A light CNN for detecting COVID-19 from CT scans of the chest

• Published in: Pattern recognition letters Vol. 140; pp. 95 - 100
• Main Authors: Polsinelli, Matteo, Cinque, Luigi, Placidi, Giuseppe
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.12.2020; Elsevier Science Ltd
• Subjects: Artificial neural networks; Chest; CNN; Computed tomography; Coronaviruses; COVID-19; Datasets; Deep Learning; Diagnosis; Disease control; Graphics processing units; Image acquisition; Medical imaging; Neural networks; Pattern Recognition; Workstations; COVID-19; CNN; Pattern Recognition; Deep Learning
• ISSN: 0167-8655; 1872-7344; 0167-8655
• DOI: 10.1016/j.patrec.2020.10.001

•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. Computer Tomography (CT) imaging of the chest is a valid diagnosis tool to detect COVID-19 promptly and to control the spread of the disease. In this work we propose a light Convolutional Neural Network (CNN) design, based on the model of the SqueezeNet, for the efficient discrimination of COVID-19 CT images with respect to other community-acquired pneumonia and/or healthy CT images. The architecture allows to an accuracy of 85.03% with an improvement of about 3.2% in the first dataset arrangement and of about 2.1% in the second dataset arrangement. The obtained gain, though of low entity, can be really important in medical diagnosis and, in particular, for Covid-19 scenario. Also the average classification time on a high-end workstation, 1.25 s, is very competitive with respect to that of more complex CNN designs, 13.41 s, witch require pre-processing. The proposed CNN can be executed on medium-end laptop without GPU acceleration in 7.81 s: this is impossible for methods requiring GPU acceleration. The performance of the method can be further improved with efficient pre-processing strategies for witch GPU acceleration is not necessary.