Abstract | ||
---|---|---|
This work aims to explore whether we can improve the accuracy of an SVM classifier for microcalcification (MC) detection by incorporating prior knowledge of MCs in mammograms. Based on the fact that MCs are inherently invariant to their spatial orientation in a mammogram, we consider two different techniques for incorporating rotation invariance into SVM, of which one is virtual support vector SVM (VSVM) and the other is tangent vector SVM (TV-SVM). The experiment results show that both techniques can improve the performance in discriminating MCs from the image background, and TV-SVM achieved the best performance. In particular, the sensitivity was 96.3% for TV-SVM, compared to 94.5% for SVM, when the false positive rate was at 0.5%. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ICIP.2012.6467490 | ICIP |
Keywords | DocType | ISSN |
mammography,computer-aided diagnosis (cad),rotation invariance,performance improvement,image background,svm classifier,support vector machine (svm),vsvm,virtual svm,virtual support vector machine,cancer,image classification,tv-svm,spatial orientation,virtual support vector svm,mammogram,mc detection,microcalcification detection,tangent vector svm,support vector machines,computer-aided diagnosis,medical image processing | Conference | 1522-4880 E-ISBN : 978-1-4673-2532-5 |
ISBN | Citations | PageRank |
978-1-4673-2532-5 | 1 | 0.36 |
References | Authors | |
8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yan Yang | 1 | 1 | 0.36 |
Juan Wang | 2 | 1 | 0.36 |
Yongyi Yang | 3 | 1409 | 140.74 |