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

doi:10.1109/ISBI48211.2021.9434154

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

Research output: Book / Book Chapter / Report › Research Books › peer-review

2 Scopus citations

Abstract

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.

Original language	English
Title of host publication	2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021
Publisher	IEEE Computer Society
Pages	1665-1668
Number of pages	4
ISBN (Electronic)	9781665412469
DOIs	https://doi.org/10.1109/ISBI48211.2021.9434154
State	Published - 13 Apr 2021
Externally published	Yes
Event	18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 - Nice, France Duration: 13 Apr 2021 → 16 Apr 2021

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2021-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	18th IEEE International Symposium on Biomedical Imaging, ISBI 2021
Country/Territory	France
City	Nice
Period	13/04/21 → 16/04/21

Keywords

3D-CNN networks
COVID-19
Deep learning
Severity
Tomography

Access to Document

10.1109/ISBI48211.2021.9434154

Cite this

Rodriguez, J., Romo-Bucheli, D., Sierra, F., Valenzuela, D., Valenzuela, C., Vasquez, L., Camacho, P., Mantilla, D., & Martinez, F. (2021). A covid-19 patient severity stratification using a 3D convolutional strategy on CT-Scans. In 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021 (pp. 1665-1668). Article 9434154 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2021-April). IEEE Computer Society. https://doi.org/10.1109/ISBI48211.2021.9434154

@inproceedings{f9092a28efaa434b9936e2e367d58bb4,

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

abstract = "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.",

keywords = "3D-CNN networks, COVID-19, Deep learning, Severity, Tomography",

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

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 ; Conference date: 13-04-2021 Through 16-04-2021",

year = "2021",

month = apr,

day = "13",

doi = "10.1109/ISBI48211.2021.9434154",

language = "Ingl{\'e}s",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "1665--1668",

booktitle = "2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021",

}

Rodriguez, J, Romo-Bucheli, D, Sierra, F, Valenzuela, D, Valenzuela, C, Vasquez, L, Camacho, P, Mantilla, D & Martinez, F 2021, A covid-19 patient severity stratification using a 3D convolutional strategy on CT-Scans. in 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021., 9434154, Proceedings - International Symposium on Biomedical Imaging, vol. 2021-April, IEEE Computer Society, pp. 1665-1668, 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021, Nice, France, 13/04/21. https://doi.org/10.1109/ISBI48211.2021.9434154

A covid-19 patient severity stratification using a 3D convolutional strategy on CT-Scans. / Rodriguez, Jefferson; Romo-Bucheli, David; Sierra, Franklin et al.
2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021. IEEE Computer Society, 2021. p. 1665-1668 9434154 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2021-April).

Research output: Book / Book Chapter / Report › Research Books › peer-review

TY - GEN

T1 - A covid-19 patient severity stratification using a 3D convolutional strategy on CT-Scans

AU - Rodriguez, Jefferson

AU - Romo-Bucheli, David

AU - Sierra, Franklin

AU - Valenzuela, Diana

AU - Valenzuela, Carolina

AU - Vasquez, Lina

AU - Camacho, Paul

AU - Mantilla, Daniel

AU - Martinez, Fabio

PY - 2021/4/13

Y1 - 2021/4/13

N2 - 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.

AB - 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.

KW - 3D-CNN networks

KW - COVID-19

KW - Deep learning

KW - Severity

KW - Tomography

UR - http://www.scopus.com/inward/record.url?scp=85107232319&partnerID=8YFLogxK

U2 - 10.1109/ISBI48211.2021.9434154

DO - 10.1109/ISBI48211.2021.9434154

M3 - Libros de Investigación

AN - SCOPUS:85107232319

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1665

EP - 1668

BT - 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021

PB - IEEE Computer Society

T2 - 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021

Y2 - 13 April 2021 through 16 April 2021

ER -

Rodriguez J, Romo-Bucheli D, Sierra F, Valenzuela D, Valenzuela C, Vasquez L et al. A covid-19 patient severity stratification using a 3D convolutional strategy on CT-Scans. In 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021. IEEE Computer Society. 2021. p. 1665-1668. 9434154. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/ISBI48211.2021.9434154

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

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this