Pareto optimization of deep networks for COVID-19 diagnosis from chest X-rays. (January 2022)

• Record Type: Journal Article
• Authors: Guarrasi, Valerio; D'Amico, Natascha Claudia; Sicilia, Rosa; Cordelli, Ermanno; Soda, Paolo
• Is Part Of: Pattern recognition. Volume 121(2022)
• Publication Date: 2022-01
• Subjects: COVID-19 -- X-ray -- Deep-learning -- Multi-expert systems -- Optimization -- Convolutional neural networks; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108242
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: On the use of chest X-ray to identify patients suffering from COVID-19. Pareto-based multi-objective optimization to set up best multi-expert systems. Ensemble of deep networks. Extensive validation using 4 different public datasets. Binary and 3-class classification tasks. Abstract: The year 2020 was characterized by the COVID-19 pandemic that has caused, by the end of March 2021, more than 2.5 million deaths worldwide. Since the beginning, besides the laboratory test, used as the gold standard, many applications have been applying deep learning algorithms to chest X-ray images to recognize COVID-19 infected patients. In this context, we found out that convolutional neural networks perform well on a single dataset but struggle to generalize to other data sources. To overcome this limitation, we propose a late fusion approach where we combine the outputs of several state-of-the-art CNNs, introducing a novel method that allows us to construct an optimum ensemble determining which and how many base learners should be aggregated. This choice is driven by a two-objective function that maximizes, on a validation set, the accuracy and the diversity of the ensemble itself. A wide set of experiments on several publicly available datasets, accounting for more than 92, 000 images, shows that the proposed approach provides average recognition rates up to 93.54% when tested on external datasets.