Deep learning-driven strategies for COVID-19 Detection and Risk Stratification

A critical step in the fight against COVID-19 is effective screening of infected patients for infection detection and risk assessment. While viral testing such as rt-PCR is the gold standard for infection detection as it is highly specific, it is moderately sensitive and is a very time-consuming, laborious, and complicated manual process that is in short supply. While faster viral testing methods are becoming available, they remain in short supply and do not provide important information on severity and extent. The goal of the proposed project is to investigate and develop deep-learning strategies for COVID-19 detection and risk stratification based on chest radiography. The objectives are designing tailored deep neural networks for COVID-19 detection for both chest X-ray and CT; risk stratification for both chest X-ray and CT, as well as strategies for secure clinical decision support.

Faculty Supervisor:

Alexander Wong;John Zelek

Student:

Alex MacLean;James Lee

Partner:

Rogers Communication

Discipline:

Engineering

Sector:

University:

University of Waterloo

Program: