POINT OF CARE IMAGE ANALYSIS FOR COVID-19 Daniel Yaron 1⋆ Daphna Keidar 2⋆ Elisha Goldstein 1⋆ Yair Shachar 3 Ayelet Blass Oz Frank 1 Nir Schipper 4 Nogah Shabshin 5 Ahuva Grubstein 7,8 Dror Suhami 7,8 Naama R. Bogot 6 Chedva S. Weiss 6 Eyal Sela 9 Amiel A. Dror 9 Mordehay Vaturi 7,8 Federico Mento 10 Elena Torri 11 Riccardo Inchingolo 12 Andrea Smargiassi 12 Gino Soldati 13 Tiziano Perrone 14 Libertario Demi 10 Meirav Galun 1 Shai Bagon 1 Yishai M. Elyada 15 Yonina C. Eldar 1 1 Weizmann Institute of Science, Israel 2 ETH Z ¨ urich, Switzerland 3 Eyeway Vision Ltd. Israel 4 The Hebrew University of Jerusalem, Israel 5 HaEmek Medical Center, Israel 6 Shaare Zedek Medical Cener, Israel 7 Sackler school of medicine, Tel Aviv University, Israel 8 Rabin Medical Center, Israel 9 Galilee Medical Center, Azrieli Faculty of Medicine, Bar-Ilan University, Israel 10 University of Trento, Italy 11 Bresciamed, Italy 12 Fondazione Policlinico Universitario A. Gemelli IRCCS, Italy 13 Valle del Serchio General Hospital, Italy 14 Fondazione IRCCS Policlinico San Matteo di Pavia, Italy 15 Mobileye Vision Technologies Ltd., Israel ⋆ These authors contributed equally to this work. ABSTRACT Early detection of COVID-19 is key in containing the pan- demic. 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 dis- infect, 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 COVID-19 patients using CXRs and LUS. Collabo- rating with several hospitals in Israel we collect a large dataset of CXRs and use this dataset to train a neural network ob- taining 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. 1. INTRODUCTION Coronavirus Disease 2019 (COVID-19) was declared a global pandemic [1], and has had severe economic, social and health- care consequences. In order to contain the disease, an imme- diate concern is to rapidly identify and isolate SARS-CoV-2 carriers. This requires means for mass testing of the general population, with low cost, high sensitivity and fast processing times. The prevalent test today is Reverse Transcription Poly- merase Chain Reaction (RT-PCR) [2, 3], which suffers from a number of problems: Testing reagents and kits are expen- sive and suitable for single-use only, processing the samples requires dedicated personnel and equipment, and it can take hours or days to obtain results. Most significantly, the test has a limited sensitivity rate of as low as 71% [4, 5]. Due to these shortcomings, finding alternative testing and identifi- cation methods is crucial. A strong candidate is diagnosis of This project is partially supported by the Weizmann Institute COVID-19 Fund, Manya Igel Centre for Biomedical Engineering, Carolito Stiftung, and Google Cloud COVID-19 credits program. patients based on medical imaging of the chest, since COVID- 19 presents primarily in the lower respiratory tract. Medical imaging, specifically computerized tomography (CT) scans, chest X-ray (CXR), and lung ultrasound (LUS), can provide an alternative approach, affording advantages that can readily complement the testing capabilities of RT-PCR. In the case of COVID-19, disease characteristics such as consolidations and ground-glass opacities can be identified in images of the lung [6, 7] which raises the possibility of using chest and lung imaging for detection and severity grading of COVID-19 pa- tients. Physiological pulmonary properties of COVID-19 on CT scans are typically detectable and clear to see [6]. However, the availability of CT equipment is limited both by its price and operational requirements such as rooms and staff. More- over, there is a need to decontaminate the machine between suspected COVID-19 patients, a lengthy process that results in a very slow rate of scanning. In contrast, with portable X-ray and ultrasound machines, imaging can be done rapidly and without needing to bring patients into radiography rooms. These machines are also less costly, use less radiation, and can be readily distributed and deployed to point-of-care (POC) lo- cations outside hospitals and primary care centers. The draw- back of these modalities is that their analysis requires quali- fied personnel and the unique characteristics of the prognostic properties of the images can make them much harder to ana- lyze than CT scans. In this paper we consider a combination of signal process- ing and deep learning tools to develop deep network architec- tures that can lead to high detection rates of COVID-19 and to severity grading of disease from POC imaging using X-ray and ultrasound. Early approaches to develop detection meth- ods based on X-ray used data from publicly available image sources relied on limited data containing compressed images with lack of detail, and coming from many different makes and models of x-ray machines [8, 9, 10]. This illustrates one of the main challenges in this field, namely the collection of large amounts of COVID-19 positive and negative images of full resolution and similar sources. Notably, one recent ef- fort has shown more reliable results based on a larger dataset 8153 978-1-7281-7605-5/21/$31.00 ©2021 IEEE ICASSP 2021 ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | 978-1-7281-7605-5/20/$31.00 ©2021 IEEE | DOI: 10.1109/ICASSP39728.2021.9413687