Send to

Choose Destination
Sci Rep. 2017 Jan 12;7:39880. doi: 10.1038/srep39880.

Longitudinal measurement and hierarchical classification framework for the prediction of Alzheimer's disease.

Collaborators (240)

Weiner MW, Aisen P, Petersen R, Jack CR, Jagust W, Trojanowki JQ, Toga AW, Beckett L, Green RC, Saykin AJ, Morris J, Shaw LM, Kaye J, Quinn J, Silbert L, Lind B, Carter R, Dolen S, Schneider LS, Pawluczyk S, Beccera M, Teodoro L, Spann BM, Brewer J, Vanderswag H, Fleisher A, Heidebrink JL, Lord JL, Mason SS, Albers CS, Knopman D, Johnson K, Doody RS, Villanueva-Meyer J, Chowdhury M, Rountree S, Dang M, Stern Y, Honig LS, Bell KL, Ances B, Morris JC, Carroll M, Creech ML, Franklin E, Mintun MA, Schneider S, Oliver A, Marson D, Griffith R, Clark D, Geldmacher D, Brockington J, Roberson E, Love MN, Grossman H, Mitsis E, Shah RC, deToledo-Morrell L, Duara R, Varon D, Greig MT, Roberts P, Albert M, Onyike C, D'Agostino D, Kielb S, Galvin JE, Cerbone B, Michel CA, Pogorelec DM, Rusinek H, de Leon MJ, Glodzik L, De Santi S, Doraiswamy PM, Petrella JR, Borges-Neto S, Wong TZ, Coleman E, Smith CD, Jicha G, Hardy P, Sinha P, Oates E, Conrad G, Porsteinsson AP, Goldstein BS, Martin K, Makino KM, Ismail MS, Brand C, Mulnard RA, Thai G, Mc-Adams-Ortiz C, Womack K, Mathews D, Quiceno M, Levey AI, Lah JJ, Cellar JS, Burns JM, Swerdlow RH, Brooks WM, Apostolova L, Tingus K, Woo E, Silverman DH, Lu PH, Bartzokis G, Graff-Radford NR, Parfitt F, Kendall T, Johnson H, Farlow MR, Hake AM, Matthews BR, Brosch JR, Herring S, Hunt C, van Dyck CH, Carson RE, MacAvoy MG, Varma P, Chertkow H, Bergman H, Hosein C, Black S, Stefanovic B, Caldwell C, Hsiung GR, Feldman H, Mudge B, Assaly M, Finger E, Pasternack S, Rachisky I, Trost D, Kertesz A, Bernick C, Munic D, Mesulam MM, Lipowski K, Weintraub S, Bonakdarpour B, Kerwin D, Wu CK, Johnson N, Sadowsky C, Villena T, Turner RS, Johnson K, Reynolds B, Sperling RA, Johnson KA, Marshall G, Yesavage J, Taylor JL, Lane B, Rosen A, Tinklenberg J, Sabbagh MN, Belden CM, Jacobson SA, Sirrel SA, Kowall N, Killiany R, Budson AE, Norbash A, Johnson PL, Obisesan TO, Wolday S, Allard J, Lerner A, Ogrocki P, Tatsuoka C, Fatica P, Fletcher E, Maillard P, Olichney J, DeCarli C, Carmichael O, Kittur S, Borrie M, Lee TY, Bartha R, Johnson S, Asthana S, Carlsson CM, Potkin SG, Preda A, Nguyen D, Tariot P, Burke A, Trncic N, Fleisher A, Reeder S, Bates V, Capote H, Rainka M, Scharre DW, Kataki M, Adeli A, Zimmerman EA, Celmins D, Brown AD, Pearlson GD, Blank K, Anderson K, Flashman LA, Seltzer M, Hynes ML, Santulli RB, Sink KM, Gordineer L, Williamson JD, Garg P, Watkins F, Ott BR, Querfurth H, Tremont G, Salloway S, Malloy P, Correia S, Rosen HJ, Miller BL, Perry D, Mintzer J, Spicer K, Bachman D, Pomara N, Hernando R, Sarrael A, Relkin N, Chaing G, Lin M, Ravdin L, Smith A, Raj BA, Fargher K.

Author information

Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, China.


Accurate prediction of Alzheimer's disease (AD) is important for the early diagnosis and treatment of this condition. Mild cognitive impairment (MCI) is an early stage of AD. Therefore, patients with MCI who are at high risk of fully developing AD should be identified to accurately predict AD. However, the relationship between brain images and AD is difficult to construct because of the complex characteristics of neuroimaging data. To address this problem, we present a longitudinal measurement of MCI brain images and a hierarchical classification method for AD prediction. Longitudinal images obtained from individuals with MCI were investigated to acquire important information on the longitudinal changes, which can be used to classify MCI subjects as either MCI conversion (MCIc) or MCI non-conversion (MCInc) individuals. Moreover, a hierarchical framework was introduced to the classifier to manage high feature dimensionality issues and incorporate spatial information for improving the prediction accuracy. The proposed method was evaluated using 131 patients with MCI (70 MCIc and 61 MCInc) based on MRI scans taken at different time points. Results showed that the proposed method achieved 79.4% accuracy for the classification of MCIc versus MCInc, thereby demonstrating very promising performance for AD prediction.

[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center