Functional connectome automatically differentiates multiple system atrophy (parkinsonian type) from idiopathic Parkinson's disease at early stages

被引:13
作者
Chen, Boyu [1 ]
Cui, Wenzhuo [1 ]
Wang, Shanshan [1 ]
Sun, Anlan [2 ]
Yu, Hongmei [3 ]
Liu, Yu [1 ]
He, Jiachuan [1 ]
Fan, Guoguang [1 ]
机构
[1] China Med Univ, Dept Radiol, Hosp 1, 155 Nanjing North St, Shenyang 110001, Liaoning, Peoples R China
[2] Yizhun Med AI Co Ltd, Beijing, Peoples R China
[3] China Med Univ, Dept Neurol, Hosp 1, Shenyang, Liaoning, Peoples R China
基金
中国国家自然科学基金;
关键词
functional connectivity; graph theory; machine learning; multiple system atrophy; Parkinson's disease; resting-state functional magnetic resonance imaging; DIAGNOSIS; CONNECTIVITY; ORGANIZATION; MODULATION;
D O I
10.1002/hbm.26201
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Differentiating the parkinsonian variant of multiple system atrophy (MSA-P) from idiopathic Parkinson's disease (IPD) is challenging, especially in the early stages. This study aimed to investigate differences and similarities in the brain functional connectomes of IPD and MSA-P patients and use machine learning methods to explore the diagnostic utility of these features. Resting-state fMRI data were acquired from 88 healthy controls, 76 MSA-P patients, and 53 IPD patients using a 3.0 T scanner. The whole-brain functional connectome was constructed by thresholding the Pearson correlation matrices of 116 regions, and topological properties were evaluated through graph theory approaches. Connectome measurements were used as features in machine learning models (random forest [RF]/logistic regression [LR]/support vector machine) to distinguish IPD and MSA-P patients. Regarding graph metrics, early IPD and MSA-P patients shared network topological properties. Both patient groups showed functional connectivity disruptions within the cerebellum-basal ganglia-cortical network, but these disconnections were mainly in the cortico-thalamo-cerebellar circuits in MSA-P patients and the basal ganglia-thalamo-cortical circuits in IPD patients. Among the connectome parameters, t tests combined with the RF method identified 15 features, from which the LR classifier achieved the best diagnostic performance on the validation set (accuracy = 92.31%, sensitivity = 90.91%, specificity = 93.33%, area under the receiver operating characteristic curve = 0.89). MSA-P and IPD patients show similar whole-brain network topological alterations. MSA-P primarily affects cerebellar nodes, and IPD primarily affects basal ganglia nodes; both conditions disrupt the cerebellum-basal ganglia-cortical network. Moreover, functional connectome parameters showed outstanding value in the differential diagnosis of early MSA-P and IPD.
引用
收藏
页码:2176 / 2190
页数:15
相关论文
共 51 条
[1]   Cerebellar resting-state functional connectivity in Parkinson's disease and multiple system atrophy: Characterization of abnormalities and potential for differential diagnosis at the single-patient level [J].
Baggio, Hugo C. ;
Abos, Alexandra ;
Segura, Barbara ;
Campabadal, Anna ;
Uribe, Carme ;
Giraldo, Darly M. ;
Perez-Soriano, Alexandra ;
Munoz, Esteban ;
Compta, Yaroslau ;
Junque, Carme ;
Jose Marti, Maria .
NEUROIMAGE-CLINICAL, 2019, 22
[2]   Graph Theory Analysis Reveals Resting-State Compensatory Mechanisms in Healthy Aging and Prodromal Alzheimer's Disease [J].
Behfar, Qumars ;
Behfar, Stefan Kambiz ;
von Reutern, Boris ;
Richter, Nils ;
Dronse, Julian ;
Fassbender, Ronja ;
Fink, Gereon R. ;
Onur, Oezguer A. .
FRONTIERS IN AGING NEUROSCIENCE, 2020, 12 :1-13
[3]  
Bhidayasiri R., 2012, MOVEMENT DISORDERS V, P4, DOI DOI 10.1007/978-1-60327-426-5_2
[4]   The basal ganglia and the cerebellum: nodes in an integrated network [J].
Bostan, Andreea C. ;
Strick, Peter L. .
NATURE REVIEWS NEUROSCIENCE, 2018, 19 (06) :338-350
[5]  
Bostan Andreea C, 2018, Prog Neurol Surg, V33, P50, DOI 10.1159/000480748
[6]   The basal ganglia communicate with the cerebellum [J].
Bostan, Andreea C. ;
Dum, Richard P. ;
Strick, Peter L. .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2010, 107 (18) :8452-8456
[7]   Staging of brain pathology related to sporadic Parkinson's disease [J].
Braak, H ;
Del Tredici, K ;
Rüb, U ;
de Vos, RAI ;
Steur, ENHJ ;
Braak, E .
NEUROBIOLOGY OF AGING, 2003, 24 (02) :197-211
[8]   Consensus Paper: Towards a Systems-Level View of Cerebellar Function: the Interplay Between Cerebellum, Basal Ganglia, and Cortex [J].
Caligiore, Daniele ;
Pezzulo, Giovanni ;
Baldassarre, Gianluca ;
Bostan, Andreea C. ;
Strick, Peter L. ;
Doya, Kenji ;
Helmich, Rick C. ;
Dirkx, Michiel ;
Houk, James ;
Jorntell, Henrik ;
Lago-Rodriguez, Angel ;
Galea, Joseph M. ;
Miall, R. Chris ;
Popa, Traian ;
Kishore, Asha ;
Verschure, Paul F. M. J. ;
Zucca, Riccardo ;
Herreros, Ivan .
CEREBELLUM, 2017, 16 (01) :203-229
[9]   A Radiomics Approach to Predicting Parkinson's Disease by Incorporating Whole-Brain Functional Activity and Gray Matter Structure [J].
Cao, Xuan ;
Wang, Xiao ;
Xue, Chen ;
Zhang, Shaojun ;
Huang, Qingling ;
Liu, Weiguo .
FRONTIERS IN NEUROSCIENCE, 2020, 14
[10]   Usefulness of diffusion-tensor MRI in the diagnosis of Parkinson variant of multiple system atrophy and Parkinson's disease: a valuable tool to differentiate between them? [J].
Chen, B. ;
Fan, G. ;
Sun, W. ;
Shang, X. ;
Shi, S. ;
Wang, S. ;
Lv, G. ;
Wu, C. .
CLINICAL RADIOLOGY, 2017, 72 (07) :610.e9-610.e15