Segmentation of microcalcifications in X-ray mammograms using
entropy thresholding

M. Melloul and L. Joskowicz

School of Computer Science and Engineering 
The Hebrew University of Jerusalem Jerusalem 91904, ISRAEL

Abstract

We describe a new algorithm for microcalcification segmentation in
mammographic X-ray images.  The algorithm detects microcalcifications in
two steps. First, it removes background tissue with a multiscale
morphological operation.  Then, it applies entropy thresholding based on a
3-dimensional co-occurrence matrix.  Unlike existing methods, ours is fully
automatic, parameter-free, and independent of local statistics.  To test
its efficacy, we applied it to images from the Mammographic Image Analysis
Society database and analyzed the results with the assistance of a
clinician.  We obtained detection rates of 93.75% of true positives, 6.25%
of false positives, and 2% of false negatives.

Keywords: X-ray mammograms, microcalcification segmentation, entropy thresholding.


Published in: Proc. of the 16th Int. Congress on Computer-Assisted
Radiology and Surgery, CARS 2002, H.U. Lemke et. al. editors, Elsevier
2002, pp. 490-495.