Breast Tumor Recognition Based on Multiple Support Vector Machine

Abstract:

In order to solve unfixed size and individual difference with the breast tumor, this paper provides a method of Multi-Support Vector Machine (MSVM) for breast tumor recognition. We take Support Vector Machine (SVM) on the eight direction of bump area to generate vector classifier and select Gauss kernel function as kernel function. The breast tumor recognition accuracy can reach 97.3% when σ=30. The experiment shows that the application of MSVM in breast tumor recognition can achieve good result, and provide the reliable basis for further medical diagnosis.

• Periodical: Advanced Materials Research (Volumes 490-495)
• Pages: 252-256
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.490-495.252
• Online since: March 2012
• Authors: Hong Jiang, Xi Chen, Bai Lin Liu, Yun Qing Liu
• Keywords: Edge Detection, Image Segmentation, Kernel Function, Multi-Support Vector Machines, Tumor Recognition

References

[1] LIN-Yao, TIAN-Jie, A Survey On Medical Image Segmentation Methods[J]. Pattern Recognition and Artificial Intelligence, 2002, 15(2): 192-204. (in Chinese).

[2] Wang Yuan, Shen Jia-lin . Breast tumor classification based on shape features of ultrasonic images [J]. Optics Precision Engineering, 2006, 14(2): 333-340. (in Chinese).

[3] LI Shu-nan, WAN Bai-kun, et al. A Novel ROI Extracting Technique Based on Wavelet Transform for the Detection of Micro-calcifications in Mammograms[J]. J Biomed Eng, 2005, 2(22): 360-362. (in Chinese).

[4] WEN Hao, Ma Jin-sheng, et al. On Microcalcifications Detection in Mammograms Based on Morphological Grayscale Reconstruction[J]. CT Theory and Applications, 2006, 15(2): 33-37. (in Chinese).

[5] Liu C.F. Babbs E.J. Delp. Multiresolution detection of speculated lesions in digital mammo- rgrams[J]. IEEE Transactions on Image Processing, 2001, 10(6): 874-884.

DOI: 10.1109/83.923284

[6] DENG Nai-yang, TIAN Ying-jie. The New Method in data mining: Support vector machine [M]. Beijing: Science press, 2004. (in Chinese).

[7] V.N. Vapnik. The essence of statistical learning theory(ZHANG Xue-gong translation)[M]. Beijing: Tsinghua University Press, 2000. (in Chinese).

[8] ZHU Jia-qun. Support vector machine and application of support vector machine technol- ogy in image segmentation of medical image visualization[D]. Nanjing University of Science & Technology, 2007. (in Chinese)Infor.

[8] .

[9] DUAN Rui, GUAN Yi-hong. Multi-threshold value segmentation approach for medical images[J]. Journal of Computer Applications, 2008, 28(S2): 196-197. (in Chinese).

[10] GAO Ni. Research and application of support vector machine technology in computer-aided medical diagnosing system for breast cancer[D]. Northwest University, 2009. (in Chinese).