Your browser doesn't support javascript.
Human-level COVID-19 diagnosis from low-dose CT scans using a two-stage time-distributed capsule network.
Afshar, Parnian; Rafiee, Moezedin Javad; Naderkhani, Farnoosh; Heidarian, Shahin; Enshaei, Nastaran; Oikonomou, Anastasia; Babaki Fard, Faranak; Anconina, Reut; Farahani, Keyvan; Plataniotis, Konstantinos N; Mohammadi, Arash.
  • Afshar P; Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, Canada.
  • Rafiee MJ; Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada.
  • Naderkhani F; Department of Medicine and Diagnostic Radiology, McGill University Health Center-Research Institute, Montreal, QC, Canada.
  • Heidarian S; Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, Canada.
  • Enshaei N; Department of Electrical and Computer Engineering, Concordia University, Montreal, QC, Canada.
  • Oikonomou A; Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, Canada.
  • Babaki Fard F; Department of Medical Imaging, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, Canada.
  • Anconina R; Faculty of Medicine, University of Montreal, Montreal, QC, Canada.
  • Farahani K; Department of Medical Imaging, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, Canada.
  • Plataniotis KN; Center for Biomedical Informatics and Information Technology, National Cancer Institute (NCI), Rockville, MD, USA.
  • Mohammadi A; Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada.
Sci Rep ; 12(1): 4827, 2022 03 22.
Article in English | MEDLINE | ID: covidwho-1758372
ABSTRACT
Reverse transcription-polymerase chain reaction is currently the gold standard in COVID-19 diagnosis. It can, however, take days to provide the diagnosis, and false negative rate is relatively high. Imaging, in particular chest computed tomography (CT), can assist with diagnosis and assessment of this disease. Nevertheless, it is shown that standard dose CT scan gives significant radiation burden to patients, especially those in need of multiple scans. In this study, we consider low-dose and ultra-low-dose (LDCT and ULDCT) scan protocols that reduce the radiation exposure close to that of a single X-ray, while maintaining an acceptable resolution for diagnosis purposes. Since thoracic radiology expertise may not be widely available during the pandemic, we develop an Artificial Intelligence (AI)-based framework using a collected dataset of LDCT/ULDCT scans, to study the hypothesis that the AI model can provide human-level performance. The AI model uses a two stage capsule network architecture and can rapidly classify COVID-19, community acquired pneumonia (CAP), and normal cases, using LDCT/ULDCT scans. Based on a cross validation, the AI model achieves COVID-19 sensitivity of [Formula see text], CAP sensitivity of [Formula see text], normal cases sensitivity (specificity) of [Formula see text], and accuracy of [Formula see text]. By incorporating clinical data (demographic and symptoms), the performance further improves to COVID-19 sensitivity of [Formula see text], CAP sensitivity of [Formula see text], normal cases sensitivity (specificity) of [Formula see text] , and accuracy of [Formula see text]. The proposed AI model achieves human-level diagnosis based on the LDCT/ULDCT scans with reduced radiation exposure. We believe that the proposed AI model has the potential to assist the radiologists to accurately and promptly diagnose COVID-19 infection and help control the transmission chain during the pandemic.
Subject(s)

Full text: Available Collection: International databases Database: MEDLINE Main subject: Artificial Intelligence / COVID-19 Type of study: Diagnostic study / Observational study / Prognostic study / Randomized controlled trials Limits: Humans Language: English Journal: Sci Rep Year: 2022 Document Type: Article Affiliation country: S41598-022-08796-8

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Artificial Intelligence / COVID-19 Type of study: Diagnostic study / Observational study / Prognostic study / Randomized controlled trials Limits: Humans Language: English Journal: Sci Rep Year: 2022 Document Type: Article Affiliation country: S41598-022-08796-8