Deep learning for Classification and Localization of COVID-19 Markers in point-of-care Lung Ultrasound

Deep learning (DL) has proved successful in medical imaging and, in the wake of the recent COVID19 pandemic, some studies have started to investigate DL based solutions for the assisted diagnosis of lung diseases. While existing works focus on CT scans, this project studies the application of DL techniques for the analysis of lung ultrasonography images. 

Specifically, we present a novel fully-annotated dataset of LUS images collected from several Italian hospitals, with labels indicating the degree of disease severity at a frame-level, video level, and pixel-level. In proposed system a deep network, derived from Spatial Transformer Networks, which simultaneously predicts the disease severity score associated to input frame and provides localization of pathological artefacts in a weakly-supervised way. Finally, we benchmark state of the art deep models for estimating pixel-level segmentations of COVID-19 imaging biomarkers.

Keywords: COVID-19, Lung Ultrasound, Deep Learning, CT scan.