Improving SVM classifier with prior knowledge in microcalcification detection1

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%.

[1]  Joachim Dengler,et al.  Segmentation of Microcalcifications in Mammograms , 1991, DAGM-Symposium.

[2]  Ling Guan,et al.  A CAD System for the Automatic Detection of Clustered Microcalcification in Digitized Mammogram Films , 2000, IEEE Trans. Medical Imaging.

[3]  Robert M. Nishikawa,et al.  Relevance vector machine for automatic detection of clustered microcalcifications , 2005, IEEE Transactions on Medical Imaging.

[4]  Nico Karssemeijer,et al.  Normalization of local contrast in mammograms , 2000, IEEE Transactions on Medical Imaging.

[5]  Robin N. Strickland,et al.  Wavelet transforms for detecting microcalcifications in mammograms , 1996, IEEE Trans. Medical Imaging.

[6]  U. G. Dailey.  Cancer,Facts and Figures about. , 2022, Journal of the National Medical Association.

[7]  Bernhard Schölkopf,et al.  Prior Knowledge in Support Vector Kernels , 1997, NIPS.

[8]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[9]  Bernhard Schölkopf,et al.  Training Invariant Support Vector Machines , 2002, Machine Learning.

[10]  D. Sanders.  Diagnosis and Differential Diagnosis of Breast Calcifications , 1988 .

[11]  Nikolas P. Galatsanos,et al.  A support vector machine approach for detection of microcalcifications , 2002, IEEE Transactions on Medical Imaging.

[12]  Bernhard Schölkopf,et al.  Incorporating invariances in nonlinear Support Vector Machines , 2001, NIPS 2001.

[13]  Gwo Giun Lee,et al.  On Digital Mammogram Segmentation and Microcalcification Detection Using Multiresolution Wavelet Analysis , 1997, CVGIP Graph. Model. Image Process..

[14]  Chronic Disease Division.  Cancer facts and figures , 2010 .

[15]  Bernhard Schölkopf,et al.  Incorporating Invariances in Non-Linear Support Vector Machines , 2001, NIPS.