Elsevier

Pattern Recognition

Volume 120, December 2021, 108135
Pattern Recognition

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

https://doi.org/10.1016/j.patcog.2021.108135Get rights and content

Highlights

  • Deep Neural Networks Ensemble for the detection of COVID-2019 from CT-Scans.

  • Feature extraction and Clustering to group specific lobes images.

  • Integration of existing CT scans datasets.

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

Deep learning
CT Scan images
COVID-19
Coronavirus

Cited by (0)

Lerina Aversano is an associate professor at the Department of Engineering of the University of Sannio Benevento (Italy). She received the Ph.D. in Computer Engineering in July 2003 at the same University where she has been assistant professor from 2005. She also was a research leader at RCOST - Research Centre On Software Technology - of the University of Sannio from 2005. She published more than 80 papers in journals and conference proceedings. Her research interests include software maintenance, program comprehension, reverse engineering, reengineering, migration, business process modelling, business process evolution, software system evolution, software quality.

Mario Luca Bernardi received the Laurea degree in Computer Science Engineering from the University of Naples ”Federico II”, Italy, in 2003 and the Ph.D. degree in Information Engineering from the University of Sannio in 2007. He is currently an assistant professor of Computer Science at the University of Sannio. Since 2003 he has been a researcher in the field of software engineering and his list of publications contains more than 60 papers published in journals and conference proceedings. His main research interests include software engineering (maintenance, testing, business process management, reverse engineering and data mining on software systems, software quality assurance with particular interest on internal quality metrics and on new paradigms for software modularity, including aspect-oriented software, component-based software and model-driven development). He serves both as a member of the program and organizing committees of conferences, and as associate editor and reviewer of papers submitted to some of the main journals and magazines in the field of software engineering, software maintenance and program comprehension.

Marta Cimitile is Assistant Professor and Aggregated Professor at Unitelma Sapienza University of Rome (Italy). She received a PhD in Computer Science in 06/05/2008 at the Department of Computer Science at the University of Bari and she received the Italian Scientific Qualification for the Associate Professor position in Computer Science Engineering in April 2017. She published more than fifty papers at international conferences and journals. Her main research topics are: Business Process Management and modeling, Knowledge modeling and Discovering, Process and Data Mining in Software Engineering Environment. In the last year, she was involved in several industrial and research projects and she is a founding member of the SpinOff of University of Bari named Software Engineering Research and Practices s.r.l. (www.serandp.com). She was in the program and organizing committees of several international conferences, she is reviewer to some of the main journals and magazines in the field of Knowledge Management and Software Engineering, knowledge representation and transfer and data mining and she is in the Editorial Board of the Journal of Information and Knowledge Management, PeerJ Computer Science. She is IEEE Member and IEEE Access reviewer.

Riccardo Pecori got his Ph.D. in Information Technology from University of Parma in 2011. From May 2015 to July 2019 he has been Assistant Professor of Computer Science at eCampus University where he taught Computer Security, Network Security, Internet of Things and Information Technology for Psychologists. Since August 2019 he is Assistant Professor at University of Sannio teaching ”Digital Design”. Since April 2017 he has been editor of the journal ”Future Generation Computer Systems” and since September 2019 of journal ”SoftwareX”. He has been Program Chair of WIVACE 2018 and HELMeTO 2019, organizing also a special session on “Social Internet of Things” at ISWCS 2017. His research interests regard network security, educational and social Big Data analysis, and identification of relevant sets in complex systems as well as deep learning.

View Abstract