosis systems to differentiate PD and PSP-RS patients based on morphological parameters.
帕金森病（PD）和进行性核上性麻痹-理查森综合征（PSP-RS）的重叠症状常常使得正确的临床诊断变得困难。基于高分辨率 T1 加权磁共振成像（MRI）数据集的皮质下脑结构体积常用于 PD 和 PSP-RS 患者的个体水平分类。本研究旨在评估在简单的区域体积之外包含额外的形态特征，以及临床特征和皮质结构的形态特征，对 PD 和 PSP-RS 患者进行自动分类的益处。
本研究共纳入 76 例 PD 患者和 22 例 PSP-RS 患者的 98 例高分辨率 T1 加权 MRI 数据集。使用基于图谱的方法，计算了 21 个皮质下和 48 个皮质脑区的体积、表面积和表面积与体积比（SA:V），并应用 RELIEF 特征选择方法后作为支持向量机分类的特征。
分类结果的比较表明，与单独使用体积或表面积相比，包含所有三个形态参数（体积、表面积和 SA:V）可以显著提高分类准确性。同样，除了形态参数外，还包括临床患者特征也可以显著提高分类准确性。与此相反，整合其他皮质结构的形态特征并不能提高分类准确性。使用这种最佳设置，仅 1 例 PD 患者和 1 例 PSP-RS 患者被错误分类，准确率达到 98%。
本研究结果表明，临床特征以及更先进的形态特征应用于未来的计算机辅助诊断系统，以基于形态参数区分 PD 和 PSP-RS 患者。
