Multimodal manifold-regularized transfer learning for MCI conversion prediction.

As the early stage of Alzheimer's disease (AD), mild cognitive impairment (MCI) has high chance to convert to AD. Effective prediction of such conversion from MCI to AD is of great importance for early diagnosis of AD and also for evaluating AD risk pre-symptomatically. Unlike most previous methods...

Full description

Bibliographic Details
Published in:Brain Imaging & Behavior Vol. 9; no. 4; pp. 913 - 927
Main Authors: Cheng, Bo, Liu, Mingxia, Suk, Heung-Il, Shen, Dinggang, Zhang, Daoqiang
Format: research Journal Article
Published: Springer Nature Dec2015
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=111244182&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 111244182
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        19317557
        3GSC
      jtl: Brain Imaging & Behavior
      issn: 19317557
      maglogo: N
    pubinfo:
      dt: Dec2015
      vid: 9
      iid: 4
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        111244182
        111244182
        NLM25702248
        111244182
        10.1007/s11682-015-9356-x
        NLM25702248
        PMC4546576
        111244182
      ppf: 913
      ppct: 14
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Multimodal manifold-regularized transfer learning for MCI conversion prediction.
      aug:
        au:
          Cheng, Bo
          Liu, Mingxia
          Suk, Heung-Il
          Shen, Dinggang
          Zhang, Daoqiang
        affil: Department of Brain and Cognitive Engineering, Korea University, Seoul Republic of Korea
      sug:
        subj:
          Brain Radiography
          Alzheimer's Disease Diagnosis
          Diagnosis, Computer Assisted Methods
          Brain Pathology
          Cognition Disorders Diagnosis
          Tomography, Emission-Computed Methods
          Magnetic Resonance Imaging Methods
          Cognition Disorders Pathology
          ROC Curve
          Alzheimer's Disease Classification
          Cognition Disorders Physiopathology
          Cognition Disorders Classification
          Regression
          Resource Databases
          Alzheimer's Disease Pathology
          Prognosis
          Aged, 80 and Over
          Middle Age
          Diagnostic Imaging Methods
          Alzheimer's Disease Physiopathology
          Information Science Methods
          Aged
          Disease Progression
          Human
          Validation Studies
          Comparative Studies
          Evaluation Research
          Multicenter Studies
          Funding Source
          Aged, 80 & over
          Middle Aged: 45-64 years
          Aged: 65+ years
      ab: As the early stage of Alzheimer's disease (AD), mild cognitive impairment (MCI) has high chance to convert to AD. Effective prediction of such conversion from MCI to AD is of great importance for early diagnosis of AD and also for evaluating AD risk pre-symptomatically. Unlike most previous methods that used only the samples from a target domain to train a classifier, in this paper, we propose a novel multimodal manifold-regularized transfer learning (M2TL) method that jointly utilizes samples from another domain (e.g., AD vs. normal controls (NC)) as well as unlabeled samples to boost the performance of the MCI conversion prediction. Specifically, the proposed M2TL method includes two key components. The first one is a kernel-based maximum mean discrepancy criterion, which helps eliminate the potential negative effect induced by the distributional difference between the auxiliary domain (i.e., AD and NC) and the target domain (i.e., MCI converters (MCI-C) and MCI non-converters (MCI-NC)). The second one is a semi-supervised multimodal manifold-regularized least squares classification method, where the target-domain samples, the auxiliary-domain samples, and the unlabeled samples can be jointly used for training our classifier. Furthermore, with the integration of a group sparsity constraint into our objective function, the proposed M2TL has a capability of selecting the informative samples to build a robust classifier. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database validate the effectiveness of the proposed method by significantly improving the classification accuracy of 80.1 % for MCI conversion prediction, and also outperforming the state-of-the-art methods.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N