TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification

The application of artificial intelligence (AI) to various medical subfields has been a popular topic research in recent years. In particular, deep learning widely used and proven effective many cases. Topological data analysis (TDA)—a rising field at the intersection mathematics, statistics, computer science—offers new insights into data. this work, we develop novel architecture that call TopoResNet integrates topological information residual neural network architecture. To demonstrate TopoResNet, apply it skin lesion classification problem. We find improves accuracy stability training process.