COVID-19 detection through X-Ray chest images
Diego Hernandez, Rodrigo Pereira, Petia Georgevia
Abstract
The new COVID-19 virus has proven to be a real threat to the humanity. In this work we propose a machine learning approach to identify cases of infected patients through X-Ray images of their lungs. Due to the scarceness of the available data and limited computational power, we come up with two approaches: i) Build a custom Convolutional Neural Network (CNN) from scratch, with large data set of historical not COVID19 pulmonary X-Rays. Tune the final layers with COVID-19 XRay images; ii) Apply transfer learning through pre-trained CNN models (ResNet, VGG, DenseNet) and fine tuning with COVID19 data. The second approach allowed us to reach around 90% accuracy on this challenging task.
Topics & Concepts
Coronavirus disease 2019 (COVID-19)Computer scienceSevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2)Artificial intelligenceMedicineInternal medicineInfectious disease (medical specialty)DiseaseCOVID-19 diagnosis using AIRadiomics and Machine Learning in Medical ImagingAdvanced X-ray and CT Imaging