| Περίληψη: | This Master Thesis presents a novel classification approach for microcalcifications (MCs) extracted from core biopsy tissue samples digitized using micro-CT, a high-resolution 3D imaging modality. MCs are tiny spots of calcium that may occur in the female breast. Although they are common in healthy woman, they are often an early sign of breast cancer. The shape of the MCs is an important factor used to discriminate between benign and malignant abnormalities. However, the current standard imaging modalities (i.e. mammography) are not efficient for a clear shape based analysis. In case of suspiciousness, a biopsy is conducted and the extracted tissue is anatomopathologically investigated for the presence of cancer cells. Nevertheless, only 20-35% of biopsies turn out to be positive. As such, the question whether some unnecessary biopsies can be avoided if the shape of the MCs could be analysed in more detail has been raised. In addition, the MCs themselves are not analysed, but they are characterised as benign (or malignant) according to whether they were found into a benign (or malignant) tissue. As a result, there is a ground truth for the tissue samples but not for the individual MCs. So, when a classifier of a Computer Aided Diagnosis System will be asked to classify a MC according to its shape, there will be a degree of ambiguity and uncertainty. This master thesis investigates whether the use of a clustering method as a preprocessing step before training the classifier could avoid the ground truth issues and could improve the obtained classification results.
|
|---|
