Tuberculosis bacteria detection based on Random Forest using fluorescent images

Chi Zheng; Jingxin Liu; Guoping Qiu

doi:10.1109/CISP-BMEI.2016.7852772

Tuberculosis bacteria detection based on Random Forest using fluorescent images

Chi Zheng
, Jingxin Liu
, Guoping Qiu

University of Nottingham Ningbo China
University of Nottingham

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

10 Citations (Scopus)

Abstract

Tuberculosis (TB) is an infectious disease in low and middle-income countries. There are many methods of physical examinations for tuberculosis detection, but the most effective method is visual examination using microscopes, including fluorescent microscopy and bright field microscopy. However, according to the analysis of previous research work, the method based on fluorescent microscopes can yield on average 10% on sensitiveness than the bright field microscopy. In this paper, we present a TB detection method based on Random Forest using fluorescent microscopic images. We have conducted experiments on three types of classifiers, in terms of Random Forest (RF), linear SVM (LinSVM), and Cross-Validation SVM (CVSVM). The experimental results show that the machine learning method of Random Forest for TB segmentation and detection using fluorescent images has obtained better performance than other two methods.

Original language	English
Title of host publication	Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	553-558
Number of pages	6
ISBN (Electronic)	9781509037100
DOIs	https://doi.org/10.1109/CISP-BMEI.2016.7852772
Publication status	Published - 13 Feb 2017
Externally published	Yes
Event	9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016 - Datong, China Duration: 15 Oct 2016 → 17 Oct 2016

Publication series

Name	Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016

Conference

Conference	9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016
Country/Territory	China
City	Datong
Period	15/10/16 → 17/10/16

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Fluorescent microscopy
Image processing
Random Forest
Tuberculosis bacteria

Access to Document

10.1109/CISP-BMEI.2016.7852772

Cite this

Zheng, C., Liu, J., & Qiu, G. (2017). Tuberculosis bacteria detection based on Random Forest using fluorescent images. In Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016 (pp. 553-558). Article 7852772 (Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CISP-BMEI.2016.7852772

Zheng, Chi ; Liu, Jingxin ; Qiu, Guoping. / Tuberculosis bacteria detection based on Random Forest using fluorescent images. Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 553-558 (Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016).

@inproceedings{f17c2efa88da4fe791478ee9ad715e53,

title = "Tuberculosis bacteria detection based on Random Forest using fluorescent images",

abstract = "Tuberculosis (TB) is an infectious disease in low and middle-income countries. There are many methods of physical examinations for tuberculosis detection, but the most effective method is visual examination using microscopes, including fluorescent microscopy and bright field microscopy. However, according to the analysis of previous research work, the method based on fluorescent microscopes can yield on average 10\% on sensitiveness than the bright field microscopy. In this paper, we present a TB detection method based on Random Forest using fluorescent microscopic images. We have conducted experiments on three types of classifiers, in terms of Random Forest (RF), linear SVM (LinSVM), and Cross-Validation SVM (CVSVM). The experimental results show that the machine learning method of Random Forest for TB segmentation and detection using fluorescent images has obtained better performance than other two methods.",

keywords = "Fluorescent microscopy, Image processing, Random Forest, Tuberculosis bacteria",

author = "Chi Zheng and Jingxin Liu and Guoping Qiu",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016 ; Conference date: 15-10-2016 Through 17-10-2016",

year = "2017",

month = feb,

day = "13",

doi = "10.1109/CISP-BMEI.2016.7852772",

language = "English",

series = "Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016",

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

pages = "553--558",

booktitle = "Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016",

}

Zheng, C, Liu, J & Qiu, G 2017, Tuberculosis bacteria detection based on Random Forest using fluorescent images. in Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016., 7852772, Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016, Institute of Electrical and Electronics Engineers Inc., pp. 553-558, 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016, Datong, China, 15/10/16. https://doi.org/10.1109/CISP-BMEI.2016.7852772

Tuberculosis bacteria detection based on Random Forest using fluorescent images. / Zheng, Chi; Liu, Jingxin; Qiu, Guoping.
Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 553-558 7852772 (Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016).

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

TY - GEN

T1 - Tuberculosis bacteria detection based on Random Forest using fluorescent images

AU - Zheng, Chi

AU - Liu, Jingxin

AU - Qiu, Guoping

PY - 2017/2/13

Y1 - 2017/2/13

N2 - Tuberculosis (TB) is an infectious disease in low and middle-income countries. There are many methods of physical examinations for tuberculosis detection, but the most effective method is visual examination using microscopes, including fluorescent microscopy and bright field microscopy. However, according to the analysis of previous research work, the method based on fluorescent microscopes can yield on average 10% on sensitiveness than the bright field microscopy. In this paper, we present a TB detection method based on Random Forest using fluorescent microscopic images. We have conducted experiments on three types of classifiers, in terms of Random Forest (RF), linear SVM (LinSVM), and Cross-Validation SVM (CVSVM). The experimental results show that the machine learning method of Random Forest for TB segmentation and detection using fluorescent images has obtained better performance than other two methods.

AB - Tuberculosis (TB) is an infectious disease in low and middle-income countries. There are many methods of physical examinations for tuberculosis detection, but the most effective method is visual examination using microscopes, including fluorescent microscopy and bright field microscopy. However, according to the analysis of previous research work, the method based on fluorescent microscopes can yield on average 10% on sensitiveness than the bright field microscopy. In this paper, we present a TB detection method based on Random Forest using fluorescent microscopic images. We have conducted experiments on three types of classifiers, in terms of Random Forest (RF), linear SVM (LinSVM), and Cross-Validation SVM (CVSVM). The experimental results show that the machine learning method of Random Forest for TB segmentation and detection using fluorescent images has obtained better performance than other two methods.

KW - Fluorescent microscopy

KW - Image processing

KW - Random Forest

KW - Tuberculosis bacteria

UR - https://www.scopus.com/pages/publications/85016000563

U2 - 10.1109/CISP-BMEI.2016.7852772

DO - 10.1109/CISP-BMEI.2016.7852772

M3 - Conference Proceeding

AN - SCOPUS:85016000563

T3 - Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016

SP - 553

EP - 558

BT - Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016

Y2 - 15 October 2016 through 17 October 2016

ER -

Zheng C, Liu J, Qiu G. Tuberculosis bacteria detection based on Random Forest using fluorescent images. In Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 553-558. 7852772. (Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016). doi: 10.1109/CISP-BMEI.2016.7852772

Tuberculosis bacteria detection based on Random Forest using fluorescent images

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this