Early detection of lung cancer using SVM classifier in biomedical image processing

Deep Prakash Kaucha; P. W.C. Prasad; Abeer Alsadoon; A. Elchouemi; Sasikumaran Sreedharan

doi:10.1109/ICPCSI.2017.8392305

Early detection of lung cancer using SVM classifier in biomedical image processing

Deep Prakash Kaucha, P. W.C. Prasad, Abeer Alsadoon, A. Elchouemi, Sasikumaran Sreedharan

Research output: Book chapter/Published conference paper › Conference paper › peer-review

32 Citations (Scopus)

Abstract

Image processing techniques are now commonly used in the medical field for early detection of diseases. This research aims to improve accuracy, sensitivity and specificity of early detection of lung cancer through a combination of image processing techniques and data mining. The Computed Tomography (CT) scan image of the lungs is pre-processed and the Region of Interest (ROI) segmented, retained and compressed using a DWT (Discrete Waveform Transform) technique. The resulting ROI image is decomposed into four sub frequencies, bands LL, HL, LH, and HH. Again, the LL sub frequency is decomposed into four sub-bands, applying a 2-level DWT to the ROI based image. Further, features such as entropy, co-relation, energy, variance and homogeneity are extracted from the 2-level DWT images using a GLCM (Gray level Co-occurrence Matrix) with classification effected by means of an SVM (Support Vector Machine). Classification identifies whether the CT image is normal or cancerous. The Lung Image Database Consortium dataset (LIDC) has been used for training and testing purpose for this study. A Receiver Operating Characteristics (ROC) curve is used to analyze the performance of the system. Overall the system has accuracy of 95.16%, sensitivity of 98.21% and specificity of 78.69%.

Original language	English
Title of host publication	2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI 2017)
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	3143-3148
Number of pages	6
ISBN (Electronic)	9781538608142
ISBN (Print)	9781538608135, 9781538608159 (Print on demand)
DOIs	https://doi.org/10.1109/ICPCSI.2017.8392305
Publication status	Published - 20 Jun 2018
Event	2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, ICPCSI 2017 - Saveetha Engineering College , Chennai, India Duration: 21 Sept 2017 → 22 Sept 2017 http://toc.proceedings.com/39832webtoc.pdf (Conference proceedings table of contents) https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8392357 (President's message)

Conference

Conference	2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, ICPCSI 2017
Country/Territory	India
City	Chennai
Period	21/09/17 → 22/09/17
Other	I welcome you to participate in the IEEE based International Conference on Power, Control , Signals and Instrumentation Engineering ICPCSI'17, organized by Department of Electrical and Electronics Engineering, Saveetha Engineering College, which will be a cornerstone of the achievements of this Institute. This Conference is just the beginning of an ongoing initiative where industry and academia can collaborate to develop research and development initiatives. ICPCSI'17 offers an energetic environment for the exchange of information with emphasis on new developments, services and applications by bringing together Researchers, Scientists, Professionals, Academicians, Corporate & Industry Professionals, Students and Entrepreneurs from various organizations allover the world under one roof. This Conference aims at facilitating the participants to exhibit and exchange their innovative work s on their appropriate topics of interest in Advanced Engineering Research.
Internet address	http://toc.proceedings.com/39832webtoc.pdf (Conference proceedings table of contents) https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8392357 (President's message)

UN SDGs

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

Access to Document

10.1109/ICPCSI.2017.8392305

Cite this

Kaucha, D. P., Prasad, P. W. C., Alsadoon, A., Elchouemi, A., & Sreedharan, S. (2018). Early detection of lung cancer using SVM classifier in biomedical image processing. In 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI 2017) (pp. 3143-3148). Article 8392305 IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICPCSI.2017.8392305

@inproceedings{2756305328804c918fe2267c7ae44945,

title = "Early detection of lung cancer using SVM classifier in biomedical image processing",

abstract = "Image processing techniques are now commonly used in the medical field for early detection of diseases. This research aims to improve accuracy, sensitivity and specificity of early detection of lung cancer through a combination of image processing techniques and data mining. The Computed Tomography (CT) scan image of the lungs is pre-processed and the Region of Interest (ROI) segmented, retained and compressed using a DWT (Discrete Waveform Transform) technique. The resulting ROI image is decomposed into four sub frequencies, bands LL, HL, LH, and HH. Again, the LL sub frequency is decomposed into four sub-bands, applying a 2-level DWT to the ROI based image. Further, features such as entropy, co-relation, energy, variance and homogeneity are extracted from the 2-level DWT images using a GLCM (Gray level Co-occurrence Matrix) with classification effected by means of an SVM (Support Vector Machine). Classification identifies whether the CT image is normal or cancerous. The Lung Image Database Consortium dataset (LIDC) has been used for training and testing purpose for this study. A Receiver Operating Characteristics (ROC) curve is used to analyze the performance of the system. Overall the system has accuracy of 95.16%, sensitivity of 98.21% and specificity of 78.69%.",

keywords = "Component, Formatting, Insert (key words), Style, Styling",

author = "Kaucha, {Deep Prakash} and Prasad, {P. W.C.} and Abeer Alsadoon and A. Elchouemi and Sasikumaran Sreedharan",

note = "Includes bibliographical references.; 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, ICPCSI 2017 ; Conference date: 21-09-2017 Through 22-09-2017",

year = "2018",

month = jun,

day = "20",

doi = "10.1109/ICPCSI.2017.8392305",

language = "English",

isbn = "9781538608135",

pages = "3143--3148",

booktitle = "2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI 2017)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

url = "http://toc.proceedings.com/39832webtoc.pdf, https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8392357",

}

Kaucha, DP, Prasad, PWC, Alsadoon, A, Elchouemi, A & Sreedharan, S 2018, Early detection of lung cancer using SVM classifier in biomedical image processing. in 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI 2017)., 8392305, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 3143-3148, 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, ICPCSI 2017, Chennai, India, 21/09/17. https://doi.org/10.1109/ICPCSI.2017.8392305

Early detection of lung cancer using SVM classifier in biomedical image processing. / Kaucha, Deep Prakash; Prasad, P. W.C.; Alsadoon, Abeer et al.
2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI 2017). United States: IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 3143-3148 8392305.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Early detection of lung cancer using SVM classifier in biomedical image processing

AU - Kaucha, Deep Prakash

AU - Prasad, P. W.C.

AU - Alsadoon, Abeer

AU - Elchouemi, A.

AU - Sreedharan, Sasikumaran

N1 - Includes bibliographical references.

PY - 2018/6/20

Y1 - 2018/6/20

N2 - Image processing techniques are now commonly used in the medical field for early detection of diseases. This research aims to improve accuracy, sensitivity and specificity of early detection of lung cancer through a combination of image processing techniques and data mining. The Computed Tomography (CT) scan image of the lungs is pre-processed and the Region of Interest (ROI) segmented, retained and compressed using a DWT (Discrete Waveform Transform) technique. The resulting ROI image is decomposed into four sub frequencies, bands LL, HL, LH, and HH. Again, the LL sub frequency is decomposed into four sub-bands, applying a 2-level DWT to the ROI based image. Further, features such as entropy, co-relation, energy, variance and homogeneity are extracted from the 2-level DWT images using a GLCM (Gray level Co-occurrence Matrix) with classification effected by means of an SVM (Support Vector Machine). Classification identifies whether the CT image is normal or cancerous. The Lung Image Database Consortium dataset (LIDC) has been used for training and testing purpose for this study. A Receiver Operating Characteristics (ROC) curve is used to analyze the performance of the system. Overall the system has accuracy of 95.16%, sensitivity of 98.21% and specificity of 78.69%.

AB - Image processing techniques are now commonly used in the medical field for early detection of diseases. This research aims to improve accuracy, sensitivity and specificity of early detection of lung cancer through a combination of image processing techniques and data mining. The Computed Tomography (CT) scan image of the lungs is pre-processed and the Region of Interest (ROI) segmented, retained and compressed using a DWT (Discrete Waveform Transform) technique. The resulting ROI image is decomposed into four sub frequencies, bands LL, HL, LH, and HH. Again, the LL sub frequency is decomposed into four sub-bands, applying a 2-level DWT to the ROI based image. Further, features such as entropy, co-relation, energy, variance and homogeneity are extracted from the 2-level DWT images using a GLCM (Gray level Co-occurrence Matrix) with classification effected by means of an SVM (Support Vector Machine). Classification identifies whether the CT image is normal or cancerous. The Lung Image Database Consortium dataset (LIDC) has been used for training and testing purpose for this study. A Receiver Operating Characteristics (ROC) curve is used to analyze the performance of the system. Overall the system has accuracy of 95.16%, sensitivity of 98.21% and specificity of 78.69%.

KW - Component

KW - Formatting

KW - Insert (key words)

KW - Style

KW - Styling

UR - http://www.scopus.com/inward/record.url?scp=85050132681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050132681&partnerID=8YFLogxK

U2 - 10.1109/ICPCSI.2017.8392305

DO - 10.1109/ICPCSI.2017.8392305

M3 - Conference paper

AN - SCOPUS:85050132681

SN - 9781538608135

SN - 9781538608159 (Print on demand)

SP - 3143

EP - 3148

BT - 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI 2017)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, ICPCSI 2017

Y2 - 21 September 2017 through 22 September 2017

ER -

Kaucha DP, Prasad PWC, Alsadoon A, Elchouemi A, Sreedharan S. Early detection of lung cancer using SVM classifier in biomedical image processing. In 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI 2017). United States: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 3143-3148. 8392305 Epub 2017. doi: 10.1109/ICPCSI.2017.8392305

Early detection of lung cancer using SVM classifier in biomedical image processing

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this