Deep neural networks ensemble to detect COVID-19 from CT scans

Lerina Aversano; Mario Luca Bernardi; Marta Cimitile; Riccardo Pecori

doi:10.1016/j.patcog.2021.108135

Deep neural networks ensemble to detect COVID-19 from CT scans

Pattern Recognit. 2021 Dec:120:108135. doi: 10.1016/j.patcog.2021.108135. Epub 2021 Jul 7.

Authors

Lerina Aversano¹, Mario Luca Bernardi¹, Marta Cimitile², Riccardo Pecori¹

Affiliations

¹ University of Sannio, Benevento (BN), Italy.
² Unitelma Sapienza University, Rome, Italy.

Abstract

Research on Coronavirus Disease 2019 (COVID-19) detection methods has increased in the last months as more accurate automated toolkits are required. Recent studies show that CT scan images contain useful information to detect the COVID-19 disease. However, the scarcity of large and well balanced datasets limits the possibility of using detection approaches in real diagnostic contexts as they are unable to generalize. Indeed, the performance of these models quickly becomes inadequate when applied to samples captured in different contexts (e.g., different equipment or populations) from those used in the training phase. In this paper, a novel ensemble-based approach for more accurate COVID-19 disease detection using CT scan images is proposed. This work exploits transfer learning using pre-trained deep networks (e.g., VGG, Xception, and ResNet) evolved with a genetic algorithm, combined into an ensemble architecture for the classification of clustered images of lung lobes. The study is validated on a new dataset obtained as an integration of existing ones. The results of the experimental evaluation show that the ensemble classifier ensures effective performance, also exhibiting better generalization capabilities.

Keywords: COVID-19; CT Scan images; Coronavirus; Deep learning.