INTERDISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY |
Prev
Next
|
|
|
Individual identification using multi-metric of DTI in Alzheimer's disease and mild cognitive impairment |
Ying-Teng Zhang(张应腾), Shen-Quan Liu(刘深泉) |
School of Mathematics, South China University of Technology, Guangzhou, China |
|
|
Abstract Accurate identification of Alzheimer's disease (AD) and mild cognitive impairment (MCI) is crucial so as to improve diagnosis techniques and to better understand the neurodegenerative process. In this work, we aim to apply the machine learning method to individual identification and identify the discriminate features associated with AD and MCI. Diffusion tensor imaging scans of 48 patients with AD, 39 patients with late MCI, 75 patients with early MCI, and 51 age-matched healthy controls (HCs) are acquired from the Alzheimer's Disease Neuroimaging Initiative database. In addition to the common fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity metrics, there are two novel metrics, named local diffusion homogeneity that used Spearman's rank correlation coefficient and Kendall's coefficient concordance, which are taken as classification metrics. The recursive feature elimination method for support vector machine (SVM) and logistic regression (LR) combined with leave-one-out cross validation are applied to determine the optimal feature dimensions. Then the SVM and LR methods perform the classification process and compare the classification performance. The results show that not only can the multi-type combined metrics obtain higher accuracy than the single metric, but also the SVM classifier with multi-type combined metrics has better classification performance than the LR classifier. Statistically, the average accuracy of the combined metric is more than 92% for all between-group comparisons of SVM classifier. In addition to the high recognition rate, significant differences are found in the statistical analysis of cognitive scores between groups. We further execute the permutation test, receiver operating characteristic curves, and area under the curve to validate the robustness of the classifiers, and indicate that the SVM classifier is more stable and efficient than the LR classifier. Finally, the uncinated fasciculus, cingulum, corpus callosum, corona radiate, external capsule, and internal capsule have been regarded as the most important white matter tracts to identify AD, MCI, and HC. Our findings reveal a guidance role for machine-learning based image analysis on clinical diagnosis.
|
Received: 27 February 2018
Revised: 15 May 2018
Accepted manuscript online:
|
PACS:
|
87.19.xr
|
(Degenerative diseases (Alzheimer's, ALS, etc))
|
|
42.30.Sy
|
(Pattern recognition)
|
|
87.61.-c
|
(Magnetic resonance imaging)
|
|
87.19.L-
|
(Neuroscience)
|
|
Fund: Project supported by the National Natural Science Foundation of China (Grant No. 11572127). |
Corresponding Authors:
Shen-Quan Liu
E-mail: mashqliu@scut.edu.cn
|
Cite this article:
Ying-Teng Zhang(张应腾), Shen-Quan Liu(刘深泉) Individual identification using multi-metric of DTI in Alzheimer's disease and mild cognitive impairment 2018 Chin. Phys. B 27 088702
|
[1] |
Chetelat G, Villemagne V L, Bourgeat P, Pike K E, Jones G, Ames D, Ellis K A, Szoeke C, Martins R N, O’Keefe G J, Salvado O, Masters C L and Rowe C C 2010 Ann. Neurol 67 317
|
[2] |
Ferri C P, Prince M, Brayne C, Brodaty H, Fratiglioni L, Ganguli M, Hall K, Hasegawa K, Hendrie H, Huang Y Q, Jorm A, Mathers C, Menezes P R, Rimmer E and Scazufca M 2005 Lancet 366 2112
|
[3] |
Association A 2015 Alzheimer’s Dementia 11 332
|
[4] |
Jack C R Jr, Wiste H J, Vemuri P, Weigand S D, Senjem M L, Zeng G, Bernstein M A, Gunter J L, Pankratz V S, Aisen P S, Weiner M W, Petersen R C, Shaw L M, Trojanowski J Q and Knopman D S 2010 Brain 133 3336
|
[5] |
Bischkopf J, Busse A and Angermeyer M C 2002 Acta Psychiatr. Scand. 106 403
|
[6] |
Ballard C, Gauthier S, Corbett A, Brayne C, Aarsland D and Jones E 2011 Lancet 377 1019
|
[7] |
Adaszewski S, Dukart J, Kherif F, Frackowiak R and Draganski B 2013 Neurobiol. Aging 34 2815
|
[8] |
Khan W, Westman E, Jones N, Wahlund L O, Mecocci P, Vellas B, Tsolaki M, Kloszewska I, Soininen H, Spenger C, Lovestone S, Muehlboeck J S and Simmons A 2015 Brain Topogr 28 746
|
[9] |
Schmitter D, Roche A, Marechal B, Ribes D, Abdulkadir A, BachCuadra M, Daducci A, Granziera C, Kloppel S, Maeder P, Meuli R and Krueger G 2015 Neuroimage Clin 7 7
|
[10] |
Roher A E, Weiss N, Kokjohn T A, Kuo Y M, Kalback W, Anthony J, Watson D, Luehrs D C, Sue L, Walker D, Emmerling M, Goux W and Beach T 2002 Biochemistry 41 11080
|
[11] |
Amlien I K and Fjell A M 2014 Neuroscience 276 206
|
[12] |
Iqbal K and Grundke-Iqbal I 2008 J. Cell. Mol. Med. 12 38
|
[13] |
Bennett D A, Schneider J A, Wilson R S, Bienias J L and Arnold S E 2004 JAMA Neurol 61 378
|
[14] |
Ni H J, Zhou L P, Zeng P, Huang X L, Liu H X and Ning X B 2015 Chin. Phys. B 24 070502
|
[15] |
Mori S and Zhang J 2016 Neuron 51 527-539
|
[16] |
Basser P J and Pierpaoli C 1998 Magn. Reson. Med. 39 928
|
[17] |
Dyrba M, Barkhof F, Fellgiebel A, Filippi M, Hausner L, Hauenstein K, Kirste T, Teipel S J and EDSD study group 2015 J. Neuroimaging25 738
|
[18] |
Casanova R, Hsu F C and Espeland M A 2012 PLoS One 7 e44877
|
[19] |
Liu X, Tosun D, Weiner M W and Schuff N 2013 NeuroImage 83 148
|
[20] |
Cui Z X, Xia Z C, Su M M, Shu H and Gong G L 2016 Hum. Brain Mapp. 37 1443
|
[21] |
Yang H X, Fu H B, Wang H D, Jia J W, Sigrist M W and Dong F Z 2016 Chin. Phys. B 25 065201
|
[22] |
Liu H, Liu D and Deng L F 2006 Chin. Phys. B 15 1196
|
[23] |
Sun Z H and Jiang F 2010 Chin. Phys. B 19 110502
|
[24] |
Folstein M F, Folstein S E and Mchugh P R 1975 J. Psychint. Res. 12 189
|
[25] |
Berg L 1975 Neurology 44 1983
|
[26] |
Cui Z X, Zhong S Y, Xu P F, He Y and Gong G L 2013 Front. Hum. Neurosci. 7 42
|
[27] |
Smith S M, Jenkinson M, Woolrich M W, Beckmann C F, Behrens T E, Johansen-Berg H, Bannister P R, De Luca M, Drobnjak I, Flitney D E, Niazy R K, Saunders J, Vickers J, Zhang Y Y, De Stefano N, Brady J M and Matthews P M 2004 NeuroImage 23 S208
|
[28] |
Bellec P, Lavoie-Courchesne S, Dickinson P, Lerch J P, Zijdenbos A P and Evans A C 2012 Front. Neuroinform. 6 7
|
[29] |
Wang R, Benner T, Sorensen A and Wedeen V 2007 Proc. Intl. Soc. Mag. Reson. Med. 15 3720
|
[30] |
Gong G L 2013 PLoS One 8 e66366
|
[31] |
Beaulieu C 2002 NMR Biomed. 15 435
|
[32] |
Mori S, Oishi K, Jiang H Y, Jiang L, Li X, Akhter K, Hua K G, Faria A V, Mahmood A, Woods R, Toga A W, Pike G B, Neto P R, EvansA, Zhang J Y, Huang H, Miller M I, van Zijl P and Mazziotta J 2008 NeuroImage 40 570
|
[33] |
Abraham A, Pedregosa F, Eickenberg M, Gervais P, Mueller A, Kossaifi J, Gramfort A, Thirion B and Varoquaux G 2014 Front. Neuroinform. 8 14
|
[34] |
Guyon I, Weston J, Barnhill S and Vapnik V 2002 Machine Learning 46 34
|
[35] |
Farahat A K, Ghodsi A and Kamel M S 2011 IEEE 11th International Conference on Data Mining (ICDM), December 11–14, 2011, Vancouver, Canada, p. 161
|
[36] |
Craddock R C, Holtzheimer P E, Hu X P and Mayberg H S 2009 Magn. Reson. Med 62 1619
|
[37] |
De Martino F, Valente G, Staeren N, Ashburner J, Goebel R and Formisano E 2008 NeuroImage 43 44
|
[38] |
Whelan R, Watts R and Orr C A 2014 Nature 512 185
|
[39] |
Fawcett T 2006 Pattern. Recogn. Lett. 27 861
|
[40] |
Weiner M W, Veitch D P, Aisen P S, Beckett L A, Cairns N J, Green R C, Danielle H, Jack C R Jr, Jagust W, Morris J C, Petersen R C, Saykin A J, Shaw L M, Toga A W and Trojanowski J Q 2017 Alzheimers Dement 13 e1-e85
|
[41] |
Nir T M, Villalon-Reina J E, Prasad G, Jahanshad N, Joshi S H, Toga A W, Bernstein M A, Jack C R Jr, Weiner M W and Thompson P M 2015 Neurobiol. Aging 36 S132-S140
|
[42] |
Schouten T M, Koini M, Vos F, Seiler S, Rooij M, Lechner A, Schmidt R, Heuvel M V D, Grond J V and Rombouts S A R B 2017 Neuroimage 152 476
|
[43] |
Maggipinto T, Bellotti R, Amoroso N, Diacono D, Donvito G, Lella E, Monaco A, Antonella Scelsi M and Tangaro S 2017 Phys. Med. Biol. 62 2361
|
[44] |
Shiraishi J, Abe H, Li F, Engelmann R, MacMahon H and Doi K 2006 Acad. Radiol. 13 995
|
[45] |
Alemayehu D and Zou K H 2012 Acad. Radiol. 19 1457
|
[46] |
Zou K H, O’Malley A J and Mauri L 2007 Circulation 115 654
|
[47] |
Xie S, Xiao J X, Gong G L, Zang Y F, Wang Y H, Wu H K and Jiang X X 2006 Neurology 66 33
|
[48] |
Huang H, Fan X, Weiner M, Martin-Cook K, Xiao G, Davis J, Devous M, Rosenberg R and Diaz-Arrastia R 2012 Neurobiol. Aging 33 2029
|
[49] |
Agosta F, Pievani M, Sala S, Geroldi C, Galluzzi S, Frisoni G B and Filippi M 2011 International Journal of Medical Radiology 258 853
|
[50] |
Bozoki A C, Korolev I O, Davis N C, Hoisington L A and Berger K L 2012 Hum. Brain Mapp. 33 1792
|
[51] |
Clark D L, Boutros N N and Mendez M F 2001 J. Neuropsychiatry 13 525
|
[52] |
Bozzali M, Falini A, Franceschi M, Cercignani M, Zuffi M, Scotti G, Comi G and Filippi M 2002 J. Neurol., Neurosurg. Psychiatry 72 742
|
[53] |
Choi S J, Lim K O, Monteiro I and Reisberg B 2005 Geriatr. Psychol. Neur. 18 12
|
[54] |
Takahashi S, Yonezawa H, Takahashi J, Kudo M, Inoue T and Tohgi H 2002 Neurosci. Lett. 332 45
|
[55] |
Kier E L, Staib L H, Davis L M and Bronen R A 2004 Am. J. Neuroradiol. 25 677
|
[56] |
Ebeling U and von Cramon D 1992 Acta Neurochir. 115 143
|
[57] |
Gaffan D, Easton A and Parker A 2002 Journal of Neuroscience the Official Journal of the Society for Neuroscience 22 7288
|
[58] |
Levine B, Black S E, Cabeza R, Sinden M, Mcintosh A R, Toth J P, Tulving E and Stuss D T 1998 Brain 121 1951
|
[59] |
Yin R H, Tan L, Liu Y, Wang W Y, Wang H F, Jiang T, Radua J, Zhang Y, Gao J, Canu E, Migliaccio R, Filippi M, Gorno-Tempini M L and Yu J T 2015 J. Alzheimers Dis. 47 495
|
[60] |
Selden N R, Gitelman D R, Salamon-Murayama N, Parrish T B and Mesulam M M 1998 Brain 121 2249
|
No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|