Automatic classification of early Parkinson's disease with multi-modal MR imaging.
Automatic classification of early Parkinson's disease with multi-modal MR imaging.
复制标题
DOI：
10.1371/journal.pone.0047714
复制
发表时间：
2012
期刊：
影响因子：
3.7
通讯作者：
Zhang M
中科院分区：
文献类型：
--
作者：
Long D;Wang J;Xuan M;Gu Q;Xu X;Kong D;Zhang M
近年来，神经影像学已越来越多地被用作诊断帕金森病（PD）的客观方法。大多数以前的研究是基于侵入性成像模式或单一的模式，这不是一个理想的诊断工具。在这项研究中，我们开发了一种非侵入性的技术，旨在用于诊断早期PD通过整合各种模式的优势。19名早期PD患者和27名正常志愿者参加了这项研究。对于每一个主题，我们收集了静息态功能磁共振成像（rsfMRI）和结构图像。对于rsfMRI图像，我们提取了三个不同水平的特征：ALFF（低频波动幅度），ReHo（区域均匀性）和RFCS（区域功能连接强度）。对于结构图像，我们从灰质（GM）、白色物质（WM）和脑脊液（CSF）中提取体积特征。使用双样本t检验进行特征选择，然后将剩余特征融合用于分类。最后，从支持向量机训练中识别出早期PD患者和正常对照受试者的分类器。分类器的性能进行了评估，使用留一交叉验证方法。用本文提出的方法对数据集进行分类，获得了较好的结果（准确率= 86.96%，敏感性= 78.95%，特异性= 92.59%）。 该方法通过整合来自各种成像模式的信息，展示了有前途的诊断性能，并且它显示出改善PD的临床诊断和治疗的潜力。
In recent years, neuroimaging has been increasingly used as an objective method for the diagnosis of Parkinson's disease (PD). Most previous studies were based on invasive imaging modalities or on a single modality which was not an ideal diagnostic tool. In this study, we developed a non-invasive technology intended for use in the diagnosis of early PD by integrating the advantages of various modals. Nineteen early PD patients and twenty-seven normal volunteers participated in this study. For each subject, we collected resting-state functional magnetic resonance imaging (rsfMRI) and structural images. For the rsfMRI images, we extracted the characteristics at three different levels: ALFF (amplitude of low-frequency fluctuations), ReHo (regional homogeneity) and RFCS (regional functional connectivity strength). For the structural images, we extracted the volume characteristics from the gray matter (GM), the white matter (WM) and the cerebrospinal fluid (CSF). A two-sample t-test was used for the feature selection, and then the remaining features were fused for classification. Finally a classifier for early PD patients and normal control subjects was identified from support vector machine training. The performance of the classifier was evaluated using the leave-one-out cross-validation method. Using the proposed methods to classify the data set, good results (accuracy = 86.96%, sensitivity = 78.95%, specificity = 92.59%) were obtained. This method demonstrates a promising diagnosis performance by the integration of information from a variety of imaging modalities, and it shows potential for improving the clinical diagnosis and treatment of PD.
登录
查看更多内容
DOI：
10.1073/pnas.0504136102
发表时间：
2005-07-05
影响因子：
11.1
作者：
Fox, MD;Snyder, AZ;Raichle, ME
通讯作者：
Raichle, ME
影响因子：
9.9
作者：
Kloeppel, S.;Chu, C.;Frackowiak, R. S. J.
通讯作者：
Frackowiak, R. S. J.
影响因子：
11
作者：
HUGHES, AJ;DANIEL, SE;LEES, AJ
通讯作者：
LEES, AJ
影响因子：
14.5
作者：
Catalan, MJ;Ishii, K;Hallett, M
通讯作者：
Hallett, M
影响因子：
3.5
作者：
Acton, Paul D.;Newberg, Andrew
通讯作者：
Newberg, Andrew