Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture

Seifedine Kadry; Fadi Al-Turjman; V. Rajinikanth

doi:10.1007/978-3-030-76063-2_2

Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture

Seifedine Kadry
, Fadi Al-Turjman
, V. Rajinikanth

Noroff University College
Near East University
Anna University

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

2 Scopus citations

Abstract

Pneumonia caused by the novel Coronavirus Disease (COVID-19) is emerged as a global threat and considerably affected a large population globally irrespective of their age, race, and gender. Due to its rapidity and the infection rate, the World Health Organization (WHO) declared this disease as a pandemic. The proposed research work aims to develop an automated COVID-19 lesion segmentation system using the Convolutional Neural Network (CNN) architecture called the U-Net. The traditional U-Net scheme is employed to examine the COVID-19 infection present in the lung CT images. This scheme is implemented on the benchmark COVID-19 images existing in the literature (300 images) and the segmentation performance of the U-Net is confirmed by computing the essential performance measures using a relative assessment among the extracted lesion and the Ground-Truth (GT). The overall result attained with the proposed study confirms that, the U-Net scheme helps to get the better values for the performance values, such as Jaccard (>86%), Dice (>92%) and segmentation accuracy (>95%).

Original language	English
Title of host publication	Science and Technologies for Smart Cities - 6th EAI International Conference, SmartCity360°, Proceedings
Editors	Sara Paiva, Sérgio Ivan Lopes, Rafik Zitouni, Nishu Gupta, Sérgio F. Lopes, Takuro Yonezawa
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	20-30
Number of pages	11
ISBN (Print)	9783030760625
DOIs	https://doi.org/10.1007/978-3-030-76063-2_2
State	Published - 2021
Externally published	Yes
Event	6th EAI International Conference on Science and Technologies for Smart Cities, SmartCity 2020 - Virtual, Online Duration: 2 Dec 2020 → 4 Dec 2020

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	372
ISSN (Print)	1867-8211
ISSN (Electronic)	1867-822X

Conference

Conference	6th EAI International Conference on Science and Technologies for Smart Cities, SmartCity 2020
City	Virtual, Online
Period	2/12/20 → 4/12/20

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

COVID-19
Lung CT images
Performance validation
Segmentation
U-Net scheme

Access to Document

10.1007/978-3-030-76063-2_2

Cite this

Kadry, S., Al-Turjman, F., & Rajinikanth, V. (2021). Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture. In S. Paiva, S. I. Lopes, R. Zitouni, N. Gupta, S. F. Lopes, & T. Yonezawa (Eds.), Science and Technologies for Smart Cities - 6th EAI International Conference, SmartCity360°, Proceedings (pp. 20-30). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 372). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-76063-2_2

Kadry, Seifedine ; Al-Turjman, Fadi ; Rajinikanth, V. / Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture. Science and Technologies for Smart Cities - 6th EAI International Conference, SmartCity360°, Proceedings. editor / Sara Paiva ; Sérgio Ivan Lopes ; Rafik Zitouni ; Nishu Gupta ; Sérgio F. Lopes ; Takuro Yonezawa. Springer Science and Business Media Deutschland GmbH, 2021. pp. 20-30 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{90b3db87a8494d3db7285b2e0431835b,

title = "Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture",

abstract = "Pneumonia caused by the novel Coronavirus Disease (COVID-19) is emerged as a global threat and considerably affected a large population globally irrespective of their age, race, and gender. Due to its rapidity and the infection rate, the World Health Organization (WHO) declared this disease as a pandemic. The proposed research work aims to develop an automated COVID-19 lesion segmentation system using the Convolutional Neural Network (CNN) architecture called the U-Net. The traditional U-Net scheme is employed to examine the COVID-19 infection present in the lung CT images. This scheme is implemented on the benchmark COVID-19 images existing in the literature (300 images) and the segmentation performance of the U-Net is confirmed by computing the essential performance measures using a relative assessment among the extracted lesion and the Ground-Truth (GT). The overall result attained with the proposed study confirms that, the U-Net scheme helps to get the better values for the performance values, such as Jaccard (>86\%), Dice (>92\%) and segmentation accuracy (>95\%).",

keywords = "COVID-19, Lung CT images, Performance validation, Segmentation, U-Net scheme",

author = "Seifedine Kadry and Fadi Al-Turjman and V. Rajinikanth",

note = "Publisher Copyright: {\textcopyright} 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.; 6th EAI International Conference on Science and Technologies for Smart Cities, SmartCity 2020 ; Conference date: 02-12-2020 Through 04-12-2020",

year = "2021",

doi = "10.1007/978-3-030-76063-2\_2",

language = "English",

isbn = "9783030760625",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "20--30",

editor = "Sara Paiva and Lopes, \{S{\'e}rgio Ivan\} and Rafik Zitouni and Nishu Gupta and Lopes, \{S{\'e}rgio F.\} and Takuro Yonezawa",

booktitle = "Science and Technologies for Smart Cities - 6th EAI International Conference, SmartCity360°, Proceedings",

address = "Germany",

}

Kadry, S, Al-Turjman, F & Rajinikanth, V 2021, Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture. in S Paiva, SI Lopes, R Zitouni, N Gupta, SF Lopes & T Yonezawa (eds), Science and Technologies for Smart Cities - 6th EAI International Conference, SmartCity360°, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 372, Springer Science and Business Media Deutschland GmbH, pp. 20-30, 6th EAI International Conference on Science and Technologies for Smart Cities, SmartCity 2020, Virtual, Online, 2/12/20. https://doi.org/10.1007/978-3-030-76063-2_2

Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture. / Kadry, Seifedine; Al-Turjman, Fadi; Rajinikanth, V.
Science and Technologies for Smart Cities - 6th EAI International Conference, SmartCity360°, Proceedings. ed. / Sara Paiva; Sérgio Ivan Lopes; Rafik Zitouni; Nishu Gupta; Sérgio F. Lopes; Takuro Yonezawa. Springer Science and Business Media Deutschland GmbH, 2021. p. 20-30 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 372).

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

TY - GEN

T1 - Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture

AU - Kadry, Seifedine

AU - Al-Turjman, Fadi

AU - Rajinikanth, V.

PY - 2021

Y1 - 2021

N2 - Pneumonia caused by the novel Coronavirus Disease (COVID-19) is emerged as a global threat and considerably affected a large population globally irrespective of their age, race, and gender. Due to its rapidity and the infection rate, the World Health Organization (WHO) declared this disease as a pandemic. The proposed research work aims to develop an automated COVID-19 lesion segmentation system using the Convolutional Neural Network (CNN) architecture called the U-Net. The traditional U-Net scheme is employed to examine the COVID-19 infection present in the lung CT images. This scheme is implemented on the benchmark COVID-19 images existing in the literature (300 images) and the segmentation performance of the U-Net is confirmed by computing the essential performance measures using a relative assessment among the extracted lesion and the Ground-Truth (GT). The overall result attained with the proposed study confirms that, the U-Net scheme helps to get the better values for the performance values, such as Jaccard (>86%), Dice (>92%) and segmentation accuracy (>95%).

AB - Pneumonia caused by the novel Coronavirus Disease (COVID-19) is emerged as a global threat and considerably affected a large population globally irrespective of their age, race, and gender. Due to its rapidity and the infection rate, the World Health Organization (WHO) declared this disease as a pandemic. The proposed research work aims to develop an automated COVID-19 lesion segmentation system using the Convolutional Neural Network (CNN) architecture called the U-Net. The traditional U-Net scheme is employed to examine the COVID-19 infection present in the lung CT images. This scheme is implemented on the benchmark COVID-19 images existing in the literature (300 images) and the segmentation performance of the U-Net is confirmed by computing the essential performance measures using a relative assessment among the extracted lesion and the Ground-Truth (GT). The overall result attained with the proposed study confirms that, the U-Net scheme helps to get the better values for the performance values, such as Jaccard (>86%), Dice (>92%) and segmentation accuracy (>95%).

KW - COVID-19

KW - Lung CT images

KW - Performance validation

KW - Segmentation

KW - U-Net scheme

UR - https://www.scopus.com/pages/publications/85111085155

U2 - 10.1007/978-3-030-76063-2_2

DO - 10.1007/978-3-030-76063-2_2

M3 - Conference contribution

AN - SCOPUS:85111085155

SN - 9783030760625

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 20

EP - 30

BT - Science and Technologies for Smart Cities - 6th EAI International Conference, SmartCity360°, Proceedings

A2 - Paiva, Sara

A2 - Lopes, Sérgio Ivan

A2 - Zitouni, Rafik

A2 - Gupta, Nishu

A2 - Lopes, Sérgio F.

A2 - Yonezawa, Takuro

PB - Springer Science and Business Media Deutschland GmbH

T2 - 6th EAI International Conference on Science and Technologies for Smart Cities, SmartCity 2020

Y2 - 2 December 2020 through 4 December 2020

ER -

Kadry S, Al-Turjman F, Rajinikanth V. Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture. In Paiva S, Lopes SI, Zitouni R, Gupta N, Lopes SF, Yonezawa T, editors, Science and Technologies for Smart Cities - 6th EAI International Conference, SmartCity360°, Proceedings. Springer Science and Business Media Deutschland GmbH. 2021. p. 20-30. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-030-76063-2_2

Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this