Mass detection algorithm based on support vector
machine and relevance feedback

doi:10.1007/s11460-008-0059-6

Front. Electr. Electron. Eng.

2008, Vol. 3

Issue (3) : 267-273 https://doi.org/10.1007/s11460-008-0059-6

Mass detection algorithm based on support vector machine and relevance feedback

WANG Ying, GAO Xinbo

School of Electronic Engineering, Xidian University;

Download: PDF(206 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract To improve the detection of mass with appearance that borders on the similarity between mass and density tissues in the breast, an support vector machine classifier based on typical features is designed to classify the region of interest (ROI). Furthermore, relevance feedback is introduced to improve the performance of support vector machines. A new mass detection scheme based on the support vector machine and the relevance feedback is proposed. Simulation experiments on mammograms illustrate that the novel support vector machine classifier based on typical features can improve the detection performance of the featureless classifier by 5%, while the introduction of relevance feedback can further improve the detection performance to about 90%.

Issue Date: 05 September 2008

Cite this article:

GAO Xinbo,WANG Ying. Mass detection algorithm based on support vector machine and relevance feedback[J]. Front. Electr. Electron. Eng., 2008, 3(3): 267-273.

URL:

https://academic.hep.com.cn/fee/EN/10.1007/s11460-008-0059-6
https://academic.hep.com.cn/fee/EN/Y2008/V3/I3/267

1	Sahiner B Chan H P Petrick N et al.Classification of mass and normal breast tissue:a convolution neural network classifier with spatial domain and textureimagesIEEE Transactions on Medical Imaging 1996 15(5)598610. doi:10.1109/42.538937
2	Wei D Chan H P Petrick N et al.False positive reduction technique for detectionof masses on digital mammograms: global and local multiresolutiontexture analysisMedical Physics 1997 24(6)903914. doi:10.1118/1.598011
3	Tourassi G D Vargas-Voracek R Catarious D M et al.Computer-assisted detection of mammographic masses:a template matching scheme based on mutual informationMedical Physics 2003 30(8)21232130. doi:10.1118/1.1589494
4	EI-Naqa I Yang Y Y Wernick M N et al.A support vector machine approach for detectionof microcalcificationsIEEE Transactionson Medical Imaging 2002 21(12)15521563. doi:10.1109/TMI.2002.806569
5	Campanini R Dongiovanni D Iampieri E et al.A novel featureless approach to mass detection indigital mammograms based on support vector machinesPhysics in Medicine & Biology 2004 49(6)961975. doi:10.1088/0031‐9155/49/6/007
6	Vapnik V N StatisticalLearning TheoryNew YorkWiley 1998
7	Ding A L Liu F Yao X Intelligent target recognition based on the support vectormachineJournal of Xidian University 2001 28(6)743746(in Chinese)
8	Wang Y Gao X B Dong Y A partial supervised mammographic masses detection methodChinese Journal of Medical Imaging Technology 2005 21(10)15721575(in Chinese)
9	EI-Naqa I Yang Y Y Galatsanos N P et al.A similarity learning approach to content-basedimage retrieval: application to digital mammographyIEEE Transactions on Medical Imaging 2004 23(10)12331244. doi:10.1109/TMI.2004.834601
10	Xu Y H Li J L Chen E H et al.A novel SVM based relevance feedback algorithm inimage retrievalComputer Engineering 2004 30(24)116118(in Chinese)
11	Guliato D Rangayyan R M Carnielli W A et al.Segmentation of breast tumors in mammograms by fuzzyregion growingIn: Proceedings of the 20thAnnual International Conference of the IEEE Engineering in Medicineand Biology Society, Hong Kong, China. IEEE 1998 210021005
12	Gonzalez R C Woods R E Digital Image Processing2nd Edition New JerseyPrentice Hall 2002
13	Miller P Astley S Classification of breast tissueby textural analysisImage and Vision Computing 1992 10(5)277282. doi:10.1016/0262‐8856(92)90042‐2

Viewed

Full text

Abstract

Cited

Shared

Discussed