Deep learning representations to support COVID-19 diagnosis on CT slices.
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 f...
| Published in: | Biomédica: Revista del Instituto Nacional de Salud Vol. 42; no. 1; pp. 170 - 184 |
|---|---|
| Main Authors: | , , , , , , , , , , , , , , , , |
| Format: | Article |
| Published: |
Instituto Nacional de Salud of Colombia
mar2022
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=lth&AN=156183210&site=ehost-live header: @attributes: shortDbName: lth uiTerm: 156183210 longDbName: MedicLatina uiTag: AN controlInfo: bkinfo: jinfo: jid: 01204157 3ANP jtl: Biomédica: Revista del Instituto Nacional de Salud issn: 01204157 maglogo: N pubinfo: dt: mar2022 vid: 42 iid: 1 pid: 35431 pub: Instituto Nacional de Salud of Colombia artinfo: ui: 156183210 10.7705/biomedica.5927 ppf: 170 ppct: 14 formats: fmt: @attributes: type: P size: 1.2MB tig: atl: Deep learning representations to support COVID-19 diagnosis on CT slices. aug: au: Ruano, Josué Arcila, John Romo-Bucheli, David Vargas, Carlos Rodríguez, Jefferson Mendoza, Óscar Plazas, Miguel Bautista, Lola Villamizar, Jorge Pedraza, Gabriel Moreno, Alejandra Valenzuela, Diana Vásquez, Lina Valenzuela-Santos, Carolina Camacho, Paúl Mantilla, Daniel Martínez, Fabio affil: BIVL2ab Biomedical Imaging, Vision and Learning Laboratory, Escuela de Ingeniería de Sistemas e Informática, Universidad Industrial de Santander, Bucaramanga, Colombia Facultad de Ingeniería, Universidad de Los Andes, Mérida, Venezuela Clínica FOSCAL, Fundación Oftalmológica de Santander, Bucaramanga, Colombia su: COVID-19 testing Deep learning COVID-19 Support vector machines COVID-19 pandemic sug: subj: COVID-19 testing Deep learning COVID-19 Support vector machines COVID-19 pandemic keyword: Coronavirus infections/diagnosis deep learning tomography X-ray computed aprendizaje profundo Coronavirus infections/diagnosis deep learning infecciones por coronavirus/diagnóstico tomografía computarizada por rayos X tomography X-ray computed ab: 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. Introducción. La enfermedad por coronavirus (COVID-19) es actualmente el principal problema de salud pública en el mundo. En este contexto, el análisis automático de tomografías computarizadas (TC) surge como una herramienta diagnóstica complementaria que permite caracterizar hallazgos radiológicos, y categorizar y hacer el seguimiento de pacientes con COVID-19. Sin embargo, este análisis depende de la experiencia de los radiólogos, por lo que las valoraciones pueden ser subjetivas. Objetivo. Explorar representaciones de aprendizaje profundo entrenadas con cortes de TC torácica para diferenciar automáticamente entre los casos de COVID-19 y personas no infectadas. Materiales y métodos. Se usaron dos conjuntos de datos de TC: de SARS-CoV-2 CT (conjunto 1) y de la clínica FOSCAL (conjunto 2). Los modelos de aprendizaje supervisados y previamente entrenados en imágenes naturales, se ajustaron usando aprendizaje por transferencia. La clasificación se llevó a cabo mediante aprendizaje de extremo a extremo y clasificadores tales como los árboles de decisiones y las máquinas de soporte vectorial, alimentados por la representación profunda previamente aprendida. Resultados. El enfoque de extremo a extremo alcanzó una exactitud promedio de 92,33 % (89,70 % de precisión) para el conjunto 1 y de 96,99 % (96,62 % de precisión) para el conjunto-2. La máquina de soporte vectorial alcanzó una exactitud promedio de 91,40 % (precisión del 95,77 %) para el conjunto-1 y del 96,00 % (precisión del 94,74 %) para el conjunto 2. Conclusión. Las representaciones profundas lograron resultados sobresalientes al caracterizar patrones radiológicos usados en la detección de casos de COVID-19 a partir de estudios de TC y demostraron ser una potencial herramienta de apoyo del diagnóstico. pubtype: Academic Journal doctype: Article src: R language: Spanish refInfo: copyright: @attributes: flag: Y custom: Copyright of Biomédica: Revista del Instituto Nacional de Salud is the property of Instituto Nacional de Salud of Colombia and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. item: Biomédica: Revista del Instituto Nacional de Salud holder: Instituto Nacional de Salud of Colombia dt: @attributes: year: 2022 holdings: @attributes: islocal: N |
|---|