During the acquisition of a mammogram the breast is compressed between the compression paddle and the support table. When compression is applied the upper plate is tilted which results in variation in breast thickness from the chest wall to the breast margin. Variation in breast thickness in uences the grey level values of the image and hampers image analysis, such as volumetric breast density estimation. In this paper we present and compare two methods that estimate and correct image tilt. The first method estimates tilt from fatty tissue regions. The second method is based on the entropy of the grey level distribution of the image. 1876 images are obtained from relatively young women with a high breast density on average. The tilt correction methods are evaluated by assessing their accuracies in estimating artificial tilts that are added to the images that are expected to have only a small tilt. On average both methods are able to estimate the artificial tilt, although the accuracy is relatively low. To the best of our knowledge this is the first paper that presents and validate tilt correction methods on individual mammograms. We expect that results will be better in screening populations which forms the majority of cases utilised in image analysis.
Comparison of Tilt Correction Methods in Full Field Digital Mammograms
M. Kallenberg and N. Karssemeijer
IWDM '10: Proceedings of the 10th international workshop on Digital Mammography 2010:191-196.