Generating Interpretable Patterns for Biomedical Image Classification
Dongwoo Kang, Sunung Kim, Yoonsik Jung, Hong Seo Ryoo · 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · 2021
In biomedical sciences, precise classification of data from normal and abnormal individuals is crucial. In this study, we address analysis of biomedical image data exploiting LAD which is a mathematical optimization-based supervised learning methodology. We propose an interpretable pattern recognition algorithm through set covering problem for practically applying large-scale biomedical data. To demonstrate the explainability and testing performance of our approach, we present computational results from analyzing breast cancer image data extracted from [3].