Matteo Polsinelli, Luigi Cinque, Giuseppe Placidi
2020.4.24PATTERN RECOGNITION LETTERS
tlooto Summary
A light CNN for efficient detection of COVID-19 from chest CT scans is proposed that is comparable with that of more complex CNN designs and 10 times better than more complex CNNs using pre-processing.
Abstract
Highlights • A light CNN for efficient detection of COVID-19 from chest CT scans is proposed.• The accuracy is comparable with that of more complex CNN designs.• The efficiency is 10 times better than more complex CNNs using pre-processing.• No GPU acceleration is required and can be executed on middle class computers.
Citation format
POLSINELLI, Matteo; CINQUE, Luigi; PLACIDI, Giuseppe. A light CNN for detecting COVID-19 from CT scans of the chest [preprint]. arXiv, 2020. arXiv:2004.12837.