Please wait a minute...
 Home  About the Journal Editorial Board Aims & Scope Peer Review Policy Subscription Contact us
 
Early Edition  //  Current Issue  //  Open Special Issues  //  Archives  //  Most Read  //  Most Downloaded  //  Most Cited
Aging and disease    2020, Vol. 11 Issue (3) : 618-628     DOI: 10.14336/AD.2019.0617
Orginal Article |
T1-weighted MRI-driven Brain Age Estimation in Alzheimer’s Disease and Parkinson’s Disease
Beheshti Iman1,*, Mishra Shiwangi2, Sone Daichi1, Khanna Pritee2, Matsuda Hiroshi1
1Integrative Brain Imaging Center, National Center of Neurology and Psychiatry, Tokyo, Japan.
2PDPM Indian Institute of Information Technology, Design and Manufacturing, Jabalpur, India.
Download: PDF(961 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

Neuroimaging-driven brain age estimation has introduced a robust (reliable and heritable) biomarker for detecting and monitoring neurodegenerative diseases. Here, we computed and compared brain age in Alzheimer’s disease (AD) and Parkinson’s disease (PD) patients using an advanced machine learning procedure involving T1-weighted MRI scans and gray matter (GM) and white matter (WM) models. Brain age estimation frameworks were built using 839 healthy individuals and then the brain estimated age difference (Brain-EAD: chronological age subtracted from brain estimated age) was assessed in a large sample of PD patients (n = 160) and AD patients (n = 129), respectively. The mean Brain-EADs for GM were +9.29 ± 6.43 years for AD patients versus +1.50 ± 6.03 years for PD patients. For WM, the mean Brain-EADs were +8.85 ± 6.62 years for AD patients versus +2.47 ± 5.85 years for PD patients. In addition, PD patients showed a significantly higher WM Brain-EAD than GM Brain-EAD. In a direct comparison between PD and AD patients, we observed significantly higher Brain-EAD values in AD patients for both GM and WM. A comparison of the Brain-EAD between PD and AD patients revealed that AD patients may have a significantly “older-appearing” brain than PD patients.

Keywords brain age      T1-weighted MRI      estimation      Alzheimer's disease      Parkinson’s disease     
Corresponding Authors: Beheshti Iman   
About author:

These authors contributed equally to this work.

Just Accepted Date: 21 July 2019   Issue Date: 13 May 2020
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Beheshti Iman
Mishra Shiwangi
Sone Daichi
Khanna Pritee
Matsuda Hiroshi
Cite this article:   
Beheshti Iman,Mishra Shiwangi,Sone Daichi, et al. T1-weighted MRI-driven Brain Age Estimation in Alzheimer’s Disease and Parkinson’s Disease[J]. Aging and disease, 2020, 11(3): 618-628.
URL:  
http://www.aginganddisease.org/EN/10.14336/AD.2019.0617     OR
Training datasetTest dataset

DatasetIXIOASISADNIPPMIADNIPPMI
CategoryHCHCHCHCADPD
No of Subjects408103227101129160
Female/Male238/17078/25110/11737/6464/6564/96
Age (years)56.48±12.0767.81±12.8575.96±5.0460.24±10.0271.64±5.8164.53±6.98
MMSEn/an/an/an/a23.25±2.26n/a
CDRn/an/an/an/a0.75±0.31n/a
GDSn/an/an/an/an/a2.24±2.33
MoCAn/an/an/an/an/a26.91±2.40
MDS-UPDRS Totaln/an/an/an/an/a31.97±13.13
MDS-UPDRS Part In/an/an/an/an/a1.35±1.57
MDS-UPDRS Part I Patient questionnairen/an/an/an/an/a4.05±2.79
MDS-UPDRS Part II Patient questionnairen/an/an/an/an/a5.71±3.96
MDS-UPDRS Part IIIn/an/an/an/an/a20.85±8.72
S&En/an/an/an/an/a93.78±5.65
UPSITn/an/an/an/an/a21.01±8.19
SCOPA-AUTn/an/an/an/an/a9.61±5.68
SBR Left Caudaten/an/an/an/an/a1.88±0.60
SBR Right Caudaten/an/an/an/an/a1.87±0.58
SBR Left Putamenn/an/an/an/an/a0.77±0.31
SBR Right Putamenn/an/an/an/an/a0.79±0.31
Table 1  Characteristics of subjects in this study.
Figure 1.  The pipeline of the T1w MRI-driven brain age estimation framework used in this study.
Figure 2.  Chronological age versus estimated brain age in the training set (n = 839) through 10-fold cross-validation strategy. (A) GM model. (B) WM model. The identity line is illustrated with a dashed black line (y = x).
GMWM
MAE (years)4.384.85
RMSE (years)5.466.06
Correlation (r)0.920.91
Mean Brain-EAD [SD]0.01 [5.46]-0.05 [6.06]
Table 2  Performance of the proposed brain age framework in the training set.
Figure 3.  Comparison of Brain-EAD values between PD patients (blue spot) and AD patients (red spot) for the GM and WM models. The mean brain-EAD values of each group is illustrated with a solid black line. The reference line is illustrated with a dashed black line (y = 0).
Figure 4.  GM and WM Brain-EAD distributions for PD, and AD individuals.
Figure 5.  Chronological age versus estimated brain age among PD patients (blue spot, blue regression line) and AD patients (red spot, red regression line). (A) GM model. (B) WM model. The identity line is illustrated with a dashed black line (y = x).
Figure 6.  Brain-EAD values versus chronological age among PD patients (blue spot, blue regression line) and AD patients (red spot, red regression line). (A) GM model. (B) WM model. The reference line is illustrated with a dashed black line (y = 0).
Variablerp-value
MMSE-0.080.17
GDS0.040.31
Table 3  Partial correlation (r) of GM Brain-EAD with adjustment for age and sex among AD patients (n = 129)
Figure 7.  Partial correlations between Brain-EAD results and clinical parameters in the PD group. (A) MoCA, (B) MDS-UPDRS Part I, and (C) UPSIT - Total Score. Variables showing a significant correlation with Brain-EAD are shown.
Variablerp-valueVariablerp-value
Duration of disease-0.060.19S&E-0.120.05
MoCA-0.150.04UPSIT - Total Score-0.140.04
GDS-0.130.43SCOPA-AUT0.020.42
MDS-UPDRS Total0.060.23SBR-Left Caudate0.010.48
MDS-UPDRS Part I0.210.005SBR-Right Caudate-0.040.27
MDS-UPDRS Part I Patient Questionnaire0.020.42SBR-Left Putamen0.020.39
MDS-UPDRS Part II Patient Questionnaire-0.020.40SBR-Right Putamen-0.120.06
MDS-UPDRS Part III0.060.06
Table 4  Partial correlation (r) of WM Brain-EAD values with clinical parameters among PD patients with adjustment for age and sex (n = 160).
[1] DeKosky ST, Marek K (2003). Looking backward to move forward: early detection of neurodegenerative disorders. Science, 302:830-834.
[2] Stefanis L, Burke RE, Greene LA (1997). Apoptosis in neurodegenerative disorders. Curr Opin Neurol, 10:299-305.
[3] Tokuchi R, Hishikawa N, Sato K, Hatanaka N, Fukui Y, Takemoto M, et al. (2016). Differences between the behavioral and psychological symptoms of Alzheimer's disease and Parkinson's disease. J Neurol Sci, 369:278-282.
[4] Joki H, Higashiyama Y, Nakae Y, Kugimoto C, Doi H, Kimura K, et al. (2018). White matter hyperintensities on MRI in dementia with Lewy bodies, Parkinson's disease with dementia, and Alzheimer's disease. J Neurol Sci, 385:99-104.
[5] Giulioli C, Amieva H (2016). Epidemiology of cognitive aging in the oldest old. Rev Invest Clin, 68:33-39.
[6] Pan Y, Nicolazzo JA (2018). Impact of aging, Alzheimer's disease and Parkinson's disease on the blood-brain barrier transport of therapeutics. Adv Drug Deliv Rev, 135:62-74.
[7] Robertson D (2017). Proposed biochemistry of Parkinson’s and Alzheimer’s diseases. Med Hypotheses, 109:131-138.
[8] Spillantini MG, Goedert M (1998). Tau protein pathology in neurodegenerative diseases. Trends Neurosci, 21:428-433.
[9] Kalia LV, Lang AE (2016). Parkinson disease in 2015: evolving basic, pathological and clinical concepts in PD. Nat Rev Neurol, 12:65.
[10] Bekris LM, Mata IF, Zabetian CP (2010). The genetics of Parkinson disease. J Geriatr Psychiatry Neurol, 23:228-242.
[11] Adams JD, Klaidman LK, Odunze IN, Shen HC, Miller CA (1991). Alzheimer’s and Parkinson’s disease. Mol Chem Neuropathol, 14:213-226.
[12] Liu G, Bao X, Jiang Y, Liao M, Jiang Q, Feng R, et al. (2015). Identifying the association between Alzheimer’s disease and Parkinson’s disease using genome-wide association studies and protein-protein interaction network. Mol Neurobiol, 52:1629-1636.
[13] DeCarlo CA, Tuokko HA, Williams D, Dixon RA, MacDonald SW (2014). BioAge: toward a multi-determined, mechanistic account of cognitive aging. Ageing Res Rev, 18:95-105.
[14] Franke K, Ziegler G, Kloppel S, Gaser C, Alzheimer's Disease Neuroimaging I (2010). Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: exploring the influence of various parameters. Neuroimage, 50:883-892.
[15] Cole JH, Underwood J, Caan MW, De Francesco D, van Zoest RA, Leech R, et al. (2017). Increased brain-predicted aging in treated HIV disease. Neurology, 88:1349-1357.
[16] Cole JH, Poudel RPK, Tsagkrasoulis D, Caan MWA, Steves C, Spector TD, et al. (2017). Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker. Neuroimage, 163:115-124.
[17] Cole JH, Annus T, Wilson LR, Remtulla R, Hong YT, Fryer TD, et al. (2017). Brain-predicted age in Down syndrome is associated with beta amyloid deposition and cognitive decline. Neurobiol Aging, 56:41-49.
[18] Cole JH, Leech R, Sharp DJ, Initiative AsDN (2015). Prediction of brain age suggests accelerated atrophy after traumatic brain injury. Ann Neurol, 77:571-581.
[19] Franke K, Clarke GD, Dahnke R, Gaser C, Kuo AH, Li C, et al. (2017). Premature Brain Aging in Baboons Resulting from Moderate Fetal Undernutrition. Front Aging Neurosci, 9:92.
[20] Frankea K, Dahnke R, Clarke G, Kuo A, Li C, Nathanielsz P, et al. (2016). MRI based biomarker for brain aging in rodents and non-human primates. Int Workshop Pattern, IEEE. 1-4.
[21] Franke K, Luders E, May A, Wilke M, Gaser C (2012). Brain maturation: predicting individual BrainAGE in children and adolescents using structural MRI. Neuroimage, 63:1305-1312.
[22] Nenadić I, Dietzek M, Langbein K, Sauer H, Gaser C (2017). BrainAGE score indicates accelerated brain aging in schizophrenia, but not bipolar disorder. Psychiatry Res Neuroimaging, 266:86-89.
[23] Franke K, Gaser C, Manor B, Novak V (2013). Advanced BrainAGE in older adults with type 2 diabetes mellitus. Front Aging Neurosci, 5:90.
[24] Franke K, Ristow M, Gaser C, Alzheimer's Disease Neuroimaging I (2014). Gender-specific impact of personal health parameters on individual brain aging in cognitively unimpaired elderly subjects. Front Aging Neurosci, 6:94.
[25] Gaser C, Franke K, Kloppel S, Koutsouleris N, Sauer H, Alzheimer's Disease Neuroimaging I (2013). BrainAGE in Mild Cognitive Impaired Patients: Predicting the Conversion to Alzheimer's Disease. PLoS One, 8:e67346.
[26] Nuytemans K, Maldonado L, Ali A, John-Williams K, Beecham GW, Martin E, et al. (2016). Overlap between Parkinson disease and Alzheimer disease in ABCA7 functional variants. Neurol Genet, 2:e44.
[27] Desikan RS, Schork AJ, Wang Y, Witoelar A, Sharma M, McEvoy LK, et al. (2015). Genetic overlap between Alzheimer’s disease and Parkinson’s disease at the MAPT locus. Mol Psychiatry, 20:1588.
[28] Cole JH, Ritchie SJ, Bastin ME, Valdes Hernandez MC, Munoz Maniega S, Royle N, et al. (2017). Brain age predicts mortality. Mol Psychiatry, 23:1385-1392.
[29] Ashburner J (2007). A fast diffeomorphic image registration algorithm. Neuroimage, 38:95-113.
[30] Smola AJ, Schölkopf B (2004). A tutorial on support vector regression. Stat Comput, 14:199-222.
[31] Koutsouleris N, Davatzikos C, Borgwardt S, Gaser C, Bottlender R, Frodl T, et al. (2013). Accelerated brain aging in schizophrenia and beyond: a neuroanatomical marker of psychiatric disorders. Schizophr Bull, 40:1140-1153.
[32] Erus G, Battapady H, Satterthwaite TD, Hakonarson H, Gur RE, Davatzikos C, et al. (2014). Imaging patterns of brain development and their relationship to cognition. Cereb Cortex, 25:1676-1684.
[33] Dosenbach NU, Nardos B, Cohen AL, Fair DA, Power JD, Church JA, et al. (2010). Prediction of individual brain maturity using fMRI. Science, 329:1358-1361.
[34] Lancaster J, Lorenz R, Leech R, Cole JH (2018). Bayesian Optimization for Neuroimaging Pre-processing in Brain Age Classification and Prediction. Front Aging Neurosci, 10:28.
[35] Beheshti I, Maikusa N, Matsuda H (2018). The association between "Brain-Age Score" (BAS) and traditional neuropsychological screening tools in Alzheimer's disease. Brain Behav, 8:e01020.
[36] Ganguly G, Chakrabarti S, Chatterjee U, Saso L (2017). Proteinopathy, oxidative stress and mitochondrial dysfunction: cross talk in Alzheimer’s disease and Parkinson’s disease. Drug Des Devel Ther, 11:797.
[37] Xie A, Gao J, Xu L, Meng D (2014). Shared mechanisms of neurodegeneration in Alzheimer’s disease and Parkinson’s disease. Biomed Res Int, 2014.
[38] Lowe LC, Gaser C, Franke K, Alzheimer's Disease Neuroimaging I (2016). The Effect of the APOE Genotype on Individual BrainAGE in Normal Aging, Mild Cognitive Impairment, and Alzheimer's Disease. PLoS One, 11:e0157514.
[39] Starkstein SE, Sabe L, Petracca G, Chemerinski E, Kuzis G, Merello M, et al. (1996). Neuropsychological and psychiatric differences between Alzheimer's disease and Parkinson's disease with dementia. J Neurol Neurosurg Psychiatry, 61:381-387.
[40] Burton EJ, McKeith IG, Burn DJ, Williams ED, O’Brien JT (2004). Cerebral atrophy in Parkinson’s disease with and without dementia: a comparison with Alzheimer’s disease, dementia with Lewy bodies and controls. Brain, 127:791-800.
[41] Sone D, Beheshti I, Maikusa N, Ota M, Kimura Y, Sato N, et al. (2019). Neuroimaging-based brain-age prediction in diverse forms of epilepsy: a signature of psychosis and beyond. Mol Psychiatry:1.
[42] Kruggel F, Turner J, Muftuler LT, Initiative AsDN (2010). Impact of scanner hardware and imaging protocol on image quality and compartment volume precision in the ADNI cohort. Neuroimage, 49:2123-2133.
[43] Han X, Jovicich J, Salat D, van der Kouwe A, Quinn B, Czanner S, et al. (2006). Reliability of MRI-derived measurements of human cerebral cortical thickness: the effects of field strength, scanner upgrade and manufacturer. Neuroimage, 32:180-194.
[1] Zhou Hefeng, Li Shengnan, Li Chuwen, Yang Xuanjun, Li Haitao, Zhong Hanbing, Lu Jia-Hong, Lee Simon Ming-Yuen. Oxyphylla A Promotes Degradation of α-Synuclein for Neuroprotection via Activation of Immunoproteasome[J]. Aging and disease, 2020, 11(3): 559-574.
[2] Le Wang, Yang Liu, Shuxin Yan, Tianshu Du, Xia Fu, Xiaoli Gong, Xinyu Zhou, Ting Zhang, Xiaomin Wang. Disease Progression-Dependent Expression of CD200R1 and CX3CR1 in Mouse Models of Parkinson’s Disease[J]. Aging and disease, 2020, 11(2): 254-268.
[3] Wenjun Deng, Changhong Xing, Rob David , Diego Mastroeni, MingMing Ning, Eng H Lo, Paul D Coleman. AmpliSeq Transcriptome of Laser Captured Neurons from Alzheimer Brain: Comparison of Single Cell Versus Neuron Pools[J]. Aging and disease, 2019, 10(6): 1146-1158.
[4] Yuan Tan, Minjing Ke, Zhijian Huang, Cheong-Meng Chong, Xiaotong Cen, Jia-Hong Lu, Xiaoli Yao, Dajiang Qin, Huanxing Su. Hydroxyurea Facilitates Manifestation of Disease Relevant Phenotypes in Patients-Derived IPSCs-Based Modeling of Late-Onset Parkinson’s Disease[J]. Aging and disease, 2019, 10(5): 1037-1048.
[5] Elizabeth Qian, Yue Huang. Subtyping of Parkinson’s Disease - Where Are We Up To?[J]. Aging and disease, 2019, 10(5): 1130-1139.
[6] Jinghui Xu, Xiaodi Fu, Mengqiu Pan, Xiao Zhou, Zhaoyu Chen, Dongmei Wang, Xiaomei Zhang, Qiong Chen, Yanhui Li, Xiaoxian Huang, Guanghui Liu, Jianjun Lu, Yan Liu, Yafang Hu, Suyue Pan, Qing Wang, Qun Wang, Yunqi Xu. Mitochondrial Creatine Kinase is Decreased in the Serum of Idiopathic Parkinson’s Disease Patients[J]. Aging and disease, 2019, 10(3): 601-610.
[7] Yong-Fei Zhao, Qiong Zhang, Jian-Feng Zhang, Zhi-Yin Lou, Hen-Bing Zu, Zi-Gao Wang, Wei-Cheng Zeng, Kai Yao, Bao-Guo Xiao. The Synergy of Aging and LPS Exposure in a Mouse Model of Parkinson’s Disease[J]. Aging and disease, 2018, 9(5): 785-797.
[8] De Lazzari Federica, Bubacco Luigi, Whitworth Alexander J, Bisaglia Marco. Superoxide Radical Dismutation as New Therapeutic Strategy in Parkinson’s Disease[J]. Aging and disease, 2018, 9(4): 716-728.
[9] Zhang Li, Hao Junwei, Zheng Yan, Su Ruijun, Liao Yajin, Gong Xiaoli, Liu Limin, Wang Xiaomin. Fucoidan Protects Dopaminergic Neurons by Enhancing the Mitochondrial Function in a Rotenone-induced Rat Model of Parkinson’s Disease[J]. Aging and disease, 2018, 9(4): 590-604.
[10] Perez-Roca Laia, Adame-Castillo Cristina, Campdelacreu Jaume, Ispierto Lourdes, Vilas Dolores, Rene Ramon, Alvarez Ramiro, Gascon-Bayarri Jordi, Serrano-Munoz Maria A., Ariza Aurelio, Beyer Katrin. Glucocerebrosidase mRNA is Diminished in Brain of Lewy Body Diseases and Changes with Disease Progression in Blood[J]. Aging and disease, 2018, 9(2): 208-219.
[11] Zhang Meng, Deng Yong-Ning, Zhang Jing-Yi, Liu Jie, Li Yan-Bo, Su Hua, Qu Qiu-Min. SIRT3 Protects Rotenone-induced Injury in SH-SY5Y Cells by Promoting Autophagy through the LKB1-AMPK-mTOR Pathway[J]. Aging and disease, 2018, 9(2): 273-286.
[12] Sun Qian, Wang Tian, Jiang Tian-Fang, Huang Pei, Wang Ying, Xiao Qin, Liu Jun, Chen Sheng-Di. Clinical Profile of Chinese Long-Term Parkinson’s Disease Survivors With 10 Years of Disease Duration and Beyond[J]. Aging and disease, 2018, 9(1): 8-16.
[13] Lv Deyong, Li Jingbo, Li Hongfu, Fu Yu, Wang Wei. Imaging and Quantitative Analysis of the Interstitial Space in the Caudate Nucleus in a Rotenone-Induced Rat Model of Parkinson’s Disease Using Tracer-based MRI[J]. Aging and disease, 2017, 8(1): 1-6.
[14] Su Ruijun, Sun Min, Wang Wei, Zhang Jianliang, Zhang Li, Zhen Junli, Qian Yanjing, Zheng Yan, Wang Xiaomin. A Novel Immunosuppressor, (5R)-5-Hydroxytriptolide, Alleviates Movement Disorder and Neuroinflammation in a 6-OHDA Hemiparkinsonian Rat Model[J]. Aging and disease, 2017, 8(1): 31-43.
[15] Smirnova Natalya A., Kaidery Navneet Ammal, Hushpulian Dmitry M., Rakhman Ilay I., Poloznikov Andrey A., Tishkov Vladimir I., Karuppagounder Saravanan S., Gaisina Irina N., Pekcec Anton, Leyen Klaus Van, Kazakov Sergey V., Yang Lichuan, Thomas Bobby, Ratan Rajiv R., Gazaryan Irina G.. Bioactive Flavonoids and Catechols as Hif1 and Nrf2 Protein Stabilizers - Implications for Parkinson’s Disease[J]. Aging and disease, 2016, 7(6): 745-762.
Viewed
Full text


Abstract

Cited

  Shared   
Copyright © 2014 Aging and Disease, All Rights Reserved.
Address: Aging and Disease Editorial Office 3400 Camp Bowie Boulevard Fort Worth, TX76106 USA
Fax: (817) 735-0408 E-mail: editorial@aginganddisease.org
Powered by Beijing Magtech Co. Ltd