Deep learning representations to support COVID-19 diagnosis on CT slices

• Published in: Biomédica
• Main Authors: Josué Ruano, John Arcila, David Romo-Bucheli, Carlos Vargas, Jefferson Rodríguez, Óscar Mendoza, Miguel Plazas, Lola Bautista, Jorge Villamizar, Gabriel Pedraza, Alejandra Moreno, Diana Valenzuela, Lina Vázquez, Carolina Valenzuela-Santos, Paul Camacho, Daniel Mantilla, Fabio Martínez Carrillo
• Format: Article in Journal/Newspaper
• Language: English; Spanish
• Published: Instituto Nacional de Salud 2022
• Subjects: coronavirus infections/diagnosis; tomography; x-ray computed; deep learning; Medicine; R; Arctic medicine. Tropical medicine; RC955-962; Arctic
• Online Access: https://doi.org/10.7705/biomedica.5927; https://doaj.org/article/21b384a2a1f141549dc6e006e65e12a2

Introduction: The coronavirus disease 2019 (COVID-19) has become a significant public health problem worldwide. In this context, CT-scan automatic analysis has emerged as a COVID-19 complementary diagnosis tool allowing for radiological finding characterization, patient categorization, and disease follow-up. However, this analysis depends on the radiologist’s expertise, which may result in subjective evaluations. Objective: To explore deep learning representations, trained from thoracic CT-slices, to automatically distinguish COVID-19 disease from control samples. Materials and methods: Two datasets were used: SARS-CoV-2 CT Scan (Set-1) and FOSCAL clinic’s dataset (Set-2). The deep representations took advantage of supervised learning models previously trained on the natural image domain, which were adjusted following a transfer learning scheme. The deep classification was carried out: (a) via an end-to-end deep learning approach and (b) via random forest and support vector machine classifiers by feeding the deep representation embedding vectors into these classifiers. Results: The end-to-end classification achieved an average accuracy of 92.33% (89.70% precision) for Set-1 and 96.99% (96.62% precision) for Set-2. The deep feature embedding with a support vector machine achieved an average accuracy of 91.40% (95.77% precision) and 96.00% (94.74% precision) for Set-1 and Set-2, respectively. Conclusion: Deep representations have achieved outstanding performance in the identification of COVID-19 cases on CT scans demonstrating good characterization of the COVID-19 radiological patterns. These representations could potentially support the COVID-19 diagnosis in clinical settings.