Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data

Tao Zhou, Kim Han Thung, Mingxia Liu, Feng Shi, Changqing Zhang, Dinggang Shen

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Fusing multi-modality data is crucial for accurate identification of brain disorder as different modalities can provide complementary perspectives of complex neurodegenerative disease. However, there are at least four common issues associated with the existing fusion methods. First, many existing fusion methods simply concatenate features from each modality without considering the correlations among different modalities. Second, most existing methods often make prediction based on a single classifier, which might not be able to address the heterogeneity of the Alzheimer's disease (AD) progression. Third, many existing methods often employ feature selection (or reduction) and classifier training in two independent steps, without considering the fact that the two pipelined steps are highly related to each other. Forth, there are missing neuroimaging data for some of the participants (e.g., missing PET data), due to the participants’ “no-show” or dropout. In this paper, to address the above issues, we propose an early AD diagnosis framework via novel multi-modality latent space inducing ensemble SVM classifier. Specifically, we first project the neuroimaging data from different modalities into a latent space, and then map the learned latent representations into the label space to learn multiple diversified classifiers. Finally, we obtain the more reliable classification results by using an ensemble strategy. More importantly, we present a Complete Multi-modality Latent Space (CMLS) learning model for complete multi-modality data and also an Incomplete Multi-modality Latent Space (IMLS) learning model for incomplete multi-modality data. Extensive experiments using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset have demonstrated that our proposed models outperform other state-of-the-art methods.

Original languageEnglish
Article number101630
JournalMedical Image Analysis
Volume60
DOIs
Publication statusPublished - 2020 Feb

Keywords

  • Alzheimer's disease (AD)
  • Latent space
  • Missing modality
  • Multi-modality data
  • Multiple diversified classifiers

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data. / Zhou, Tao; Thung, Kim Han; Liu, Mingxia; Shi, Feng; Zhang, Changqing; Shen, Dinggang.

In: Medical Image Analysis, Vol. 60, 101630, 02.2020.

Research output: Contribution to journalArticle

Zhou, Tao ; Thung, Kim Han ; Liu, Mingxia ; Shi, Feng ; Zhang, Changqing ; Shen, Dinggang. / Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data. In: Medical Image Analysis. 2020 ; Vol. 60.
@article{6ad7c22c54b64aad9eb63fb461753560,
title = "Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data",
abstract = "Fusing multi-modality data is crucial for accurate identification of brain disorder as different modalities can provide complementary perspectives of complex neurodegenerative disease. However, there are at least four common issues associated with the existing fusion methods. First, many existing fusion methods simply concatenate features from each modality without considering the correlations among different modalities. Second, most existing methods often make prediction based on a single classifier, which might not be able to address the heterogeneity of the Alzheimer's disease (AD) progression. Third, many existing methods often employ feature selection (or reduction) and classifier training in two independent steps, without considering the fact that the two pipelined steps are highly related to each other. Forth, there are missing neuroimaging data for some of the participants (e.g., missing PET data), due to the participants’ “no-show” or dropout. In this paper, to address the above issues, we propose an early AD diagnosis framework via novel multi-modality latent space inducing ensemble SVM classifier. Specifically, we first project the neuroimaging data from different modalities into a latent space, and then map the learned latent representations into the label space to learn multiple diversified classifiers. Finally, we obtain the more reliable classification results by using an ensemble strategy. More importantly, we present a Complete Multi-modality Latent Space (CMLS) learning model for complete multi-modality data and also an Incomplete Multi-modality Latent Space (IMLS) learning model for incomplete multi-modality data. Extensive experiments using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset have demonstrated that our proposed models outperform other state-of-the-art methods.",
keywords = "Alzheimer's disease (AD), Latent space, Missing modality, Multi-modality data, Multiple diversified classifiers",
author = "Tao Zhou and Thung, {Kim Han} and Mingxia Liu and Feng Shi and Changqing Zhang and Dinggang Shen",
year = "2020",
month = "2",
doi = "10.1016/j.media.2019.101630",
language = "English",
volume = "60",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

TY - JOUR

T1 - Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data

AU - Zhou, Tao

AU - Thung, Kim Han

AU - Liu, Mingxia

AU - Shi, Feng

AU - Zhang, Changqing

AU - Shen, Dinggang

PY - 2020/2

Y1 - 2020/2

N2 - Fusing multi-modality data is crucial for accurate identification of brain disorder as different modalities can provide complementary perspectives of complex neurodegenerative disease. However, there are at least four common issues associated with the existing fusion methods. First, many existing fusion methods simply concatenate features from each modality without considering the correlations among different modalities. Second, most existing methods often make prediction based on a single classifier, which might not be able to address the heterogeneity of the Alzheimer's disease (AD) progression. Third, many existing methods often employ feature selection (or reduction) and classifier training in two independent steps, without considering the fact that the two pipelined steps are highly related to each other. Forth, there are missing neuroimaging data for some of the participants (e.g., missing PET data), due to the participants’ “no-show” or dropout. In this paper, to address the above issues, we propose an early AD diagnosis framework via novel multi-modality latent space inducing ensemble SVM classifier. Specifically, we first project the neuroimaging data from different modalities into a latent space, and then map the learned latent representations into the label space to learn multiple diversified classifiers. Finally, we obtain the more reliable classification results by using an ensemble strategy. More importantly, we present a Complete Multi-modality Latent Space (CMLS) learning model for complete multi-modality data and also an Incomplete Multi-modality Latent Space (IMLS) learning model for incomplete multi-modality data. Extensive experiments using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset have demonstrated that our proposed models outperform other state-of-the-art methods.

AB - Fusing multi-modality data is crucial for accurate identification of brain disorder as different modalities can provide complementary perspectives of complex neurodegenerative disease. However, there are at least four common issues associated with the existing fusion methods. First, many existing fusion methods simply concatenate features from each modality without considering the correlations among different modalities. Second, most existing methods often make prediction based on a single classifier, which might not be able to address the heterogeneity of the Alzheimer's disease (AD) progression. Third, many existing methods often employ feature selection (or reduction) and classifier training in two independent steps, without considering the fact that the two pipelined steps are highly related to each other. Forth, there are missing neuroimaging data for some of the participants (e.g., missing PET data), due to the participants’ “no-show” or dropout. In this paper, to address the above issues, we propose an early AD diagnosis framework via novel multi-modality latent space inducing ensemble SVM classifier. Specifically, we first project the neuroimaging data from different modalities into a latent space, and then map the learned latent representations into the label space to learn multiple diversified classifiers. Finally, we obtain the more reliable classification results by using an ensemble strategy. More importantly, we present a Complete Multi-modality Latent Space (CMLS) learning model for complete multi-modality data and also an Incomplete Multi-modality Latent Space (IMLS) learning model for incomplete multi-modality data. Extensive experiments using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset have demonstrated that our proposed models outperform other state-of-the-art methods.

KW - Alzheimer's disease (AD)

KW - Latent space

KW - Missing modality

KW - Multi-modality data

KW - Multiple diversified classifiers

UR - http://www.scopus.com/inward/record.url?scp=85077503344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077503344&partnerID=8YFLogxK

U2 - 10.1016/j.media.2019.101630

DO - 10.1016/j.media.2019.101630

M3 - Article

C2 - 31927474

AN - SCOPUS:85077503344

VL - 60

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

M1 - 101630

ER -