SARS-CoV-2

An study on the suitability of different pooling operators for Convolutional Neural Networks in the prediction of COVID-19 through chest x-ray image analysis
The COVID-19 pandemic since 2019 has strained healthcare globally. In such a context, chest x-ray images are vital for diagnosis. Automating their classification through Convolutional Neural Networks (CNNs) can save time. In this paper we propose a CNN-based pipeline for diagnosis that focuses on improving information fusion in pooling layers with new aggregation functions. Replacing traditional CNN processes yields varied model behaviors, useful for prioritizing metrics like precision or recall.
Iosu Rodríguez Martínez, Pablo Ursua-Medrano, Javier Fernandez, Zdenko Takáč, Humberto Bustince
Cite DOI