Semi-supervised multimodal relevance vector regression improves cognitive performance estimation from imaging and biological biomarkers

Bo Cheng, Daoqiang Zhang, Songcan Chen, Daniel I. Kaufer, Dinggang Shen

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Accurate estimation of cognitive scores for patients can help track the progress of neurological diseases. In this paper, we present a novel semi-supervised multimodal relevance vector regression (SM-RVR) method for predicting clinical scores of neurological diseases from multimodal imaging and biological biomarker, to help evaluate pathological stage and predict progression of diseases, e.g.; Alzheimer's diseases (AD). Unlike most existing methods, we predict clinical scores from multimodal (imaging and biological) biomarkers, including MRI, FDG-PET, and CSF. Considering that the clinical scores of mild cognitive impairment (MCI) subjects are often less stable compared to those of AD and normal control (NC) subjects due to the heterogeneity of MCI, we use only the multimodal data of MCI subjects, but no corresponding clinical scores, to train a semi-supervised model for enhancing the estimation of clinical scores for AD and NC subjects. We also develop a new strategy for selecting the most informative MCI subjects. We evaluate the performance of our approach on 202 subjects with all three modalities of data (MRI, FDG-PET and CSF) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our SM-RVR method achieves a root-mean-square error (RMSE) of 1.91 and a correlation coefficient (CORR) of 0.80 for estimating the MMSE scores, and also a RMSE of 4.45 and a CORR of 0.78 for estimating the ADAS-Cog scores, demonstrating very promising performances in AD studies.

Original languageEnglish
Pages (from-to)339-353
Number of pages15
JournalNeuroinformatics
Volume11
Issue number3
DOIs
Publication statusPublished - 2013 Jul 1
Externally publishedYes

Fingerprint

Biomarkers
Alzheimer Disease
Imaging techniques
Multimodal Imaging
Mean square error
Magnetic resonance imaging
Neuroimaging
Disease Progression
Databases
Cognitive Dysfunction

Keywords

  • Alzheimer's disease (AD)
  • Mild cognitive impairment (MCI)
  • Multimodality
  • Relevance vector regression (RVR)
  • Semi-supervised learning

ASJC Scopus subject areas

  • Neuroscience(all)
  • Information Systems
  • Software

Cite this

Semi-supervised multimodal relevance vector regression improves cognitive performance estimation from imaging and biological biomarkers. / Cheng, Bo; Zhang, Daoqiang; Chen, Songcan; Kaufer, Daniel I.; Shen, Dinggang.

In: Neuroinformatics, Vol. 11, No. 3, 01.07.2013, p. 339-353.

Research output: Contribution to journalArticle

@article{4eef9716e9b14b768679c897c37c6e9c,
title = "Semi-supervised multimodal relevance vector regression improves cognitive performance estimation from imaging and biological biomarkers",
abstract = "Accurate estimation of cognitive scores for patients can help track the progress of neurological diseases. In this paper, we present a novel semi-supervised multimodal relevance vector regression (SM-RVR) method for predicting clinical scores of neurological diseases from multimodal imaging and biological biomarker, to help evaluate pathological stage and predict progression of diseases, e.g.; Alzheimer's diseases (AD). Unlike most existing methods, we predict clinical scores from multimodal (imaging and biological) biomarkers, including MRI, FDG-PET, and CSF. Considering that the clinical scores of mild cognitive impairment (MCI) subjects are often less stable compared to those of AD and normal control (NC) subjects due to the heterogeneity of MCI, we use only the multimodal data of MCI subjects, but no corresponding clinical scores, to train a semi-supervised model for enhancing the estimation of clinical scores for AD and NC subjects. We also develop a new strategy for selecting the most informative MCI subjects. We evaluate the performance of our approach on 202 subjects with all three modalities of data (MRI, FDG-PET and CSF) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our SM-RVR method achieves a root-mean-square error (RMSE) of 1.91 and a correlation coefficient (CORR) of 0.80 for estimating the MMSE scores, and also a RMSE of 4.45 and a CORR of 0.78 for estimating the ADAS-Cog scores, demonstrating very promising performances in AD studies.",
keywords = "Alzheimer's disease (AD), Mild cognitive impairment (MCI), Multimodality, Relevance vector regression (RVR), Semi-supervised learning",
author = "Bo Cheng and Daoqiang Zhang and Songcan Chen and Kaufer, {Daniel I.} and Dinggang Shen",
year = "2013",
month = "7",
day = "1",
doi = "10.1007/s12021-013-9180-7",
language = "English",
volume = "11",
pages = "339--353",
journal = "Neuroinformatics",
issn = "1539-2791",
publisher = "Humana Press",
number = "3",

}

TY - JOUR

T1 - Semi-supervised multimodal relevance vector regression improves cognitive performance estimation from imaging and biological biomarkers

AU - Cheng, Bo

AU - Zhang, Daoqiang

AU - Chen, Songcan

AU - Kaufer, Daniel I.

AU - Shen, Dinggang

PY - 2013/7/1

Y1 - 2013/7/1

N2 - Accurate estimation of cognitive scores for patients can help track the progress of neurological diseases. In this paper, we present a novel semi-supervised multimodal relevance vector regression (SM-RVR) method for predicting clinical scores of neurological diseases from multimodal imaging and biological biomarker, to help evaluate pathological stage and predict progression of diseases, e.g.; Alzheimer's diseases (AD). Unlike most existing methods, we predict clinical scores from multimodal (imaging and biological) biomarkers, including MRI, FDG-PET, and CSF. Considering that the clinical scores of mild cognitive impairment (MCI) subjects are often less stable compared to those of AD and normal control (NC) subjects due to the heterogeneity of MCI, we use only the multimodal data of MCI subjects, but no corresponding clinical scores, to train a semi-supervised model for enhancing the estimation of clinical scores for AD and NC subjects. We also develop a new strategy for selecting the most informative MCI subjects. We evaluate the performance of our approach on 202 subjects with all three modalities of data (MRI, FDG-PET and CSF) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our SM-RVR method achieves a root-mean-square error (RMSE) of 1.91 and a correlation coefficient (CORR) of 0.80 for estimating the MMSE scores, and also a RMSE of 4.45 and a CORR of 0.78 for estimating the ADAS-Cog scores, demonstrating very promising performances in AD studies.

AB - Accurate estimation of cognitive scores for patients can help track the progress of neurological diseases. In this paper, we present a novel semi-supervised multimodal relevance vector regression (SM-RVR) method for predicting clinical scores of neurological diseases from multimodal imaging and biological biomarker, to help evaluate pathological stage and predict progression of diseases, e.g.; Alzheimer's diseases (AD). Unlike most existing methods, we predict clinical scores from multimodal (imaging and biological) biomarkers, including MRI, FDG-PET, and CSF. Considering that the clinical scores of mild cognitive impairment (MCI) subjects are often less stable compared to those of AD and normal control (NC) subjects due to the heterogeneity of MCI, we use only the multimodal data of MCI subjects, but no corresponding clinical scores, to train a semi-supervised model for enhancing the estimation of clinical scores for AD and NC subjects. We also develop a new strategy for selecting the most informative MCI subjects. We evaluate the performance of our approach on 202 subjects with all three modalities of data (MRI, FDG-PET and CSF) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our SM-RVR method achieves a root-mean-square error (RMSE) of 1.91 and a correlation coefficient (CORR) of 0.80 for estimating the MMSE scores, and also a RMSE of 4.45 and a CORR of 0.78 for estimating the ADAS-Cog scores, demonstrating very promising performances in AD studies.

KW - Alzheimer's disease (AD)

KW - Mild cognitive impairment (MCI)

KW - Multimodality

KW - Relevance vector regression (RVR)

KW - Semi-supervised learning

UR - http://www.scopus.com/inward/record.url?scp=84881085429&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881085429&partnerID=8YFLogxK

U2 - 10.1007/s12021-013-9180-7

DO - 10.1007/s12021-013-9180-7

M3 - Article

C2 - 23504659

AN - SCOPUS:84881085429

VL - 11

SP - 339

EP - 353

JO - Neuroinformatics

JF - Neuroinformatics

SN - 1539-2791

IS - 3

ER -