Open AccessDeep learning representations to support COVID-19 diagnosis on CT slices
Author(s) -
Josué Ruano,
John Arcila,
David Romo-Bucheli,
Carlos Vargas,
Juan Manuel Melchor Rodríguez,
Óscar Mendoza,
Miguel Plazas,
Lola Bautista,
Jorge Villamizar,
Gabriel Pedraza,
Alejandra Moreno,
Diana Valenzuela,
L. Moreno Vázquez,
Carolina Valenzuela-Santos,
Paul Anthony Camacho,
Daniel Mantilla,
Fabio Carrillo
Publication year - 2022
Publication title -
biomédica/biomedica
Language(s) - English
Resource type - Journals
eISSN - 2590-7379
pISSN - 0120-4157
DOI - 10.7705/biomedica.5927
Subject(s) - artificial intelligence , deep learning , context (archaeology) , support vector machine , computer science , machine learning , covid-19 , pattern recognition (psychology) , transfer of learning , categorization , feature (linguistics) , test set , set (abstract data type) , medical diagnosis , medicine , radiology , disease , pathology , geography , linguistics , philosophy , infectious disease (medical specialty) , programming language , archaeology
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.