Classification of diffuse lung disease patterns on high-resolution computed tomography by a bag of words approach

Authors:
Rui Xu;Yasushi Hirano;Rie Tachibana;Shoji Kido
Affiliations:
Applied Medical Engineering Science, Graduate School of Medicine, Yamaguchi University, Ube, Japan;Applied Medical Engineering Science, Graduate School of Medicine, Yamaguchi University, Ube, Japan;Information Science and Technology Dept., Oshima National College of Maritime Technology, Oshima-Gun, Japan;Applied Medical Engineering Science, Graduate School of Medicine, Yamaguchi University, Ube, Japan
Venue:
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III
Year:
2011

Citing 5
Cited 0

Foundations of statistical natural language processing

Foundations of statistical natural language processing
Local invariant feature detectors: a survey

Foundations and Trends® in Computer Graphics and Vision
Kernel Methods in Computer Vision

Foundations and Trends® in Computer Graphics and Vision
A texton-based approach for the classification of lung parenchyma in CT images

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part III
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Visual inspection of diffuse lung disease (DLD) patterns on high-resolution computed tomography (HRCT) is difficult because of their high complexity. We proposed a bag of words based method on the classification of these textural patters in order to improve the detection and diagnosis of DLD for radiologists. Six kinds of typical pulmonary patterns were considered in this work. They were consolidation, ground-glass opacity, honeycombing, emphysema, nodular and normal tissue. Because they were characterized by both CT values and shapes, we proposed a set of statistical measure based local features calculated from both CT values and the eigen-values of Hessian matrices. The proposed method could achieve the recognition rate of 95.85%, which was higher comparing with one global feature based method and two other CT values based bag of words methods.