Show simple item record

dc.contributor.advisorKendall, Edward J.en_US
dc.creatorErickson, Carissa Michelleen_US
dc.date.accessioned2005-07-29T15:32:28Zen_US
dc.date.accessioned2013-01-04T04:48:56Z
dc.date.available2005-08-02T08:00:00Zen_US
dc.date.available2013-01-04T04:48:56Z
dc.date.created2005-06en_US
dc.date.issued2005-06-30en_US
dc.date.submittedJune 2005en_US
dc.identifier.urihttp://hdl.handle.net/10388/etd-07292005-153228en_US
dc.description.abstractThe overarching goal of this project was to improve breast cancer screening protocols first by collecting small angle x-ray scattering (SAXS) images from breast biopsy tissue, and second, by applying pattern recognition techniques as a semi-automatic screen. Wavelet based features were generated from the SAXS image data. The features were supplied to a classifier, which sorted the images into distinct groups, such as “normal” and “tumor”. The main problem in the project was to find a set of features that provided sufficient separation for classification into groups of “normal” and “tumor.” In the original SAXS patterns, information useful for classification was obscured. The wavelet maps allowed new scale-based information to be uncovered from each SAXS pattern. The new information was subsequently used to define features that allowed for classification. Several calculations were tested to extract useful features from the wavelet decomposition maps. The wavelet map average intensity feature was selected as the most promising feature. The wavelet map intensity feature was improved by using pre-processing to remove the high central intensities from the SAXS patterns, and by using different wavelet bases for the wavelet decomposition. The investigation undertaken for this project showed very promising results. A classification rate of 100% was achieved for distinguishing between normal samples and tumor samples. The system also showed promising results when tested on unrelated MRI data. In the future, the semi-automatic pattern recognition tool developed for this project could be automated. With a larger set of data for training and testing, the tool could be improved upon and used to assist radiologists in the detection and classification of breast lesions.en_US
dc.language.isoen_USen_US
dc.subjectNaive Bayesian Classifieren_US
dc.subjectSynchrotronen_US
dc.subjectDiffractionen_US
dc.subjectMultiresolutionen_US
dc.titleAutomated detection of breast cancer using SAXS data and wavelet featuresen_US
thesis.degree.departmentBiomedical Engineeringen_US
thesis.degree.disciplineBiomedical Engineeringen_US
thesis.degree.grantorUniversity of Saskatchewanen_US
thesis.degree.levelMastersen_US
thesis.degree.nameMaster of Science (M.Sc.)en_US
dc.type.materialtexten_US
dc.type.genreThesisen_US
dc.contributor.committeeMemberThomlinson, Billen_US
dc.contributor.committeeMemberGander, Roberten_US
dc.contributor.committeeMemberEramian, Mark G.en_US
dc.contributor.committeeMemberBolton, Ronald J.en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record