Advertisement

Breast Compression

  • Ralph Highnam
  • Michael Brady
Part of the Computational Imaging and Vision book series (CIVI, volume 14)

Abstract

This chapter analyses the effects of breast compression in mammography. There are three key reasons for our interest:
  1. (i)

    We believe that it might be possible to determine hardness of tissue and tissue connectivity on the basis of knowing how the tissue moves and deforms with compression. We describe in this chapter a technique which we have dubbed “differential compression mammography” that aims to show movement and deformation.

     
  2. (ii)

    Automated image analysis must be robust to changes in the imaging conditions and to changes in the breast which are not clinically significant. Earlier chapters have dealt with modelling the mammographic imaging process in order to ensure robustness to changes in the imaging condition. In this chapter, we consider robustness to changes in breast compression and show the improvements to image analysis possible using h int .

     
  3. (iii)

    Matching between cranio-caudal and medio-lateral oblique mammograms is difficult, not because of the change in viewing angle; but because of the change in direction of the breast compression. We report our initial work1 on matching between cranio-caudal and medio-lateral oblique image pairs which has already proved to be useful to radiologists, for whom establishing such correspondences turns out to be remarkably hard.

     

Keywords

Fatty Tissue Automatic Exposure Control Average Pixel Compression Model Breast Thickness 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media Dordrecht 1999

Authors and Affiliations

  • Ralph Highnam
    • 1
  • Michael Brady
    • 1
  1. 1.Department of Engineering ScienceOxford UniversityOxfordUK

Personalised recommendations