Alliance for Pandemic Preparedness

April 29, 2020

Explanable- by-design approach for COVID-19 classification via CT-scan

Category:

Topic:

  • This paper presents a new eXplainable Deep Learning (XDL) approach to detect COVID-19 from CT. The authors suggest this new approach is more sensitive and the performance surpasses other state-of-the-art approaches such as the baseline Deep Neural Network approach. It produce highly interpretable results which may be helpful for the early detection of the disease by specialists.

Angelov and Soares. (April, 29 2020). Explanable- by-design approach for COVID-19 classification via CT-scan. Pre-print downloaded Apr 29 from https://doi.org/10.1101/2020.04.24.20078584