Indian Journal of Science and Technology

Open Access Open Access  Restricted Access Subscription Access

Comparative Analysis of Learning Algorithms for Lung Cancer Identification


Affiliations
1 NED University of Engineering and Technology, Karachi, Karachi City, Sindh − 75270, Pakistan
2 Sir Syed University of Engineering and Technology, Block 5 Gulshan-e-Iqbal, Karachi, Sindh − 75270, Pakistan
 

Lung Cancer detection making use of medical imaging is still a challenging task for radiologist. The objective of this research is to classify the types of lung tumours for extracted and selected features using learning algorithms. In this paper, an experimental study is conducted on 100 cases of lung cancer to evaluate the performance of learning classifiers (DNN, SVM, Random Forest, Decision Tree, Naïve Bayes) with different medical Imaging (DICOM) features to identify the two types of Lung cancer (Benign and Malignant). The proposed methodology intends to automate the entire procedure of diagnosis by automatically detecting the tumor, measuring the required values such as diameter, perimeter, area, centroid, roundness, indentations and calcification. Experiment is conducted in to two phases: In the first phase, identify the most significant feature used in lung cancer analysis by CT scan and perform the mapping to computer related format. In the second phase, feature selection and extraction is performed to machine learning algorithms. To evaluate the performance of classifiers in term of classification accuracy and improving the false positive rate, every stage of evolution is divided into four different phases: single phase module, single slice testing, series testing and testing of learning algorithms. Experimental results show significant improvement in false positive rate up to 30% for both Benign and Malignant. Whereas, Deep Neural Network (DNN) demonstrate high values in term of classification accuracy in comparison with other classifiers. The proposed methodology for lung cancer detection system having a potential to reduce the time and cost of diagnosis procedure and use for early detection of lung cancer.
User

  • Ang KC. Analysis of a tumor Growth Model with MATLAB, National Institute of Education, Nanyang Technological University, Singapore. http://atcm.mathandtech.org/EP2009/papers_invited/2812009_17198.pdf.

  • Lee N, Laine AF, Márquez G, Levsky JM, Gohagan JK. Potential of computer aided diagnosis to improve CT lung cancer screening, IEEE Reviews in Biomedical Engineering. 2009; 2:136−46. Crossref. PMid: 22275043.

  • Gajdhane VA, Deshpande LM. Detection of lung cancer stages on CT scan images by using various image processing techniques, IOSR Journal of Computer Engineering (IOSRJCE). 2014; 16(5):28−35. www.iosrjournals.org.

  • Sukhjinder Kaur. Comparative study review on lung cancer detection using neural network and clustering algorithm, International Journal of Advanced Research in Electronics and Communication Engineering (IJARECE). 2015; 4(2):169−74. Crossref.

  • Aggarwal P, Sardana H, Vig R. An efficient visualization and segmentation of lung ct scan images for early diagnosis of cancer. In: NCCI 2010 National Conference on Computational Instrumentation, Chandigarh, 2010.

  • Keshani M, Azimifar Z, Tajeripour F, Boostani. Lung nodule segmentation and recognition using SVM classifier and contour modeling: A complete intelligent system, 2012; 43(4):287−300. https://www.ncbi.nlm.nih.gov/pubmed/23369568.

  • Hiram Madero Orczco, Osslan Osiris Vergara Villegas, Vianey Guadalupe Cruz Sanchez, Humberto de Jesus Ochoa Domínguez, Manuel de Jesus Nandayapa Alfaro. Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine, Mexico City; 2013. 14:9. Crossref.

  • Arvind Kumar Tiwari. Prediction of lung cancer using image processing techniques: A review, Advanced Computational Intelligence: An International Journal. 2016; 3(1):1−9. https://www.aircconline.com/acii/V3N1/3116acii01.pdf. Crossref.

  • Sharma Ritika, Rajput Meenu, Prakash Pawan. Sharma Saurabh. Fast dissolving drug delivery system-a review, International Research Journal of Pharmacy. 2011; 2(11):21−29. www.irjponline.com/admin/php/uploads/671_pdf.pdf.

  • Rangapriya Sundararajan, Lionel Gellon, Rachel M. Zunder, Catherine H. Freudenreich. Double-strand break repair pathways protect against CAG/CTG repeat expansions, contractions and repeat-mediated chromosomal fragility in saccharomyces cerevisiae, Genetics. 2010; 184(1):65–77. Crossref. https://www.ncbi.nlm.nih.gov/pmc/ articles/PMC2815931.

  • Hassan Javed Chaudhary, Warda Shahid, Asghari Bano, Farman Ullah, Farooq Munis, Shah Fahad, Izhar Ahmad1. In vitro analysis of Cupressus sempervirens L. plant extracts antibaterial activity, Journal of Medicinal Plants Research. 2012; 6(2):273−76. Crossref.

  • Sluimer, Schilham A, Prokop M, van Ginneken B. Computer analysis of computed tomography scans of the lung: A survey, IEEE Transactions on Medical Imaging. 2006; 25(4):385−405. Crossref. https://ieeexplore.ieee.org/document/1610745/.

  • Carlos S. Pereira, Hugo Fernandes, Ana Maria Mendonça, Aurélio Campilho. Detection of lung nodule candidates in chest radiographs, Lecture Notes in Computer Science, v. 4478, Springer, Berlin, Heidelberg; IbPRIA 2007. 170−77. https://link.springer.com/chapter/10.1007/978-3-540-72849-8_22.

  • Vijai Anand SK. Segmentation coupled textural feature classification for lung tumor prediction, ICCCCT; 2010. Crossref 1, 2.

  • Lee SLA, Kouzani AZ, Hu EJ. A random forest for lung nodule identification, 2010; 23(1):151−63 Crossref.

  • Jia Tong, Zhao Da-Zhe, Wei Ying, Zhu Xin-Hua, Wang Xu. Computer-aided lung nodule detection based on CT images, IEEE/ICME International Conference on Complex Medical Engineering; 2007. Crossref.

  • Mao F, Qian. Fragmentary window filtering for multiscale lung nodule detection: Preliminary study, Acad Radiol. 1998; 5:306–11. Crossref.

  • Kourou K, Exarchos T, Exarchos K, Karamouzis M, Fotiadis. Machine learning applications in cancer prognosis and prediction, Computational and Structural Biotechnology Journal. 2015; 13:8–17. doi: 10.1016/ j.csbj.2014.11.005. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4348437/.

  • El-Baz A, Farag AA, Falk R, Rocco RL. Detection, visualization and identification of lung abnormalities in chest spiral CT scan: Phase I, Information Conference on Biomedical Engineering, Egypt, 2002.

  • Vinod Kumar, Kanwal Garg, Rakesh Kumar. Pulmonary nodules diagnosis from x-ray imaging using image processing, International Conference on Recent Trends of Computer Technology in Academia, ICRTCTA, J.R.N. Rajasthan Vidyapeeth University, Udaipur; 21-23 April 2012.


Abstract Views: 200

PDF Views: 0




  • Comparative Analysis of Learning Algorithms for Lung Cancer Identification

Abstract Views: 200  |  PDF Views: 0

Authors

Syed Abbas Ali
NED University of Engineering and Technology, Karachi, Karachi City, Sindh − 75270, Pakistan
Fatima Waheed
NED University of Engineering and Technology, Karachi, Karachi City, Sindh − 75270, Pakistan
Wajahat Rehman
NED University of Engineering and Technology, Karachi, Karachi City, Sindh − 75270, Pakistan
Sallar Khan
NED University of Engineering and Technology, Karachi, Karachi City, Sindh − 75270, Pakistan
Marium Zia
NED University of Engineering and Technology, Karachi, Karachi City, Sindh − 75270, Pakistan
Jawaria Sallar
Sir Syed University of Engineering and Technology, Block 5 Gulshan-e-Iqbal, Karachi, Sindh − 75270, Pakistan

Abstract


Lung Cancer detection making use of medical imaging is still a challenging task for radiologist. The objective of this research is to classify the types of lung tumours for extracted and selected features using learning algorithms. In this paper, an experimental study is conducted on 100 cases of lung cancer to evaluate the performance of learning classifiers (DNN, SVM, Random Forest, Decision Tree, Naïve Bayes) with different medical Imaging (DICOM) features to identify the two types of Lung cancer (Benign and Malignant). The proposed methodology intends to automate the entire procedure of diagnosis by automatically detecting the tumor, measuring the required values such as diameter, perimeter, area, centroid, roundness, indentations and calcification. Experiment is conducted in to two phases: In the first phase, identify the most significant feature used in lung cancer analysis by CT scan and perform the mapping to computer related format. In the second phase, feature selection and extraction is performed to machine learning algorithms. To evaluate the performance of classifiers in term of classification accuracy and improving the false positive rate, every stage of evolution is divided into four different phases: single phase module, single slice testing, series testing and testing of learning algorithms. Experimental results show significant improvement in false positive rate up to 30% for both Benign and Malignant. Whereas, Deep Neural Network (DNN) demonstrate high values in term of classification accuracy in comparison with other classifiers. The proposed methodology for lung cancer detection system having a potential to reduce the time and cost of diagnosis procedure and use for early detection of lung cancer.

References





DOI: https://doi.org/10.17485/ijst%2F2018%2Fv11i27%2F130707