Detecting COVID-19 from chest computed tomography scans using AI-driven android application

• Type of Material: Article
• Authors: Sagar Amin, Emory University; Muhammad Naeem, Emory University; A Verma, Natl Inst Technol; M Saha, Emory University
• Language: English
• Date: 2022-04-01
• Publisher: PERGAMON-ELSEVIER SCIENCE LTD
• Publication Version: Final Published Version
• Copyright Statement: Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. T
• Final Published Version (URL): http://dx.doi.org/10.1016/j.compbiomed.2022.105298
• Title of Journal or Parent Work: COMPUTERS IN BIOLOGY AND MEDICINE
• Volume: 143
• Start Page: 105298
• End Page: 105298
• Keywords: Artificial intelligence; Life Sciences & Biomedicine; SEGMENTATION; Computer Science; Deep learning; Life Sciences & Biomedicine - Other Topics; COVID-19; Technology; Mathematical & Computational Biology; Computed tomography; Android application; Engineering; Engineering, Biomedical; Lung; Biology; Science & Technology; Computer Science, Interdisciplinary Applications
• Research Categories: Computer Science; Health Sciences, Radiology

Abstract

The COVID-19 (coronavirus disease 2019) pandemic affected more than 186 million people with over 4 million deaths worldwide by June 2021. The magnitude of which has strained global healthcare systems. Chest Computed Tomography (CT) scans have a potential role in the diagnosis and prognostication of COVID-19. Designing a diagnostic system, which is cost-efficient and convenient to operate on resource-constrained devices like mobile phones would enhance the clinical usage of chest CT scans and provide swift, mobile, and accessible diagnostic capabilities. This work proposes developing a novel Android application that detects COVID-19 infection from chest CT scans using a highly efficient and accurate deep learning algorithm. It further creates an attention heatmap, augmented on the segmented lung parenchyma region in the chest CT scans which shows the regions of infection in the lungs through an algorithm developed as a part of this work, and verified through radiologists. We propose a novel selection approach combined with multi-threading for a faster generation of heatmaps on a Mobile Device, which reduces the processing time by about 93%. The neural network trained to detect COVID-19 in this work is tested with a F1 score and accuracy, both of 99.58% and sensitivity of 99.69%, which is better than most of the results in the domain of COVID diagnosis from CT scans. This work will be beneficial in high-volume practices and help doctors triage patients for the early diagnosis of COVID-19 quickly and efficiently.