A Graph-Based Method for Detecting and Classifying Clusters in Mammographic Images
In this paper we propose a method based on a graph-theoretical cluster analysis for automatically finding and classifying clusters of microcalcifications in mammographic images, starting from the output of a microcalcification detection phase. This method does not require the user to provide either the expected number of clusters or any threshold values, often with no clear physical meaning, as other algorithms do.
The proposed approach has been tested on a standard database of 40 mammographic images and has demonstrated to be very effective, even when the detection phase gives rise to several false positives.
KeywordsMinimum Span Tree Multi Layer Perceptron Clear Physical Meaning Cluster Classification Cluster Detection
- 1.Lanyi, M.: Diagnosis and differential diagnosis of breast calcifications. Springer, New York (1986)Google Scholar
- 2.De Yoldi, G.C., Viganotti, G., Bergonzi, S., Gerranti, C., Piragine, G., Cassano, E., Barberini, M., Rilke, F., Veronesi, U.: Le microcalcificazioni nei carcinomi mammari non palpabili. Analisi di 427 casi (in Italian), Rad. Med., no. 85, pp. 611–614 (1993)Google Scholar
- 3.Lauria, A., Palmiero, R., Imbriaco, M., Selva, G., et al.: Analysis of radiologist performance with and without a CAD system. In: European Congress of Radiology (2002)Google Scholar
- 5.Thangavel, K., Karnan, M., Sivakumar, R., Kaja Mohideen, A.: Automatic Detection of Microcalcification in Mammograms – A Review. International Journal on Graphics, Vision and Image Processing 5, 31–61 (2005)Google Scholar
- 7.Horowitz, E., Sahni, S.: Fundamentals of Computer Algorithms. Computer Science Press (1978)Google Scholar
- 10.D’Elia, C., Marrocco, C., Molinara, M., Poggi, G., Scarpa, G., Tortorella, F.: Detection of Microcalcifications Clusters in Mammograms through TS-MRF Segmentation and SVM-based Classification. In: IEEE International Conference on Pattern Recognition, vol. 3, pp. 742–745 (2004)Google Scholar
- 14.Papadopoulos, A., Fotiadis, D.I., Likas, A.: Characterization of clustered microcalcifications in digitized mammograms using neural networks and support vector machines. Artificial Intelligence in Medicine (in press, 2006)Google Scholar