AUTHOR=Makrogiannis Sokratis , Zheng Keni , Harris Chelsea 

TITLE=Discriminative Localized Sparse Approximations for Mass Characterization in Mammograms

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.725320

DOI=10.3389/fonc.2021.725320

ISSN=2234-943X

ABSTRACT=Breast cancer is the most common cancer among women both in developed and developing countries. Early detection and diagnosis of breast cancer may reduce its mortality and improve the quality of life. Computer-aided detection (CADe) and computer-aided diagnosis (CADx) techniques have shown promise for reducing the burden of human expert reading and improve the accuracy and reproducibility of results. One significant application is for breast cancer screening using mammograms.
In machine learning and image processing research, sparse analysis techniques have produced relevant results for representing and recognizing imaging patterns. In this work we propose methods for label-specific and label-consistent dictionary learning to improve the separation of benign breast masses from malignant breast masses in mammograms. We integrated these approaches into our Spatially Localized Ensemble Sparse Analysis (SLESA) methodology. We performed 10-, and 30-fold cross validation experiments on multiple mammography datasets to evaluate the classification performance of our methodology in comparison to deep learning models and conventional sparse representation. Our results indicate that the proposed sparse analysis can be a useful component for breast cancer screening applications.