Automatic detection and clustering of the breast microcalcifications in three dimensions

A method for the automatic detection and the three dimensional localization of clustered microcalcifications is described. It is based on the analysis of two mammograms: one is the craniocaudal view and the other is the mediolateral view. Both mammograms are digitized with 400 dpi, their resolution allows us to have 16 pixels per millimeter, and to detect small microcalcifications (125 micrometer). The basic detection algorithm allows the correct detection of microcalcifications (MC) in the range of 90 % and even more for 2D clusters. The clusters (CL) detected on each mammogram are matched and their position is given in 3D by using a continuous deformation model of the breast tissues during their compression in the mammographic system. Clusters containing 3 or more microcalcifications can be isolated and positionned in the breast tissues. Their precise localization based on the deformation model can be used to guide the needle for biopsies.