Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT

Suresh Manic Kesavan; Imad Al Naimi; Feras Al Attar; Venkatesan Rajinikanth; Seifedine Kadry

doi:10.1109/ICSCAN53069.2021.9526434

Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT

Suresh Manic Kesavan
, Imad Al Naimi
, Feras Al Attar
, Venkatesan Rajinikanth
, Seifedine Kadry

National University of Science & Technology (by Merger of Caledonian College of Engineering and Oman Medical College)
Anna University
Noroff University College

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

COVID19 is one of the hash lung infections; which causes severe pneumonia in humans and untreated infection will lead to death. The goal of this study is to employ an automated Infection-Segmentation-Scheme (ISS) to extract and evaluate the COVID19 lesion on CT scans of the Lungs. This work implemented a Convolution-Neural-Network (CNN) scheme called Res-UNet to study the CT slices of the lungs. The various phases of this research involve in; (i) 3D to 2D conversion and resizing, (ii) Implementation of CNN segmentation scheme, (iii) Comparison of mined COVID19 lesion with Ground-Truth (GT) and (iv) Validation. In this study, 200 CT images (10 patients x 20 slices/patient) of dimension 224× 224× 3 pixels are considered for the assessment and the Image-Quality-Measures (IQM), like Jaccard, Dice ad Accuracy are computed between extracted lesion and the GT. The experimental outcome confirms that the result of Res-UNet is better on sagittal-view of CT compared to axial and coronal.

Original language	English
Title of host publication	2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665439862
DOIs	https://doi.org/10.1109/ICSCAN53069.2021.9526434
State	Published - 30 Jul 2021
Externally published	Yes
Event	2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021 - Puducherry, India Duration: 30 Jul 2021 → 31 Jul 2021

Publication series

Name	2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021

Conference

Conference	2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021
Country/Territory	India
City	Puducherry
Period	30/07/21 → 31/07/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Assesment
COVID19
Lung CT
Pneumonia
Res-UNet

Access to Document

10.1109/ICSCAN53069.2021.9526434

Cite this

Kesavan, S. M., Al Naimi, I., Al Attar, F., Rajinikanth, V., & Kadry, S. (2021). Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT. In 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021 (2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSCAN53069.2021.9526434

Kesavan, Suresh Manic ; Al Naimi, Imad ; Al Attar, Feras et al. / Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT. 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021).

@inproceedings{e73475df7b294bc39d02ab2db0a22332,

title = "Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT",

abstract = "COVID19 is one of the hash lung infections; which causes severe pneumonia in humans and untreated infection will lead to death. The goal of this study is to employ an automated Infection-Segmentation-Scheme (ISS) to extract and evaluate the COVID19 lesion on CT scans of the Lungs. This work implemented a Convolution-Neural-Network (CNN) scheme called Res-UNet to study the CT slices of the lungs. The various phases of this research involve in; (i) 3D to 2D conversion and resizing, (ii) Implementation of CNN segmentation scheme, (iii) Comparison of mined COVID19 lesion with Ground-Truth (GT) and (iv) Validation. In this study, 200 CT images (10 patients x 20 slices/patient) of dimension 224× 224× 3 pixels are considered for the assessment and the Image-Quality-Measures (IQM), like Jaccard, Dice ad Accuracy are computed between extracted lesion and the GT. The experimental outcome confirms that the result of Res-UNet is better on sagittal-view of CT compared to axial and coronal.",

keywords = "Assesment, COVID19, Lung CT, Pneumonia, Res-UNet",

author = "Kesavan, \{Suresh Manic\} and \{Al Naimi\}, Imad and \{Al Attar\}, Feras and Venkatesan Rajinikanth and Seifedine Kadry",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021 ; Conference date: 30-07-2021 Through 31-07-2021",

year = "2021",

month = jul,

day = "30",

doi = "10.1109/ICSCAN53069.2021.9526434",

language = "English",

series = "2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021",

address = "United States",

}

Kesavan, SM, Al Naimi, I, Al Attar, F, Rajinikanth, V & Kadry, S 2021, Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT. in 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021. 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021, Institute of Electrical and Electronics Engineers Inc., 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021, Puducherry, India, 30/07/21. https://doi.org/10.1109/ICSCAN53069.2021.9526434

Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT. / Kesavan, Suresh Manic; Al Naimi, Imad; Al Attar, Feras et al.
2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT

AU - Kesavan, Suresh Manic

AU - Al Naimi, Imad

AU - Al Attar, Feras

AU - Rajinikanth, Venkatesan

AU - Kadry, Seifedine

PY - 2021/7/30

Y1 - 2021/7/30

N2 - COVID19 is one of the hash lung infections; which causes severe pneumonia in humans and untreated infection will lead to death. The goal of this study is to employ an automated Infection-Segmentation-Scheme (ISS) to extract and evaluate the COVID19 lesion on CT scans of the Lungs. This work implemented a Convolution-Neural-Network (CNN) scheme called Res-UNet to study the CT slices of the lungs. The various phases of this research involve in; (i) 3D to 2D conversion and resizing, (ii) Implementation of CNN segmentation scheme, (iii) Comparison of mined COVID19 lesion with Ground-Truth (GT) and (iv) Validation. In this study, 200 CT images (10 patients x 20 slices/patient) of dimension 224× 224× 3 pixels are considered for the assessment and the Image-Quality-Measures (IQM), like Jaccard, Dice ad Accuracy are computed between extracted lesion and the GT. The experimental outcome confirms that the result of Res-UNet is better on sagittal-view of CT compared to axial and coronal.

AB - COVID19 is one of the hash lung infections; which causes severe pneumonia in humans and untreated infection will lead to death. The goal of this study is to employ an automated Infection-Segmentation-Scheme (ISS) to extract and evaluate the COVID19 lesion on CT scans of the Lungs. This work implemented a Convolution-Neural-Network (CNN) scheme called Res-UNet to study the CT slices of the lungs. The various phases of this research involve in; (i) 3D to 2D conversion and resizing, (ii) Implementation of CNN segmentation scheme, (iii) Comparison of mined COVID19 lesion with Ground-Truth (GT) and (iv) Validation. In this study, 200 CT images (10 patients x 20 slices/patient) of dimension 224× 224× 3 pixels are considered for the assessment and the Image-Quality-Measures (IQM), like Jaccard, Dice ad Accuracy are computed between extracted lesion and the GT. The experimental outcome confirms that the result of Res-UNet is better on sagittal-view of CT compared to axial and coronal.

KW - Assesment

KW - COVID19

KW - Lung CT

KW - Pneumonia

KW - Res-UNet

UR - https://www.scopus.com/pages/publications/85115693589

U2 - 10.1109/ICSCAN53069.2021.9526434

DO - 10.1109/ICSCAN53069.2021.9526434

M3 - Conference contribution

AN - SCOPUS:85115693589

T3 - 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021

BT - 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021

Y2 - 30 July 2021 through 31 July 2021

ER -

Kesavan SM, Al Naimi I, Al Attar F, Rajinikanth V, Kadry S. Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT. In 2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021). doi: 10.1109/ICSCAN53069.2021.9526434

Res-UNet Supported Segmentation and Evaluation of COVID19 Lesion in Lung CT

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this