[u' @inproceedings{almeida_lung_2020, address = {Las Vegas, USA}, title = {Lung {Ultrasound} for {Point}-of-{Care} {COVID}-19 {Pneumonia} {Stratification}: {Computer}-{Aided} {Diagnostics} in a {Smartphone}. {First} {Experiences} {Classifying} {Semiology} from {Public} {Datasets}}, url = {https://2020.ieee-ius.org/}, abstract = {Lung ultrasound (LUS) has demonstrated potential in managing pneumonia patients, and is actively used at the point-of-care in COVID-19 patient stratification. However, image interpretation is presently both time-consuming and operator-dependent. We explore computer-aided diagnostics of pneumonia semiology based on light-weight neural networks (MobileNets). For proof-of-concept, multi-task learning is performed from online available COVID-19 datasets, for which semiology (overall abnormality, B-lines, consolidations and pleural thickening) is annotated by two radiologists. Initial results suggest that individual indications can be classified with good performance in a smartphone. Neural networks may also help to reduce inter-reader variability and objectivize LUS interpretation, especially for early-stage pathological indications.}, booktitle = {Proceedings of the {International} {Ultrasound} {Symposium} 2020}, author = {Almeida, Aitor and Bilbao-Jayo, Aritz and Ruby, Lisa and Rominger, Marga and L\xf3pez-De-Ipi\xf1a, Diego and Dahl, Jeremy and El Kaffas, Ahmed and Sanabria, Sergio}, month = aug, year = {2020}, keywords = {AI for health, Artificial Intelligence, ISI, LUS, POCUS, b-lines, convolutional networks, covid19, image processing, lung ultrasound, machine learning, mobilenet, pneumonia, point-of-care ultrasound, semiology, subpleural consolidations, ultrasound}, } ']