Domain Transfer Learning for MCI Conversion Prediction

Bo Cheng, Mingxia Liu, Daoqiang Zhang, Brent C. Munsell, Dinggang Shen

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

Machine learning methods have successfully been used to predict the conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD), by classifying MCI converters (MCI-C) from MCI nonconverters (MCI-NC). However, most existing methods construct classifiers using data from one particular target domain (e.g., MCI), and ignore data in other related domains (e.g., AD and normal control (NC)) that may provide valuable information to improve MCI conversion prediction performance. To address is limitation, we develop a novel domain transfer learning method for MCI conversion prediction, which can use data from both the target domain (i.e., MCI) and auxiliary domains (i.e., AD and NC). Specifically, the proposed method consists of three key components: 1) a domain transfer feature selection component that selects the most informative feature-subset from both target domain and auxiliary domains from different imaging modalities; 2) a domain transfer sample selection component that selects the most informative sample-subset from the same target and auxiliary domains from different data modalities; and 3) a domain transfer support vector machine classification component that fuses the selected features and samples to separate MCI-C and MCI-NC patients. We evaluate our method on 202 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) that have MRI, FDG-PET, and CSF data. The experimental results show the proposed method can classify MCI-C patients from MCI-NC patients with an accuracy of 79.4%, with the aid of additional domain knowledge learned from AD and NC.

Original languageEnglish
Article number10
Pages (from-to)1805-1817
Number of pages13
JournalIEEE Transactions on Biomedical Engineering
Volume62
Issue number7
DOIs
Publication statusPublished - 2015 Jul 1

Fingerprint

Alzheimer Disease
Neuroimaging
Electric fuses
Magnetic resonance imaging
Support vector machines
Learning systems
Feature extraction
Classifiers
Transfer (Psychology)
Cognitive Dysfunction
Imaging techniques

Keywords

  • Alzheimer's Disease
  • Domain Transfer Learning
  • Feature Selection
  • Mild Cognitive Impairment Converters
  • Sample Selection

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Domain Transfer Learning for MCI Conversion Prediction. / Cheng, Bo; Liu, Mingxia; Zhang, Daoqiang; Munsell, Brent C.; Shen, Dinggang.

In: IEEE Transactions on Biomedical Engineering, Vol. 62, No. 7, 10, 01.07.2015, p. 1805-1817.

Research output: Contribution to journalArticle

Cheng, Bo ; Liu, Mingxia ; Zhang, Daoqiang ; Munsell, Brent C. ; Shen, Dinggang. / Domain Transfer Learning for MCI Conversion Prediction. In: IEEE Transactions on Biomedical Engineering. 2015 ; Vol. 62, No. 7. pp. 1805-1817.
@article{fd828a6a623741c79a4c93b8fb73ccd3,
title = "Domain Transfer Learning for MCI Conversion Prediction",
abstract = "Machine learning methods have successfully been used to predict the conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD), by classifying MCI converters (MCI-C) from MCI nonconverters (MCI-NC). However, most existing methods construct classifiers using data from one particular target domain (e.g., MCI), and ignore data in other related domains (e.g., AD and normal control (NC)) that may provide valuable information to improve MCI conversion prediction performance. To address is limitation, we develop a novel domain transfer learning method for MCI conversion prediction, which can use data from both the target domain (i.e., MCI) and auxiliary domains (i.e., AD and NC). Specifically, the proposed method consists of three key components: 1) a domain transfer feature selection component that selects the most informative feature-subset from both target domain and auxiliary domains from different imaging modalities; 2) a domain transfer sample selection component that selects the most informative sample-subset from the same target and auxiliary domains from different data modalities; and 3) a domain transfer support vector machine classification component that fuses the selected features and samples to separate MCI-C and MCI-NC patients. We evaluate our method on 202 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) that have MRI, FDG-PET, and CSF data. The experimental results show the proposed method can classify MCI-C patients from MCI-NC patients with an accuracy of 79.4{\%}, with the aid of additional domain knowledge learned from AD and NC.",
keywords = "Alzheimer's Disease, Domain Transfer Learning, Feature Selection, Mild Cognitive Impairment Converters, Sample Selection",
author = "Bo Cheng and Mingxia Liu and Daoqiang Zhang and Munsell, {Brent C.} and Dinggang Shen",
year = "2015",
month = "7",
day = "1",
doi = "10.1109/TBME.2015.2404809",
language = "English",
volume = "62",
pages = "1805--1817",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "7",

}

TY - JOUR

T1 - Domain Transfer Learning for MCI Conversion Prediction

AU - Cheng, Bo

AU - Liu, Mingxia

AU - Zhang, Daoqiang

AU - Munsell, Brent C.

AU - Shen, Dinggang

PY - 2015/7/1

Y1 - 2015/7/1

N2 - Machine learning methods have successfully been used to predict the conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD), by classifying MCI converters (MCI-C) from MCI nonconverters (MCI-NC). However, most existing methods construct classifiers using data from one particular target domain (e.g., MCI), and ignore data in other related domains (e.g., AD and normal control (NC)) that may provide valuable information to improve MCI conversion prediction performance. To address is limitation, we develop a novel domain transfer learning method for MCI conversion prediction, which can use data from both the target domain (i.e., MCI) and auxiliary domains (i.e., AD and NC). Specifically, the proposed method consists of three key components: 1) a domain transfer feature selection component that selects the most informative feature-subset from both target domain and auxiliary domains from different imaging modalities; 2) a domain transfer sample selection component that selects the most informative sample-subset from the same target and auxiliary domains from different data modalities; and 3) a domain transfer support vector machine classification component that fuses the selected features and samples to separate MCI-C and MCI-NC patients. We evaluate our method on 202 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) that have MRI, FDG-PET, and CSF data. The experimental results show the proposed method can classify MCI-C patients from MCI-NC patients with an accuracy of 79.4%, with the aid of additional domain knowledge learned from AD and NC.

AB - Machine learning methods have successfully been used to predict the conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD), by classifying MCI converters (MCI-C) from MCI nonconverters (MCI-NC). However, most existing methods construct classifiers using data from one particular target domain (e.g., MCI), and ignore data in other related domains (e.g., AD and normal control (NC)) that may provide valuable information to improve MCI conversion prediction performance. To address is limitation, we develop a novel domain transfer learning method for MCI conversion prediction, which can use data from both the target domain (i.e., MCI) and auxiliary domains (i.e., AD and NC). Specifically, the proposed method consists of three key components: 1) a domain transfer feature selection component that selects the most informative feature-subset from both target domain and auxiliary domains from different imaging modalities; 2) a domain transfer sample selection component that selects the most informative sample-subset from the same target and auxiliary domains from different data modalities; and 3) a domain transfer support vector machine classification component that fuses the selected features and samples to separate MCI-C and MCI-NC patients. We evaluate our method on 202 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) that have MRI, FDG-PET, and CSF data. The experimental results show the proposed method can classify MCI-C patients from MCI-NC patients with an accuracy of 79.4%, with the aid of additional domain knowledge learned from AD and NC.

KW - Alzheimer's Disease

KW - Domain Transfer Learning

KW - Feature Selection

KW - Mild Cognitive Impairment Converters

KW - Sample Selection

UR - http://www.scopus.com/inward/record.url?scp=84933053884&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933053884&partnerID=8YFLogxK

U2 - 10.1109/TBME.2015.2404809

DO - 10.1109/TBME.2015.2404809

M3 - Article

VL - 62

SP - 1805

EP - 1817

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 7

M1 - 10

ER -