2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDSS-4.2
Paper Title POINT OF CARE IMAGE ANALYSIS FOR COVID-19
Authors Daniel Yaron, Weizmann Institute of Science, Israel; Daphna Keidar, ETH Zurich, Switzerland; Elisha Goldstein, Weizmann Institute of Science, Israel; Yair Shachar, Eyeway Vision Ltd, Israel; Ayelet Blass, Oz Frank, Weizmann Institute of Science, Israel; Nir Schipper, The Hebrew University of Jerusalem, Israel; Nogah Shabshin, HaEmek Medical Center, Israel; Ahuva Grubstein, Dror Suhami, Sackler school of medicine Tel Aviv University, Rabin Medical Center, Israel; Naama R. Bogot, Chedva Weiss, Shaare Zedek Medical Cener, Israel; Eyal Sela, Amiel A. Dror, Galilee Medical Center, Azrieli Faculty of Medicine, Bar-Ilan University, Israel; Mordehay Vaturi, Sackler school of medicine Tel Aviv University, Rabin Medical Center, Israel; Federico Mento, University of Trento, Italy; Elena Torri, Bresciamed, Italy; Riccardo Inchingolo, Andrea Smargiassi, Fondazione Policlinico Universitario A. Gemelli IRCCS, Italy; Gino Soldati, Valle del Serchio General Hospital, Italy; Tiziano Perrone, Fondazione IRCCS Policlinico San Matteo di Pavia, Italy; Libertario Demi, University of Trento, Italy; Meirav Galun, Shai Bagon, Weizmann Institute of Science, Israel; Yishai M. Elyada, Mobileye Vision Technologies Ltd, Israel; Yonina C. Eldar, Weizmann Institute of Science, Israel
SessionSS-4: Data Science Methods for COVID-19
LocationGather.Town
Session Time:Tuesday, 08 June, 16:30 - 17:15
Presentation Time:Tuesday, 08 June, 16:30 - 17:15
Presentation Poster
Topic Special Sessions: Data Science Methods for COVID-19
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract Early detection of COVID-19 is key in containing the pandemic. Disease detection and evaluation based on imaging is fast and cheap and therefore plays an important role in COVID-19 handling. COVID-19 is easier to detect in chest CT, however, it is expensive, non-portable, and difficult to disinfect, making it unfit as a point-of-care (POC) modality. On the other hand, chest X-ray (CXR) and lung ultrasound (LUS) are widely used, yet, COVID-19 findings in these modalities are not always very clear. Here we train deep neural networks to significantly enhance the capability to detect, grade and monitor COVID19 patients using CXRs and LUS. Collaborating with several hospitals in Israel we collect a large dataset of CXRs and use this dataset to train a neural network obtaining above 90% detection rate for COVID-19. In addition, in collaboration with ULTRa (Ultrasound Laboratory Trento, Italy) and hospitals in Italy we obtained POC ultrasound data with annotations of the severity of disease and trained a deep network for automatic severity grading.