Symbiosis Center for Medical Image Analysis and Symbiosis Institute of Technology, Symbiosis International University, Lavale, Mulshi, Pune, Maharashtra, 412115, India.
Department of Clinical Neurosciences and Neurology, National Institute of Mental Health & Neurosciences, Hosur Road, Bangalore, Karnataka, 560029, India.
Eur Radiol. 2021 Nov;31(11):8218-8227. doi: 10.1007/s00330-021-07979-7. Epub 2021 May 4.
This study aimed to explore the feasibility of radiomics features extracted from T1-weighted MRI images to differentiate Parkinson's disease (PD) from atypical parkinsonian syndromes (APS).
Radiomics features were computed from T1 images of 65 patients with PD, 61 patients with APS (31: progressive supranuclear palsy and 30: multiple system atrophy), and 75 healthy controls (HC). These features were extracted from 19 regions of interest primarily from subcortical structures, cerebellum, and brainstem. Separate random forest classifiers were applied to classify different groups based on a reduced set of most important radiomics features for each classification as determined by the random forest-based recursive feature elimination by cross-validation method.
The PD vs HC classifier illustrated an accuracy of 70%, while the PD vs APS classifier demonstrated a superior test accuracy of 92%. Moreover, a 3-way PD/MSA/PSP classifier performed with 96% accuracy. While first-order and texture-based differences like Gray Level Co-occurrence Matrix (GLCM) and Gray Level Difference Matrix for the substantia nigra pars compacta and thalamus were highly discriminative for PD vs HC, textural features mainly GLCM of the ventral diencephalon were highlighted for APS vs HC, and features extracted from the ventral diencephalon and nucleus accumbens were highlighted for the classification of PD and APS.
This study establishes the utility of radiomics to differentiate PD from APS using routine T1-weighted images. This may aid in the clinical diagnosis of PD and APS which may often be indistinguishable in early stages of disease.
• Radiomics features were extracted from T1-weighted MRI images. • Parkinson's disease and atypical parkinsonian syndromes were classified at an accuracy of 92%. • This study establishes the utility of radiomics to differentiate Parkinson's disease and atypical parkinsonian syndromes using routine T1-weighted images.
本研究旨在探讨从 T1 加权 MRI 图像中提取的影像组学特征区分帕金森病（PD）与非典型帕金森综合征（APS）的可行性。
从 65 例 PD 患者、61 例 APS（31 例进行性核上性麻痹和 30 例多系统萎缩）患者和 75 例健康对照者（HC）的 T1 图像中计算影像组学特征。这些特征主要从皮质下结构、小脑和脑干的 19 个感兴趣区域中提取。基于基于随机森林的递归特征消除交叉验证方法，应用单独的随机森林分类器根据每个分类的最重要影像组学特征的减少集来对不同组进行分类。
PD 与 HC 分类器的准确率为 70%，而 PD 与 APS 分类器的测试准确率更高，为 92%。此外，PD/MSA/PSP 三分类器的准确率为 96%。虽然一阶和基于纹理的差异，如用于黑质致密部和丘脑的灰度共生矩阵（GLCM）和灰度差矩阵，对 PD 与 HC 具有高度的鉴别力，但 APS 与 HC 的鉴别力主要基于腹侧间脑的纹理特征，主要是 GLCM，而 PD 和 APS 的分类则突出了腹侧间脑和伏隔核提取的特征。
本研究确立了使用常规 T1 加权图像区分 PD 与 APS 的影像组学的实用性。这可能有助于 PD 和 APS 的临床诊断，因为在疾病的早期阶段，它们可能经常无法区分。
从 T1 加权 MRI 图像中提取影像组学特征。
帕金森病和非典型帕金森综合征的分类准确率为 92%。
本研究确立了使用常规 T1 加权图像区分帕金森病和非典型帕金森综合征的影像组学的实用性。
