Computer aided diagnosis for pulmonary nodules by shape feature extraction

Kazunori Takei; Noriyasu Homma; Tadashi Ishibashi; Masao Sakai; Makoto Yoshizawa

doi:10.1109/SICE.2007.4421308

Computer aided diagnosis for pulmonary nodules by shape feature extraction

Kazunori Takei, Noriyasu Homma, Tadashi Ishibashi, Masao Sakai, Makoto Yoshizawa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

In this paper, we propose a new diagnosis method of pulmonary nodules in CT images to reduce false positive (FP) rate for high true positive (TP) rate conditions. An essential core of the method is to extract two novel and effective features from the raw CT images: One is orientation features of nodules in a region of interest (ROI) extracted by a gabor filter, while the other is variation of CT values of the ROI in the direction along body axis. By using the extracted features, a principal component analysis technic and neural network approaches are then used to discriminate between nodule and non-nodule images. Simulation results show that discrimination performance using the proposed features is extremely improved compared to that of the conventional method.

Original language	English
Title of host publication	SICE Annual Conference, SICE 2007
Pages	1964-1967
Number of pages	4
DOIs	https://doi.org/10.1109/SICE.2007.4421308
Publication status	Published - 2007 Dec 1
Event	SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007 - Takamatsu, Japan Duration: 2007 Sept 17 → 2007 Sept 20

Publication series

Name	Proceedings of the SICE Annual Conference

Other

Other	SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007
Country/Territory	Japan
City	Takamatsu
Period	07/9/17 → 07/9/20

Keywords

Computer aided diagnosis
Feature extraction
Pulmonary nodules
X-ray CT images

ASJC Scopus subject areas

Control and Systems Engineering
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/SICE.2007.4421308

Cite this

Takei, K, Homma, N, Ishibashi, T, Sakai, M & Yoshizawa, M 2007, Computer aided diagnosis for pulmonary nodules by shape feature extraction. in SICE Annual Conference, SICE 2007., 4421308, Proceedings of the SICE Annual Conference, pp. 1964-1967, SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007, Takamatsu, Japan, 07/9/17. https://doi.org/10.1109/SICE.2007.4421308

@inproceedings{f618d0a4ae9c4ecd9270e3be849a7c4f,

title = "Computer aided diagnosis for pulmonary nodules by shape feature extraction",

abstract = "In this paper, we propose a new diagnosis method of pulmonary nodules in CT images to reduce false positive (FP) rate for high true positive (TP) rate conditions. An essential core of the method is to extract two novel and effective features from the raw CT images: One is orientation features of nodules in a region of interest (ROI) extracted by a gabor filter, while the other is variation of CT values of the ROI in the direction along body axis. By using the extracted features, a principal component analysis technic and neural network approaches are then used to discriminate between nodule and non-nodule images. Simulation results show that discrimination performance using the proposed features is extremely improved compared to that of the conventional method.",

keywords = "Computer aided diagnosis, Feature extraction, Pulmonary nodules, X-ray CT images",

author = "Kazunori Takei and Noriyasu Homma and Tadashi Ishibashi and Masao Sakai and Makoto Yoshizawa",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/SICE.2007.4421308",

language = "English",

isbn = "4907764286",

series = "Proceedings of the SICE Annual Conference",

pages = "1964--1967",

booktitle = "SICE Annual Conference, SICE 2007",

note = "SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007 ; Conference date: 17-09-2007 Through 20-09-2007",

}

TY - GEN

T1 - Computer aided diagnosis for pulmonary nodules by shape feature extraction

AU - Takei, Kazunori

AU - Homma, Noriyasu

AU - Ishibashi, Tadashi

AU - Sakai, Masao

AU - Yoshizawa, Makoto

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, we propose a new diagnosis method of pulmonary nodules in CT images to reduce false positive (FP) rate for high true positive (TP) rate conditions. An essential core of the method is to extract two novel and effective features from the raw CT images: One is orientation features of nodules in a region of interest (ROI) extracted by a gabor filter, while the other is variation of CT values of the ROI in the direction along body axis. By using the extracted features, a principal component analysis technic and neural network approaches are then used to discriminate between nodule and non-nodule images. Simulation results show that discrimination performance using the proposed features is extremely improved compared to that of the conventional method.

AB - In this paper, we propose a new diagnosis method of pulmonary nodules in CT images to reduce false positive (FP) rate for high true positive (TP) rate conditions. An essential core of the method is to extract two novel and effective features from the raw CT images: One is orientation features of nodules in a region of interest (ROI) extracted by a gabor filter, while the other is variation of CT values of the ROI in the direction along body axis. By using the extracted features, a principal component analysis technic and neural network approaches are then used to discriminate between nodule and non-nodule images. Simulation results show that discrimination performance using the proposed features is extremely improved compared to that of the conventional method.

KW - Computer aided diagnosis

KW - Feature extraction

KW - Pulmonary nodules

KW - X-ray CT images

UR - http://www.scopus.com/inward/record.url?scp=50249136128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249136128&partnerID=8YFLogxK

U2 - 10.1109/SICE.2007.4421308

DO - 10.1109/SICE.2007.4421308

M3 - Conference contribution

AN - SCOPUS:50249136128

SN - 4907764286

SN - 9784907764289

T3 - Proceedings of the SICE Annual Conference

SP - 1964

EP - 1967

BT - SICE Annual Conference, SICE 2007

T2 - SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007

Y2 - 17 September 2007 through 20 September 2007

ER -

Computer aided diagnosis for pulmonary nodules by shape feature extraction

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this