Relational learning helps in three-way classification of Alzheimer patients from structural magnetic resonance images of the brain

Sriraam Natarajan, Baidya Saha, Saket Joshi, Adam Edwards, Tushar Khot, Elizabeth M. Davenport, Kristian Kersting, Christopher T. Whitlow, Joseph A Maldjian

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Magnetic resonance imaging (MRI) has emerged as an important tool to identify intermediate biomarkers of Alzheimer’s disease (AD) due to its ability to measure regional changes in the brain that are thought to reflect disease severity and progression. In this paper, we set out a novel pipeline that uses volumetric MRI data collected from different subjects as input and classifies them into one of three classes: AD, mild cognitive impairment (MCI) and cognitively normal (CN). Our pipeline consists of three stages—(1) a segmentation layer where brain MRI data is divided into clinically relevant regions; (2) a classification layer that uses relational learning algorithms to make pairwise predictions between the three classes; and (3) a combination layer that combines the results of the different classes to obtain the final classification. One of the key features of our proposed approach is that it allows for domain expert’s knowledge to guide the learning in all the layers. We evaluate our pipeline on 397 patients acquired from the Alzheimer’s Disease Neuroimaging Initiative and demonstrate that it obtains state-of-the-art performance with minimal feature engineering.

Original languageEnglish (US)
Pages (from-to)659-669
Number of pages11
JournalInternational Journal of Machine Learning and Cybernetics
Volume5
Issue number5
DOIs
StatePublished - Jan 1 2013

Fingerprint

Magnetic resonance
Brain
Magnetic resonance imaging
Pipelines
Neuroimaging
Biomarkers
Learning algorithms

Keywords

  • Biomedical applications
  • Ensemble methods
  • FMRI prediction
  • Statistical relational learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Relational learning helps in three-way classification of Alzheimer patients from structural magnetic resonance images of the brain. / Natarajan, Sriraam; Saha, Baidya; Joshi, Saket; Edwards, Adam; Khot, Tushar; Davenport, Elizabeth M.; Kersting, Kristian; Whitlow, Christopher T.; Maldjian, Joseph A.

In: International Journal of Machine Learning and Cybernetics, Vol. 5, No. 5, 01.01.2013, p. 659-669.

Research output: Contribution to journalArticle

Natarajan, Sriraam ; Saha, Baidya ; Joshi, Saket ; Edwards, Adam ; Khot, Tushar ; Davenport, Elizabeth M. ; Kersting, Kristian ; Whitlow, Christopher T. ; Maldjian, Joseph A. / Relational learning helps in three-way classification of Alzheimer patients from structural magnetic resonance images of the brain. In: International Journal of Machine Learning and Cybernetics. 2013 ; Vol. 5, No. 5. pp. 659-669.
@article{fe4f7a2797ab49b0bdfa9c98b5ba24bc,
title = "Relational learning helps in three-way classification of Alzheimer patients from structural magnetic resonance images of the brain",
abstract = "Magnetic resonance imaging (MRI) has emerged as an important tool to identify intermediate biomarkers of Alzheimer’s disease (AD) due to its ability to measure regional changes in the brain that are thought to reflect disease severity and progression. In this paper, we set out a novel pipeline that uses volumetric MRI data collected from different subjects as input and classifies them into one of three classes: AD, mild cognitive impairment (MCI) and cognitively normal (CN). Our pipeline consists of three stages—(1) a segmentation layer where brain MRI data is divided into clinically relevant regions; (2) a classification layer that uses relational learning algorithms to make pairwise predictions between the three classes; and (3) a combination layer that combines the results of the different classes to obtain the final classification. One of the key features of our proposed approach is that it allows for domain expert’s knowledge to guide the learning in all the layers. We evaluate our pipeline on 397 patients acquired from the Alzheimer’s Disease Neuroimaging Initiative and demonstrate that it obtains state-of-the-art performance with minimal feature engineering.",
keywords = "Biomedical applications, Ensemble methods, FMRI prediction, Statistical relational learning",
author = "Sriraam Natarajan and Baidya Saha and Saket Joshi and Adam Edwards and Tushar Khot and Davenport, {Elizabeth M.} and Kristian Kersting and Whitlow, {Christopher T.} and Maldjian, {Joseph A}",
year = "2013",
month = "1",
day = "1",
doi = "10.1007/s13042-013-0161-9",
language = "English (US)",
volume = "5",
pages = "659--669",
journal = "International Journal of Machine Learning and Cybernetics",
issn = "1868-8071",
publisher = "Springer Science + Business Media",
number = "5",

}

TY - JOUR

T1 - Relational learning helps in three-way classification of Alzheimer patients from structural magnetic resonance images of the brain

AU - Natarajan, Sriraam

AU - Saha, Baidya

AU - Joshi, Saket

AU - Edwards, Adam

AU - Khot, Tushar

AU - Davenport, Elizabeth M.

AU - Kersting, Kristian

AU - Whitlow, Christopher T.

AU - Maldjian, Joseph A

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Magnetic resonance imaging (MRI) has emerged as an important tool to identify intermediate biomarkers of Alzheimer’s disease (AD) due to its ability to measure regional changes in the brain that are thought to reflect disease severity and progression. In this paper, we set out a novel pipeline that uses volumetric MRI data collected from different subjects as input and classifies them into one of three classes: AD, mild cognitive impairment (MCI) and cognitively normal (CN). Our pipeline consists of three stages—(1) a segmentation layer where brain MRI data is divided into clinically relevant regions; (2) a classification layer that uses relational learning algorithms to make pairwise predictions between the three classes; and (3) a combination layer that combines the results of the different classes to obtain the final classification. One of the key features of our proposed approach is that it allows for domain expert’s knowledge to guide the learning in all the layers. We evaluate our pipeline on 397 patients acquired from the Alzheimer’s Disease Neuroimaging Initiative and demonstrate that it obtains state-of-the-art performance with minimal feature engineering.

AB - Magnetic resonance imaging (MRI) has emerged as an important tool to identify intermediate biomarkers of Alzheimer’s disease (AD) due to its ability to measure regional changes in the brain that are thought to reflect disease severity and progression. In this paper, we set out a novel pipeline that uses volumetric MRI data collected from different subjects as input and classifies them into one of three classes: AD, mild cognitive impairment (MCI) and cognitively normal (CN). Our pipeline consists of three stages—(1) a segmentation layer where brain MRI data is divided into clinically relevant regions; (2) a classification layer that uses relational learning algorithms to make pairwise predictions between the three classes; and (3) a combination layer that combines the results of the different classes to obtain the final classification. One of the key features of our proposed approach is that it allows for domain expert’s knowledge to guide the learning in all the layers. We evaluate our pipeline on 397 patients acquired from the Alzheimer’s Disease Neuroimaging Initiative and demonstrate that it obtains state-of-the-art performance with minimal feature engineering.

KW - Biomedical applications

KW - Ensemble methods

KW - FMRI prediction

KW - Statistical relational learning

UR - http://www.scopus.com/inward/record.url?scp=84919908630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919908630&partnerID=8YFLogxK

U2 - 10.1007/s13042-013-0161-9

DO - 10.1007/s13042-013-0161-9

M3 - Article

AN - SCOPUS:84919908630

VL - 5

SP - 659

EP - 669

JO - International Journal of Machine Learning and Cybernetics

JF - International Journal of Machine Learning and Cybernetics

SN - 1868-8071

IS - 5

ER -