Locality-constrained Subcluster Representation Ensemble for lung image classification

Yang Song, Weidong Cai, Heng Huang, Yun Zhou, Yue Wang, David Dagan Feng

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a new Locality-constrained Subcluster Representation Ensemble (LSRE) model, to classify high-resolution computed tomography (HRCT) images of interstitial lung diseases (ILDs). Medical images normally exhibit large intra-class variation and inter-class ambiguity in the feature space. Modelling of feature space separation between different classes is thus problematic and this affects the classification performance. Our LSRE model tackles this issue in an ensemble classification construct. The image set is first partitioned into subclusters based on spectral clustering with approximation-based affinity matrix. Basis representations of the test image are then generated with sparse approximation from the subclusters. These basis representations are finally fused with approximation- and distribution-based weights to classify the test image. Our experimental results on a large HRCT database show good performance improvement over existing popular classifiers.

Original languageEnglish (US)
Pages (from-to)102-113
Number of pages12
JournalMedical Image Analysis
Volume22
Issue number1
DOIs
StatePublished - May 1 2015

Fingerprint

Image classification
Tomography
Lung
Pulmonary diseases
Interstitial Lung Diseases
Cluster Analysis
Classifiers
Databases
Weights and Measures

Keywords

  • Clustering
  • Ensemble classification
  • Locality-constrained linear coding
  • Medical image classification
  • Sparse representation

ASJC Scopus subject areas

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

Cite this

Locality-constrained Subcluster Representation Ensemble for lung image classification. / Song, Yang; Cai, Weidong; Huang, Heng; Zhou, Yun; Wang, Yue; Feng, David Dagan.

In: Medical Image Analysis, Vol. 22, No. 1, 01.05.2015, p. 102-113.

Research output: Contribution to journalArticle

Song, Yang ; Cai, Weidong ; Huang, Heng ; Zhou, Yun ; Wang, Yue ; Feng, David Dagan. / Locality-constrained Subcluster Representation Ensemble for lung image classification. In: Medical Image Analysis. 2015 ; Vol. 22, No. 1. pp. 102-113.
@article{d6d94f1ab8c24070a83af587c14c0306,
title = "Locality-constrained Subcluster Representation Ensemble for lung image classification",
abstract = "In this paper, we propose a new Locality-constrained Subcluster Representation Ensemble (LSRE) model, to classify high-resolution computed tomography (HRCT) images of interstitial lung diseases (ILDs). Medical images normally exhibit large intra-class variation and inter-class ambiguity in the feature space. Modelling of feature space separation between different classes is thus problematic and this affects the classification performance. Our LSRE model tackles this issue in an ensemble classification construct. The image set is first partitioned into subclusters based on spectral clustering with approximation-based affinity matrix. Basis representations of the test image are then generated with sparse approximation from the subclusters. These basis representations are finally fused with approximation- and distribution-based weights to classify the test image. Our experimental results on a large HRCT database show good performance improvement over existing popular classifiers.",
keywords = "Clustering, Ensemble classification, Locality-constrained linear coding, Medical image classification, Sparse representation",
author = "Yang Song and Weidong Cai and Heng Huang and Yun Zhou and Yue Wang and Feng, {David Dagan}",
year = "2015",
month = "5",
day = "1",
doi = "10.1016/j.media.2015.03.003",
language = "English (US)",
volume = "22",
pages = "102--113",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Locality-constrained Subcluster Representation Ensemble for lung image classification

AU - Song, Yang

AU - Cai, Weidong

AU - Huang, Heng

AU - Zhou, Yun

AU - Wang, Yue

AU - Feng, David Dagan

PY - 2015/5/1

Y1 - 2015/5/1

N2 - In this paper, we propose a new Locality-constrained Subcluster Representation Ensemble (LSRE) model, to classify high-resolution computed tomography (HRCT) images of interstitial lung diseases (ILDs). Medical images normally exhibit large intra-class variation and inter-class ambiguity in the feature space. Modelling of feature space separation between different classes is thus problematic and this affects the classification performance. Our LSRE model tackles this issue in an ensemble classification construct. The image set is first partitioned into subclusters based on spectral clustering with approximation-based affinity matrix. Basis representations of the test image are then generated with sparse approximation from the subclusters. These basis representations are finally fused with approximation- and distribution-based weights to classify the test image. Our experimental results on a large HRCT database show good performance improvement over existing popular classifiers.

AB - In this paper, we propose a new Locality-constrained Subcluster Representation Ensemble (LSRE) model, to classify high-resolution computed tomography (HRCT) images of interstitial lung diseases (ILDs). Medical images normally exhibit large intra-class variation and inter-class ambiguity in the feature space. Modelling of feature space separation between different classes is thus problematic and this affects the classification performance. Our LSRE model tackles this issue in an ensemble classification construct. The image set is first partitioned into subclusters based on spectral clustering with approximation-based affinity matrix. Basis representations of the test image are then generated with sparse approximation from the subclusters. These basis representations are finally fused with approximation- and distribution-based weights to classify the test image. Our experimental results on a large HRCT database show good performance improvement over existing popular classifiers.

KW - Clustering

KW - Ensemble classification

KW - Locality-constrained linear coding

KW - Medical image classification

KW - Sparse representation

UR - http://www.scopus.com/inward/record.url?scp=84961371685&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961371685&partnerID=8YFLogxK

U2 - 10.1016/j.media.2015.03.003

DO - 10.1016/j.media.2015.03.003

M3 - Article

C2 - 25839422

AN - SCOPUS:84961371685

VL - 22

SP - 102

EP - 113

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 1

ER -