You are viewing a javascript disabled version of the site. Please enable Javascript for this site to function properly.
Go to headerGo to navigationGo to searchGo to contentsGo to footer
In content section. Select this link to jump to navigation

Tuning to optimize SVM approach for assisting ovarian cancer diagnosis with photoacoustic imaging

Issue title: Frontiers in Biomedical Engineering and Biotechnology – Proceedings of the 4th International Conference on Biomedical Engineering and Biotechnology, 18–21 August 2015, Shanghai, China

Guest editors: Feng Liu, Dong-Hoon Lee, Ricardo Lagoa and Sandeep Kumar

Article type: Research Article

Authors: Wang, Ruia | Li, Ruia; * | Lei, Yanyana | Zhu, Quingb

Affiliations: [a] Key Laboratory of Precision Opto-Mechatronics Technology, Ministry of Education, The School of Istrumentation Science and Opto-Electronics Engineering, Beihang University, Beijing, 100191, China | [b] Department of Electrical and Computer Engineering, University of Connecticut, 371 Fairfield Way, U-2157, 06269 CT, Storrs, USA

Correspondence: [*] Address for correspondence: Rui Li, The School of Instrumentation Science and Opto-Electronics Engineering, Beihang University, Beijing, 100191, China. Tel.: +86 010-82338896; Fax: +86 010-82338896; E-mail: [email protected].

Keywords: Support vector machines, ovarian cancer detection, feature selection, correlation filter, SVM-RFE

DOI: 10.3233/BME-151392

Journal: Bio-Medical Materials and Engineering, vol. 26, no. s1, pp. S975-S981, 2015

Published: 2015
Get PDF open access

Support vector machine (SVM) is one of the most effective classification methods for cancer detection. The efficiency and quality of a SVM classifier depends strongly on several important features and a set of proper parameters. Here, a series of classification analyses, with one set of photoacoustic data from ovarian tissues ex vivo and a widely used breast cancer dataset- the Wisconsin Diagnostic Breast Cancer (WDBC), revealed the different accuracy of a SVM classification in terms of the number of features used and the parameters selected. A pattern recognition system is proposed by means of SVM-Recursive Feature Elimination (RFE) with the Radial Basis Function (RBF) kernel. To improve the effectiveness and robustness of the system, an optimized tuning ensemble algorithm called as SVM-RFE(C) with correlation filter was implemented to quantify feature and parameter information based on cross validation. The proposed algorithm is first demonstrated outperforming SVM-RFE on WDBC. Then the best accuracy of 94.643% and sensitivity of 94.595% were achieved when using SVM-RFE(C) to test 57 new PAT data from 19 patients. The experiment results show that the classifier constructed with SVM-RFE(C) algorithm is able to learn additional information from new data and has significant potential in ovarian cancer diagnosis.

Show more