Statistical modelling of lines and structures in mammograms

R Zwiggelaar, T C Parr, C R M Boggis, Susan Astley, C J Taylor

Research output: Chapter in Book/Conference proceedingConference contribution

Abstract

Computer-aided mammographic prompting systems require the reliable detection of a variety of signs of cancer. The emphasis of the work described is the correct classification of linear structures in mammograms. Statistical modelling, based on principal component analysis (PCA), has been developed for describing the cross-sectional profiles of linear structures, the motivation being that the shapes of intensity profiles may be characteristic of the type of structure. PCA models have been applied to whole mammograms to obtain images in which spicules, linear structures associated with stellate lesions, are emphasised. The aim is to improve the performance of automatic stellate lesion detection by concentrating on those structures most likely to be associated with lesions.
Original languageEnglish
Title of host publication Information Processing in Medical Imaging
PublisherSpringer Nature
Pages405-410
Number of pages6
DOIs
Publication statusPublished - 1997
EventInformation Processing in Medical Imaging 1997 - Poultney, United States
Duration: 9 Jun 199713 Jun 1997

Publication series

NameLECTURE NOTES IN COMPUTER SCIENCE
PublisherSpringer
Number1230

Conference

ConferenceInformation Processing in Medical Imaging 1997
Abbreviated titleIPMI 1997
Country/TerritoryUnited States
CityPoultney
Period9/06/9713/06/97

Fingerprint

Dive into the research topics of 'Statistical modelling of lines and structures in mammograms'. Together they form a unique fingerprint.

Cite this