Joint learning and weighting of visual vocabulary for bag-of-feature based tissue classification

Jim Jing Yan Wang, Halima Bensmail, Xin Gao

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

Automated classification of tissue types of Region of Interest (ROI) in medical images has been an important application in Computer-Aided Diagnosis (CAD). Recently, bag-of-feature methods which treat each ROI as a set of local features have shown their power in this field. Two important issues of bag-of-feature strategy for tissue classification are investigated in this paper: the visual vocabulary learning and weighting, which are always considered independently in traditional methods by neglecting the inner relationship between the visual words and their weights. To overcome this problem, we develop a novel algorithm, Joint-ViVo, which learns the vocabulary and visual word weights jointly. A unified objective function based on large margin is defined for learning of both visual vocabulary and visual word weights, and optimized alternately in the iterative algorithm. We test our algorithm on three tissue classification tasks: classifying breast tissue density in mammograms, classifying lung tissue in High-Resolution Computed Tomography (HRCT) images, and identifying brain tissue type in Magnetic Resonance Imaging (MRI). The results show that Joint-ViVo outperforms the state-of-art methods on tissue classification problems.

Original languageEnglish
Pages (from-to)3249-3255
Number of pages7
JournalPattern Recognition
Volume46
Issue number12
DOIs
Publication statusPublished - 1 Dec 2013

Fingerprint

Tissue
Tomography
Brain

Keywords

  • Bag-of-features
  • Tissue classification
  • Visual vocabulary
  • Visual word weighting

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Joint learning and weighting of visual vocabulary for bag-of-feature based tissue classification. / Wang, Jim Jing Yan; Bensmail, Halima; Gao, Xin.

In: Pattern Recognition, Vol. 46, No. 12, 01.12.2013, p. 3249-3255.

Research output: Contribution to journalArticle

@article{f13027122ad946a18c70121517c38757,
title = "Joint learning and weighting of visual vocabulary for bag-of-feature based tissue classification",
abstract = "Automated classification of tissue types of Region of Interest (ROI) in medical images has been an important application in Computer-Aided Diagnosis (CAD). Recently, bag-of-feature methods which treat each ROI as a set of local features have shown their power in this field. Two important issues of bag-of-feature strategy for tissue classification are investigated in this paper: the visual vocabulary learning and weighting, which are always considered independently in traditional methods by neglecting the inner relationship between the visual words and their weights. To overcome this problem, we develop a novel algorithm, Joint-ViVo, which learns the vocabulary and visual word weights jointly. A unified objective function based on large margin is defined for learning of both visual vocabulary and visual word weights, and optimized alternately in the iterative algorithm. We test our algorithm on three tissue classification tasks: classifying breast tissue density in mammograms, classifying lung tissue in High-Resolution Computed Tomography (HRCT) images, and identifying brain tissue type in Magnetic Resonance Imaging (MRI). The results show that Joint-ViVo outperforms the state-of-art methods on tissue classification problems.",
keywords = "Bag-of-features, Tissue classification, Visual vocabulary, Visual word weighting",
author = "Wang, {Jim Jing Yan} and Halima Bensmail and Xin Gao",
year = "2013",
month = "12",
day = "1",
doi = "10.1016/j.patcog.2013.05.001",
language = "English",
volume = "46",
pages = "3249--3255",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "12",

}

TY - JOUR

T1 - Joint learning and weighting of visual vocabulary for bag-of-feature based tissue classification

AU - Wang, Jim Jing Yan

AU - Bensmail, Halima

AU - Gao, Xin

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Automated classification of tissue types of Region of Interest (ROI) in medical images has been an important application in Computer-Aided Diagnosis (CAD). Recently, bag-of-feature methods which treat each ROI as a set of local features have shown their power in this field. Two important issues of bag-of-feature strategy for tissue classification are investigated in this paper: the visual vocabulary learning and weighting, which are always considered independently in traditional methods by neglecting the inner relationship between the visual words and their weights. To overcome this problem, we develop a novel algorithm, Joint-ViVo, which learns the vocabulary and visual word weights jointly. A unified objective function based on large margin is defined for learning of both visual vocabulary and visual word weights, and optimized alternately in the iterative algorithm. We test our algorithm on three tissue classification tasks: classifying breast tissue density in mammograms, classifying lung tissue in High-Resolution Computed Tomography (HRCT) images, and identifying brain tissue type in Magnetic Resonance Imaging (MRI). The results show that Joint-ViVo outperforms the state-of-art methods on tissue classification problems.

AB - Automated classification of tissue types of Region of Interest (ROI) in medical images has been an important application in Computer-Aided Diagnosis (CAD). Recently, bag-of-feature methods which treat each ROI as a set of local features have shown their power in this field. Two important issues of bag-of-feature strategy for tissue classification are investigated in this paper: the visual vocabulary learning and weighting, which are always considered independently in traditional methods by neglecting the inner relationship between the visual words and their weights. To overcome this problem, we develop a novel algorithm, Joint-ViVo, which learns the vocabulary and visual word weights jointly. A unified objective function based on large margin is defined for learning of both visual vocabulary and visual word weights, and optimized alternately in the iterative algorithm. We test our algorithm on three tissue classification tasks: classifying breast tissue density in mammograms, classifying lung tissue in High-Resolution Computed Tomography (HRCT) images, and identifying brain tissue type in Magnetic Resonance Imaging (MRI). The results show that Joint-ViVo outperforms the state-of-art methods on tissue classification problems.

KW - Bag-of-features

KW - Tissue classification

KW - Visual vocabulary

KW - Visual word weighting

UR - http://www.scopus.com/inward/record.url?scp=84881050542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881050542&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2013.05.001

DO - 10.1016/j.patcog.2013.05.001

M3 - Article

VL - 46

SP - 3249

EP - 3255

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 12

ER -