A SARS-CoV-2 Microscopic Image Dataset with Ground Truth Images and Visual Features

2020/04/07 by Chen Li, Jiawei Zhang, Li, Chen +7
Engineering · Medicine · #COVID-19 diagnosis using AI #FOS: Electrical engineering #Image Processing Techniques and Applications #Image and Video Processing (eess.IV) #SARS-CoV-2 and COVID-19 Research #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2004.03416

openalex publication_date 2020/04/07 · openalex created_date 2020/05/13 · openalex updated_date 2026/07/28

Abstract

SARS-CoV-2 has characteristics of wide contagion and quick propagation velocity. To analyse the visual information of it, we build a SARS-CoV-2 Microscopic Image Dataset (SC2-MID) with 48 electron microscopic images and also prepare their ground truth images. Furthermore, we extract multiple classical features and novel deep learning features to describe the visual information of SARS-CoV-2. Finally, it is proved that the visual features of the SARS-CoV-2 images which are observed under the electron microscopic can be extracted and analysed.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• The continuing 2019-nCoV epidemic threat of novel coronaviruses to global health — The latest 2019 novel coronavirus outbreak in Wuhan, China
• Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study

Related

• SARS-CoV-2 Result Interpretation based on Image Analysis of Lateral Flow Devices
• Classification of COVID-19 via Homology of CT-SCAN
• Early Screening of SARS-CoV-2 by Intelligent Analysis of X-Ray Images
• Deep Learning for Reliable Classification of COVID-19, MERS, and SARS from Chest X-Ray Images
• Diagnosis of COVID-19 disease using CT scan images and pre-trained models