A covid-19 patient severity stratification using a 3D convolutional strategy on CT-Scans

Jefferson Rodriguez, David Romo-Bucheli, Franklin Sierra, Diana Valenzuela, Carolina Valenzuela, Lina Vasquez, Paul Camacho, Daniel Mantilla, Fabio Martinez

Resultado de la investigación: Libro / Capitulo del libro / InformeLibros de Investigaciónrevisión exhaustiva

1 Cita (Scopus)

Resumen

This work introduces a 3D deep learning methodology to stratify patients according to the severity of lung infection caused by COVID-19 disease on computerized tomography images (CT). A set of volumetric attention maps were also obtained to explain the results and support the diagnostic tasks. The validation of the approach was carried out on a dataset composed of 350 patients, diagnosed by the RT-PCR assay either as negative (control-175) or positive (COVID-19-175). Additionally, the patients were graded (0-25) by two expert radiologists according to the extent of lobar involvement. These gradings were used to define 5 COVID-19 severity categories. The model yields an average 60% accuracy for the multi-severity classification task. Additionally, a set of Mann Whitney U significance tests were conducted to compare the severity groups. Results show that patients in different severity groups have significantly different severity scores (p < 0.01) for all the compared severity groups.

Idioma originalInglés
Título de la publicación alojada2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021
EditorialIEEE Computer Society
Páginas1665-1668
Número de páginas4
ISBN (versión digital)9781665412469
DOI
EstadoPublicada - 13 abr. 2021
Publicado de forma externa
Evento18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 - Nice, Francia
Duración: 13 abr. 202116 abr. 2021

Serie de la publicación

NombreProceedings - International Symposium on Biomedical Imaging
Volumen2021-April
ISSN (versión impresa)1945-7928
ISSN (versión digital)1945-8452

Conferencia

Conferencia18th IEEE International Symposium on Biomedical Imaging, ISBI 2021
País/TerritorioFrancia
CiudadNice
Período13/04/2116/04/21

Huella

Profundice en los temas de investigación de 'A covid-19 patient severity stratification using a 3D convolutional strategy on CT-Scans'. En conjunto forman una huella única.

Citar esto