Alzheimer’s disease (AD) and mild cognitive impairment (MCI) are age-related neurodegenerative diseases characterized by progressive loss of memory and irreversible cognitive functions. The hippocampus, a brain area critical for learning and memory processes, is especially susceptible to damage at early stages of AD.
Objective:
We aimed to develop prediction model using a multi-modality sparse representation approach.
Methods:
We proposed a sparse representation approach to the hippocampus using structural T1-weighted magnetic resonance imaging (MRI) and 18-fluorodeoxyglucose-positron emission tomography (FDG-PET) to distinguish AD/MCI from healthy control subjects (HCs). We considered structural and function information for the hippocampus and applied a sparse patch-based approach to effectively reduce the dimensions of neuroimaging biomarkers.
Results:
In experiments using Alzheimer’s Disease Neuroimaging Initiative data, our proposed method demonstrated more reliable than previous classification studies. The effects of different parameters on segmentation accuracy were also evaluated. The mean classification accuracy obtained with our proposed method was 0.94 for AD/HCs, 0.82 for MCI/HCs, and 0.86 for AD/MCI.
Conclusion:
We extracted multi-modal features from automatically defined hippocampal regions of training subjects and found this method to be discriminative and robust for AD and MCI classification. The extraction of features in T1 and FDG-PET images is expected to improve classification performance due to the relationship between brain structure and function.
HinrichsC, SinghV, XuG, JohnsonSC, Alzheimer’s Disease Neuroimaging Initiative (2011) Predictive markers for AD in a multi-modality framework: An analysis of MCI progression in the ADNI population. Neuroimage55, 574–589
CuingnetR, GerardinE, TessierasJ, AuziasG, LehéricyS, HabertMO, ChupinM, BenaliH, ColliotO, Alzheimer’s Disease Neuroimaging Initiative (2011) Automatic classification of patients with Alzheimer’s disease from structural MRI: A comparison of ten methods using the ADNI database. Neuroimage56, 766–781.
ChupinM, GérardinE, CuingnetR, BoutetC, LemieuxL, LehéricyS, BenaliH, GarneroL, ColliotO, Alzheimer’s Disease Neuroimaging Initiative (2009) Fully automatic hippocampus segmentation and classification in Alzheimer’s disease and mild cognitive impairment applied on data from ADNI. Hippocampus19, 579–587.
12.
ClerxL, van RossumIA, BurnsL, KnolDL, ScheltensP, VerheyF, AaltenP, LapuertaP, van de PolL, van SchijndelR, de JongR, BarkhofF, WolzR, RueckertD, BocchettaM, TsolakiM, NobiliF, WahlundLO, MinthonL, FrölichL, HampelH, SoininenH, VisserPJ (2013) Measurements of medial temporal lobe atrophy for prediction of Alzheimer’s disease in subjects with mild cognitive impairment. Neurobiol Aging34, 2003–2013.
13.
CoupéP, EskildsenSF, ManjónJV, FonovVS, PruessnerJC, AllardM, CollinsDL, Alzheimer’s Disease Neuroimaging Initiative (2012) Scoring by nonlocal image patch estimator for early detection of Alzheimer’s disease. Neuroimage Clin1, 141–152.
14.
WolfH, GrunwaldM, KruggelF, Riedel-HellerSG, AngerhöferS, HojjatoleslamiA, HenselA, ArendtT, GertzH (2001) Hippocampal volume discriminates between normal cognition; questionable and mild dementia in the elderly. Neurobiol Aging22, 177–186.
DiehlJ, GrimmerT, DrzezgaA, RiemenschneiderM, FörstlH, KurzA (2004) Cerebral metabolic patterns at early stages of frontotemporal dementia and semantic dementia. A PET study. Neurobiol Aging25, 1051–1056.
17.
DrzezgaA, LautenschlagerN, SiebnerH, RiemenschneiderM, WillochF, MinoshimaS, SchwaigerM, KurzA (2003) Cerebral metabolic changes accompanying conversion of mild cognitive impairment into Alzheimer’s disease: A PET follow-up study. Eur J Nucl Med Mol Imaging30, 1104–1113.
ColliotO, ChételatG, ChupinM, DesgrangesB, MagninB, BenaliH, DuboisB, GarneroL, EustacheF, LehericyS (2008) Discrimination between Alzheimer disease, mild cognitive impairment, and normal aging by using automated segmentation of the hippocampus. Radiology248, 194–201.
20.
SukHI, LeeSW, ShenD, Alzheimer’s Disease Neuroimaging Initiative (2014) Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. Neuroimage101, 569–582.
21.
BaronJC, ChételatG, DesgrangesB, PercheyG, LandeauB, de la SayetteV, EustacheF (2001) In vivo mapping of gray matter loss with voxel-based morphometry in mild Alzheimer’s disease. Neuroimage14, 298–309.
22.
GoodCD, JohnsrudeIS, AshburnerJ, HensonRN, FristonKJ, FrackowiakRS (2001) A voxel-based morphometric study of ageing in 465 normal adult human brains. Neuroimage14, 21–36.
LiuM, ZhangD, ShenD, Alzheimer’s Disease Neuroimaging Initiative (2014) Hierarchical fusion of features and classifier decisions for Alzheimer’s disease diagnosis. Hum Brain Mapp35, 1305–1319.
29.
BallMJ, FismanM, HachinskiV, BlumeW, FoxA, KralVA, KirshenAJ, FoxH, MerskeyH (1985) A new definition of Alzheimer’s disease: A hippocampal dementia. Lancet1, 14–16.
30.
JackCRJr, ShiungMM, GunterJL, O’BrienPC, WeigandSD, KnopmanDS, BoeveBF, IvnikRJ, SmithGE, ChaRH, TangalosEG, PetersenRC (2004) Comparison of different MRI brain atrophy rate measures with clinical disease progression in AD. Neurology62, 591–600.
31.
LötjönenJ, WolzR, KoikkalainenJ, JulkunenV, ThurfjellL, LundqvistR, WaldemarG, SoininenH, RueckertD, Alzheimer’s Disease Neuroimaging Initiative (2011) Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer’s disease. Neuroimage56, 185–196.
32.
GerardinE, ChételatG, ChupinM, CuingnetR, DesgrangesB, KimHS, NiethammerM, DuboisB, LehéricyS, GarneroL, EustacheF, ColliotO, Alzheimer’s Disease Neuroimaging Initiative (2009) Multidimensional classification of hippocampal shape features discriminates Alzheimer’s disease and mild cognitive impairment from normal aging. Neuroimage47, 1476–1486.
LiuF, GuoW, YuD, GaoQ, GaoK, XueZ, DuH, ZhangJ, TanC, LiuZ, ZhaoJ, ChenH (2012) Classification of different therapeutic responses of major depressive disorder with multivariate pattern analysis method based on structural MR scans. PLoS One7, e40968.
40.
CuingnetR, RossoC, ChupinM, LehéricyS, DormontD, BenaliH, SamsonY, ColliotO (2011) Spatial regularization of SVM for the detection of diffusion alterations associated with stroke outcome. Med Image Anal15, 729–737.
41.
DavatzikosC, BhattP, ShawLM, BatmanghelichKN, TrojanowskiJQ (2011) Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification. Neurobiol Aging32, 2322.e2319–2322.e2327.
42.
WrightJ, MaY, MairalJ, SapiroG, HuangTS, YanS (2010) Sparse representation for computer vision and pattern recognition. Proc IEEE98, 1031–1044.
43.
TongT, WolzR, CoupéP, HajnalJV, RueckertD, Alzheimer’s Disease Neuroimaging Initiative (2013) Segmentation of MR images via discriminative dictionary learning and sparse coding: Application to hippocampus labeling. Neuroimage76, 11–23.
ShiF, WangL, WuG, LiG, GilmoreJH, LinW, ShenD (2014) Neonatal atlas construction using sparse representation. Hum Brain Mapp35, 4663–4677.
48.
SledJG, ZijdenbosAP, EvansAC (1998) A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging17, 87–97.
49.
ZijdenbosAP, ForghaniR, EvansAC (2002) Automatic “pipeline” analysis of 3-D MRI data for clinical trials: Application to multiple sclerosis. IEEE Trans Med Imaging21, 1280–1291.
50.
KlingmannT (1946) Physical signs in schizophrenia. Am J Psychiatry103, 69–71.
51.
KimS, ChungJK, KwakK, BowmanSE, BrenKL, BagchiB, FayerMD (2008) Native and unfolded cytochrome c–comparison of dynamics using 2D-IR vibrational echo spectroscopy. J Phys Chem B112, 10054–10063.
52.
TohkaJ, ZijdenbosA, EvansA (2004) Fast and robust parameter estimation for statistical partial volume models in brain MRI. Neuroimage23, 84–97.
KwakK, YoonU, LeeDK, KimGH, SeoSW, NaDL, ShimHJ, LeeJM (2013) Fully-automated approach to hippocampus segmentation using a graph-cuts algorithm combined with atlas-based segmentation and morphological opening. Magn Reson Imaging31, 1190–1196.
56.
WrightJ, YangAY, GaneshA, SastrySS, MaY (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell31, 210–227.
57.
TibshiraniR (1996) Regression shrinkage and selection via the Lasso. J R Stat Soc Series B Stat Methodol58, 267–288.
58.
LiuJ, JiS, JiepingYE (2009) Multi-task feature learning via efficient l2,1-norm minimization. Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pp. 339–348.
59.
Jun LiuSJ, JiepingYE (2011) SLEP: Sparse Learning with Efficient Projections. Arizona State University.
BaillyM, DestrieuxC, HommetC, MondonK, CottierJP, BeaufilsE, VierronE, VercouillieJ, IbazizeneM, VoisinT, PayouxP, BarréL, CamusV, GuilloteauD, RibeiroMJ (2015) Precuneus and cingulate cortex atrophy and hypometabolism in patients with Alzheimer’s Disease and mild cognitive impairment: MRI and (18)F-FDG PET quantitative analysis using FreeSurfer. Biomed Res Int2015, 583931.
62.
KhedherL, RamirezJ, GórrizJM, BrahimA, SegoviaF (2015) Alzheimer’s Disease Neuroimaging Initiative, Early diagnosis of Alzheimer’s disease based on partial least squares, principal component analysis and support vector machine using segmented MRI images. Neurocomputing151, 139–150.
63.
KhedherL, IllánIA, GórrizJM, RamírezJ, BrahimA, Meyer-BaeseA (2017) Independent component analysis-support vector machine-based computer-aided diagnosis system for Alzheimer’s with visual support. Int J Neural Syst27, 1650050.
64.
OrtizA, MunillaJ, GórrizJM, RamírezJ (2016) Ensembles of deep learning architectures for the early diagnosis of the Alzheimer’s disease. Int J Neural Syst26, 1650025.
65.
McInnisMG, GredenJF (2016) Longitudinal studies: An essential component for complex psychiatric disorders. Neurosci Res102, 4–12.
