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 paperConference paperpeer-review

12 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 languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Power, Control, Signals and Instrumentation Engineering
Subtitle of host publicationICPCSI 2017
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages3143-3148
Number of pages6
ISBN (Electronic)9781538608142
ISBN (Print)9781538608135
DOIs
Publication statusPublished - 20 Jun 2018
Event2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, ICPCSI 2017 - Saveetha Engineering College , Chennai, India
Duration: 21 Sep 201722 Sep 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

Conference2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, ICPCSI 2017
Country/TerritoryIndia
CityChennai
Period21/09/1722/09/17
OtherWe are happy to welcome you. We Saveetha Engineering College is one of very renowned institute located at Chennai. We constructed our education system by quality which yields good and effective products. That is why we are pioneers among. Our main aim is to make people feel education. We are practicing as many options as possible. So, here we are with one kind to elaborate your ideas, to know what and how. "International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI-2017)" is a platform to propose your ideas and your work for its implementation in form technical papers. Every work needed consideration and it has to be in a proper manner. We too follow the same to make your work yours by publishing them in standard journals.
Internet address

Fingerprint

Dive into the research topics of 'Early detection of lung cancer using SVM classifier in biomedical image processing'. Together they form a unique fingerprint.

Cite this