Accuracy improvement for analysis of emphysema by lung lobe segmentation

Kazuaki Neda, Toshiyuki Tanaka, Shotaro Chubachi, Hiroaki Sugiura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Emphysema is a kind of obstructive lung disease, and the number of patients is increasing in recent years. The increase of the number of patients cause the increase of burden of physician, so computer aided diagnosis is strongly required and many researchers have been involved. In this study, we introduce a method of lung lobe segmentation. We incorporated this segmentation method into discriminant system of Emphysem and aimed at reducing false negative rate. To segment lobes, we emphasize the rarefied regions of the vessel by projecting an image to the sagittal plane, and applied basic techniques of image processing. Lastly, we carried out discriminant analysis based on the Mahalanobis's generalized distance. As a result, there was a reduction of 18.7% false-negative rate and improvement of 11.2% determining rate of positive compared to the conventional segmentation that uses only information of height.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages1498-1500
Number of pages3
Publication statusPublished - 2011
Event50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011 - Tokyo, Japan
Duration: 2011 Sep 132011 Sep 18

Other

Other50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011
CountryJapan
CityTokyo
Period11/9/1311/9/18

Fingerprint

Computer aided diagnosis
Pulmonary diseases
Discriminant analysis
Image processing

Keywords

  • CT image
  • Emphysema
  • Lung Lobe Segmentation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Neda, K., Tanaka, T., Chubachi, S., & Sugiura, H. (2011). Accuracy improvement for analysis of emphysema by lung lobe segmentation. In Proceedings of the SICE Annual Conference (pp. 1498-1500). [6060198]

Accuracy improvement for analysis of emphysema by lung lobe segmentation. / Neda, Kazuaki; Tanaka, Toshiyuki; Chubachi, Shotaro; Sugiura, Hiroaki.

Proceedings of the SICE Annual Conference. 2011. p. 1498-1500 6060198.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Neda, K, Tanaka, T, Chubachi, S & Sugiura, H 2011, Accuracy improvement for analysis of emphysema by lung lobe segmentation. in Proceedings of the SICE Annual Conference., 6060198, pp. 1498-1500, 50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011, Tokyo, Japan, 11/9/13.
Neda K, Tanaka T, Chubachi S, Sugiura H. Accuracy improvement for analysis of emphysema by lung lobe segmentation. In Proceedings of the SICE Annual Conference. 2011. p. 1498-1500. 6060198
Neda, Kazuaki ; Tanaka, Toshiyuki ; Chubachi, Shotaro ; Sugiura, Hiroaki. / Accuracy improvement for analysis of emphysema by lung lobe segmentation. Proceedings of the SICE Annual Conference. 2011. pp. 1498-1500
@inproceedings{ee91ba5a4aba42cb8ca4f2ee4cc14bcc,
title = "Accuracy improvement for analysis of emphysema by lung lobe segmentation",
abstract = "Emphysema is a kind of obstructive lung disease, and the number of patients is increasing in recent years. The increase of the number of patients cause the increase of burden of physician, so computer aided diagnosis is strongly required and many researchers have been involved. In this study, we introduce a method of lung lobe segmentation. We incorporated this segmentation method into discriminant system of Emphysem and aimed at reducing false negative rate. To segment lobes, we emphasize the rarefied regions of the vessel by projecting an image to the sagittal plane, and applied basic techniques of image processing. Lastly, we carried out discriminant analysis based on the Mahalanobis's generalized distance. As a result, there was a reduction of 18.7{\%} false-negative rate and improvement of 11.2{\%} determining rate of positive compared to the conventional segmentation that uses only information of height.",
keywords = "CT image, Emphysema, Lung Lobe Segmentation",
author = "Kazuaki Neda and Toshiyuki Tanaka and Shotaro Chubachi and Hiroaki Sugiura",
year = "2011",
language = "English",
isbn = "9784907764395",
pages = "1498--1500",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Accuracy improvement for analysis of emphysema by lung lobe segmentation

AU - Neda, Kazuaki

AU - Tanaka, Toshiyuki

AU - Chubachi, Shotaro

AU - Sugiura, Hiroaki

PY - 2011

Y1 - 2011

N2 - Emphysema is a kind of obstructive lung disease, and the number of patients is increasing in recent years. The increase of the number of patients cause the increase of burden of physician, so computer aided diagnosis is strongly required and many researchers have been involved. In this study, we introduce a method of lung lobe segmentation. We incorporated this segmentation method into discriminant system of Emphysem and aimed at reducing false negative rate. To segment lobes, we emphasize the rarefied regions of the vessel by projecting an image to the sagittal plane, and applied basic techniques of image processing. Lastly, we carried out discriminant analysis based on the Mahalanobis's generalized distance. As a result, there was a reduction of 18.7% false-negative rate and improvement of 11.2% determining rate of positive compared to the conventional segmentation that uses only information of height.

AB - Emphysema is a kind of obstructive lung disease, and the number of patients is increasing in recent years. The increase of the number of patients cause the increase of burden of physician, so computer aided diagnosis is strongly required and many researchers have been involved. In this study, we introduce a method of lung lobe segmentation. We incorporated this segmentation method into discriminant system of Emphysem and aimed at reducing false negative rate. To segment lobes, we emphasize the rarefied regions of the vessel by projecting an image to the sagittal plane, and applied basic techniques of image processing. Lastly, we carried out discriminant analysis based on the Mahalanobis's generalized distance. As a result, there was a reduction of 18.7% false-negative rate and improvement of 11.2% determining rate of positive compared to the conventional segmentation that uses only information of height.

KW - CT image

KW - Emphysema

KW - Lung Lobe Segmentation

UR - http://www.scopus.com/inward/record.url?scp=81255144422&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81255144422&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:81255144422

SN - 9784907764395

SP - 1498

EP - 1500

BT - Proceedings of the SICE Annual Conference

ER -