Kernel-based Joint Feature Selection and Max-Margin Classification for Early Diagnosis of Parkinson's Disease

Ehsan Adeli, Guorong Wu, Behrouz Saghafi, Le An, Feng Shi, Dinggang Shen

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Feature selection methods usually select the most compact and relevant set of features based on their contribution to a linear regression model. Thus, these features might not be the best for a non-linear classifier. This is especially crucial for the tasks, in which the performance is heavily dependent on the feature selection techniques, like the diagnosis of neurodegenerative diseases. Parkinson's disease (PD) is one of the most common neurodegenerative disorders, which progresses slowly while affects the quality of life dramatically. In this paper, we use the data acquired from multi-modal neuroimaging data to diagnose PD by investigating the brain regions, known to be affected at the early stages. We propose a joint kernel-based feature selection and classification framework. Unlike conventional feature selection techniques that select features based on their performance in the original input feature space, we select features that best benefit the classification scheme in the kernel space. We further propose kernel functions, specifically designed for our non-negative feature types. We use MRI and SPECT data of 538 subjects from the PPMI database, and obtain a diagnosis accuracy of 97.5%, which outperforms all baseline and state-of-the-art methods.

Original languageEnglish
Article number41069
JournalScientific Reports
Volume7
DOIs
Publication statusPublished - 2017 Jan 25

Fingerprint

Parkinson Disease
Early Diagnosis
Joints
Neurodegenerative Diseases
Linear Models
Single-Photon Emission-Computed Tomography
Neuroimaging
Quality of Life
Databases
Brain

ASJC Scopus subject areas

  • General

Cite this

Kernel-based Joint Feature Selection and Max-Margin Classification for Early Diagnosis of Parkinson's Disease. / Adeli, Ehsan; Wu, Guorong; Saghafi, Behrouz; An, Le; Shi, Feng; Shen, Dinggang.

In: Scientific Reports, Vol. 7, 41069, 25.01.2017.

Research output: Contribution to journalArticle

@article{1e62822754d84532b8454d7754846135,
title = "Kernel-based Joint Feature Selection and Max-Margin Classification for Early Diagnosis of Parkinson's Disease",
abstract = "Feature selection methods usually select the most compact and relevant set of features based on their contribution to a linear regression model. Thus, these features might not be the best for a non-linear classifier. This is especially crucial for the tasks, in which the performance is heavily dependent on the feature selection techniques, like the diagnosis of neurodegenerative diseases. Parkinson's disease (PD) is one of the most common neurodegenerative disorders, which progresses slowly while affects the quality of life dramatically. In this paper, we use the data acquired from multi-modal neuroimaging data to diagnose PD by investigating the brain regions, known to be affected at the early stages. We propose a joint kernel-based feature selection and classification framework. Unlike conventional feature selection techniques that select features based on their performance in the original input feature space, we select features that best benefit the classification scheme in the kernel space. We further propose kernel functions, specifically designed for our non-negative feature types. We use MRI and SPECT data of 538 subjects from the PPMI database, and obtain a diagnosis accuracy of 97.5{\%}, which outperforms all baseline and state-of-the-art methods.",
author = "Ehsan Adeli and Guorong Wu and Behrouz Saghafi and Le An and Feng Shi and Dinggang Shen",
year = "2017",
month = "1",
day = "25",
doi = "10.1038/srep41069",
language = "English",
volume = "7",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Kernel-based Joint Feature Selection and Max-Margin Classification for Early Diagnosis of Parkinson's Disease

AU - Adeli, Ehsan

AU - Wu, Guorong

AU - Saghafi, Behrouz

AU - An, Le

AU - Shi, Feng

AU - Shen, Dinggang

PY - 2017/1/25

Y1 - 2017/1/25

N2 - Feature selection methods usually select the most compact and relevant set of features based on their contribution to a linear regression model. Thus, these features might not be the best for a non-linear classifier. This is especially crucial for the tasks, in which the performance is heavily dependent on the feature selection techniques, like the diagnosis of neurodegenerative diseases. Parkinson's disease (PD) is one of the most common neurodegenerative disorders, which progresses slowly while affects the quality of life dramatically. In this paper, we use the data acquired from multi-modal neuroimaging data to diagnose PD by investigating the brain regions, known to be affected at the early stages. We propose a joint kernel-based feature selection and classification framework. Unlike conventional feature selection techniques that select features based on their performance in the original input feature space, we select features that best benefit the classification scheme in the kernel space. We further propose kernel functions, specifically designed for our non-negative feature types. We use MRI and SPECT data of 538 subjects from the PPMI database, and obtain a diagnosis accuracy of 97.5%, which outperforms all baseline and state-of-the-art methods.

AB - Feature selection methods usually select the most compact and relevant set of features based on their contribution to a linear regression model. Thus, these features might not be the best for a non-linear classifier. This is especially crucial for the tasks, in which the performance is heavily dependent on the feature selection techniques, like the diagnosis of neurodegenerative diseases. Parkinson's disease (PD) is one of the most common neurodegenerative disorders, which progresses slowly while affects the quality of life dramatically. In this paper, we use the data acquired from multi-modal neuroimaging data to diagnose PD by investigating the brain regions, known to be affected at the early stages. We propose a joint kernel-based feature selection and classification framework. Unlike conventional feature selection techniques that select features based on their performance in the original input feature space, we select features that best benefit the classification scheme in the kernel space. We further propose kernel functions, specifically designed for our non-negative feature types. We use MRI and SPECT data of 538 subjects from the PPMI database, and obtain a diagnosis accuracy of 97.5%, which outperforms all baseline and state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85010806727&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010806727&partnerID=8YFLogxK

U2 - 10.1038/srep41069

DO - 10.1038/srep41069

M3 - Article

C2 - 28120883

AN - SCOPUS:85010806727

VL - 7

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 41069

ER -