PROJECT TITLE :
Topological Modeling and Classification of Mammographic Microcalcification Clusters
Goal: The presence of microcalcification clusters is a primary sign of breast cancer; however, it is tough and time consuming for radiologists to classify microcalcifications as malignant or benign. During this paper, a unique methodology for the classification of microcalcification clusters in mammograms is proposed. Methods: The topology/connectivity of individual microcalcifications is analyzed within a cluster using multiscale morphology. This is often distinct from existing approaches that tend to focus on the morphology of individual microcalcifications and/or world (statistical) cluster features. A set of microcalcification graphs are generated to represent the topological structure of microcalcification clusters at different scales. Subsequently, graph theoretical options are extracted, that represent the topological feature house for modeling and classifying microcalcification clusters. $k$-nearest-neighbors-based classifiers are used for classifying microcalcification clusters. Results: The validity of the proposed technique is evaluated using 2 well-known digitized datasets (MIAS and DDSM) and a full-field digital dataset. High classification accuracies (up to 96%) and good ROC results (area below the ROC curve up to zero.ninety six) are achieved. A full comparison with related publications is provided, which includes an immediate comparison. Conclusion: The results indicate that the proposed approach is able to outperform the current state-of-the-art ways. Significance: This study shows that topology modeling is a vital tool for microcalcification analysis not solely as a result of of the improved classification accuracy but additionally because the topological measures can be linked to clinical understanding.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here