An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images

Cesar Supanta; Guillermo Kemper; Christian Del Carpio

doi:10.1109/ICA-ACCA.2018.8609795

An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images

Cesar Supanta, Guillermo Kemper, Christian Del Carpio

Universidad de San Martín de Porres

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

4 Scopus citations

Abstract

This work proposes a method for feature extraction and detection of pulmonary nodules in digital radiographic images, as little visualization and highlighting of these features often prevent a deeper diagnosis in chest radiographs. The proposed method involves digital image processing techniques such as re-quantization, gamma correction, OTSU thresholding, projection analysis, convergence filter, dilation, erosion and geometric filters. The proposed algorithm has a sensitivity of 91%, specificity of 96% and precision 94% with a referential database of 50 chest radiographs.

Original language	English
Title of host publication	IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control
Subtitle of host publication	Towards an Industry 4.0 - Proceedings
Editors	Cristian Duran-Faundez, Gaston Lefranc, Mario Fernandez-Fernandez, Carlos Munoz, Ernesto Rubio
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538655863
DOIs	https://doi.org/10.1109/ICA-ACCA.2018.8609795
State	Published - 2 Jul 2018
Externally published	Yes
Event	IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0, ICA-ACCA 2018 - Greater Concepcion, Chile Duration: 17 Oct 2018 → 19 Oct 2018

Publication series

Name	IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings

Conference

Conference	IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0, ICA-ACCA 2018
Country/Territory	Chile
City	Greater Concepcion
Period	17/10/18 → 19/10/18

Keywords

Convergence filter
geometric filters
lung nodules
OTSU
projection analysis

Access to Document

10.1109/ICA-ACCA.2018.8609795

Cite this

Supanta, C., Kemper, G., & Carpio, C. D. (2018). An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images. In C. Duran-Faundez, G. Lefranc, M. Fernandez-Fernandez, C. Munoz, & E. Rubio (Eds.), IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings Article 8609795 (IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICA-ACCA.2018.8609795

Supanta, Cesar ; Kemper, Guillermo ; Carpio, Christian Del. / An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images. IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings. editor / Cristian Duran-Faundez ; Gaston Lefranc ; Mario Fernandez-Fernandez ; Carlos Munoz ; Ernesto Rubio. Institute of Electrical and Electronics Engineers Inc., 2018. (IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings).

@inproceedings{7c7f8daba64547d0b26cdcabcb11a875,

title = "An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images",

abstract = "This work proposes a method for feature extraction and detection of pulmonary nodules in digital radiographic images, as little visualization and highlighting of these features often prevent a deeper diagnosis in chest radiographs. The proposed method involves digital image processing techniques such as re-quantization, gamma correction, OTSU thresholding, projection analysis, convergence filter, dilation, erosion and geometric filters. The proposed algorithm has a sensitivity of 91\%, specificity of 96\% and precision 94\% with a referential database of 50 chest radiographs.",

keywords = "Convergence filter, geometric filters, lung nodules, OTSU, projection analysis",

author = "Cesar Supanta and Guillermo Kemper and Carpio, \{Christian Del\}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0, ICA-ACCA 2018 ; Conference date: 17-10-2018 Through 19-10-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/ICA-ACCA.2018.8609795",

language = "Ingl{\'e}s",

series = "IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Cristian Duran-Faundez and Gaston Lefranc and Mario Fernandez-Fernandez and Carlos Munoz and Ernesto Rubio",

booktitle = "IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control",

}

Supanta, C, Kemper, G & Carpio, CD 2018, An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images. in C Duran-Faundez, G Lefranc, M Fernandez-Fernandez, C Munoz & E Rubio (eds), IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings., 8609795, IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings, Institute of Electrical and Electronics Engineers Inc., IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0, ICA-ACCA 2018, Greater Concepcion, Chile, 17/10/18. https://doi.org/10.1109/ICA-ACCA.2018.8609795

An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images. / Supanta, Cesar; Kemper, Guillermo ; Carpio, Christian Del.
IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings. ed. / Cristian Duran-Faundez; Gaston Lefranc; Mario Fernandez-Fernandez; Carlos Munoz; Ernesto Rubio. Institute of Electrical and Electronics Engineers Inc., 2018. 8609795 (IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings).

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

TY - GEN

T1 - An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images

AU - Supanta, Cesar

AU - Kemper, Guillermo

AU - Carpio, Christian Del

PY - 2018/7/2

Y1 - 2018/7/2

N2 - This work proposes a method for feature extraction and detection of pulmonary nodules in digital radiographic images, as little visualization and highlighting of these features often prevent a deeper diagnosis in chest radiographs. The proposed method involves digital image processing techniques such as re-quantization, gamma correction, OTSU thresholding, projection analysis, convergence filter, dilation, erosion and geometric filters. The proposed algorithm has a sensitivity of 91%, specificity of 96% and precision 94% with a referential database of 50 chest radiographs.

AB - This work proposes a method for feature extraction and detection of pulmonary nodules in digital radiographic images, as little visualization and highlighting of these features often prevent a deeper diagnosis in chest radiographs. The proposed method involves digital image processing techniques such as re-quantization, gamma correction, OTSU thresholding, projection analysis, convergence filter, dilation, erosion and geometric filters. The proposed algorithm has a sensitivity of 91%, specificity of 96% and precision 94% with a referential database of 50 chest radiographs.

KW - Convergence filter

KW - geometric filters

KW - lung nodules

KW - OTSU

KW - projection analysis

UR - https://www.scopus.com/pages/publications/85062172004

U2 - 10.1109/ICA-ACCA.2018.8609795

DO - 10.1109/ICA-ACCA.2018.8609795

M3 - Contribución a la conferencia

AN - SCOPUS:85062172004

T3 - IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings

BT - IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control

A2 - Duran-Faundez, Cristian

A2 - Lefranc, Gaston

A2 - Fernandez-Fernandez, Mario

A2 - Munoz, Carlos

A2 - Rubio, Ernesto

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0, ICA-ACCA 2018

Y2 - 17 October 2018 through 19 October 2018

ER -

Supanta C, Kemper G , Carpio CD. An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images. In Duran-Faundez C, Lefranc G, Fernandez-Fernandez M, Munoz C, Rubio E, editors, IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. 8609795. (IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings). doi: 10.1109/ICA-ACCA.2018.8609795

An algorithm for feature extraction and detection of pulmonary nodules in digital radiographic images

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this