Abstract

A mediolateral oblique (MLO) mammogram image contains far more than just an image of the breast. A film clip is generally present along with imaging artefacts and background noise. Before any computer analysis of the mammogram begins, the identification and extraction of the breast area is necessary – a technique called global segmentation. This paper describes in detail a fully automated algorithm for global segmentation of MLO mammograms to create an accurate breast region without user intervention.

Keywords. mediolateral oblique; mammogram; global segmentation; image processing; image analysis

Download: PDF Document (89 Kb)

CRAIG HENDERSON holds a B.Sc. Honours Degree in Computing for Real Time Systems, has been a professional software engineer for over 11 years. His interests include systems programming, enterprise software and modern generic programming. He works in the UK as a Software Development Manager. He can be contacted at cdm.henderson@googlemail.com.

See other papers by Craig.