Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features

R. Sivakumar; Seifedine Kadry; Sujatha Krishnamoorthy; Gangadharam Balaji; S. U. Nethrra; J. Varsha; Venkatesan Rajinikanth

doi:10.1007/978-981-99-3432-4_28

Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features

R. Sivakumar
, Seifedine Kadry
, Sujatha Krishnamoorthy
, Gangadharam Balaji
, S. U. Nethrra
, J. Varsha
, Venkatesan Rajinikanth

Artificial Intelligence Research Center (AIRC)

Anna University
Noroff University College
Lebanese American University
Wenzhou-Kean University
Tata Group India
Saveetha Institute of Medical and Technical Sciences (Deemed to be University)

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

Abstract

This research proposes and implements an automatic diagnostic scheme for detecting COVID-19 infection using lung CT slices to decrease the diagnostic burden. The proposed framework consists of (i) Image collection and preprocessing, (ii) Deep feature mining using the chosen scheme, (iii) Feature reduction and serial integration, and (iv) Classification and validation. A pre-trained deep-learning scheme is implemented in this scheme to obtain the necessary deep features from the CT slices selected and then to reduce these features by 50%. A CT image classification task is initially performed with SoftMax, and the outcome is then verified with other binary classifiers. Finally, we present and discuss the results of the proposed classification work using (i) single PDS and (ii) dual-deep features. With a single PDS, the Random Forest (RF) classifier provided a detection accuracy of 94%, and the K-Nearest Neighbor (KNN) classifier provided an accuracy of 99%.

Original language	English
Title of host publication	Lecture Notes on Data Engineering and Communications Technologies
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	359-369
Number of pages	11
DOIs	https://doi.org/10.1007/978-981-99-3432-4_28
State	Published - 2023

Publication series

Name	Lecture Notes on Data Engineering and Communications Technologies
Volume	175
ISSN (Print)	2367-4512
ISSN (Electronic)	2367-4520

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

COVID-19
Classification
Deep-learning
Lung CT
SoftMax

Access to Document

10.1007/978-981-99-3432-4_28

Cite this

Sivakumar, R., Kadry, S., Krishnamoorthy, S., Balaji, G., Nethrra, S. U., Varsha, J., & Rajinikanth, V. (2023). Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features. In Lecture Notes on Data Engineering and Communications Technologies (pp. 359-369). (Lecture Notes on Data Engineering and Communications Technologies; Vol. 175). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-3432-4_28

Sivakumar, R. ; Kadry, Seifedine ; Krishnamoorthy, Sujatha et al. / Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features. Lecture Notes on Data Engineering and Communications Technologies. Springer Science and Business Media Deutschland GmbH, 2023. pp. 359-369 (Lecture Notes on Data Engineering and Communications Technologies).

@inbook{d42c6021c9c3423c85fa6fcc781877ee,

title = "Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features",

abstract = "This research proposes and implements an automatic diagnostic scheme for detecting COVID-19 infection using lung CT slices to decrease the diagnostic burden. The proposed framework consists of (i) Image collection and preprocessing, (ii) Deep feature mining using the chosen scheme, (iii) Feature reduction and serial integration, and (iv) Classification and validation. A pre-trained deep-learning scheme is implemented in this scheme to obtain the necessary deep features from the CT slices selected and then to reduce these features by 50\%. A CT image classification task is initially performed with SoftMax, and the outcome is then verified with other binary classifiers. Finally, we present and discuss the results of the proposed classification work using (i) single PDS and (ii) dual-deep features. With a single PDS, the Random Forest (RF) classifier provided a detection accuracy of 94\%, and the K-Nearest Neighbor (KNN) classifier provided an accuracy of 99\%.",

keywords = "COVID-19, Classification, Deep-learning, Lung CT, SoftMax",

author = "R. Sivakumar and Seifedine Kadry and Sujatha Krishnamoorthy and Gangadharam Balaji and Nethrra, \{S. U.\} and J. Varsha and Venkatesan Rajinikanth",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.",

year = "2023",

doi = "10.1007/978-981-99-3432-4\_28",

language = "English",

series = "Lecture Notes on Data Engineering and Communications Technologies",

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

pages = "359--369",

booktitle = "Lecture Notes on Data Engineering and Communications Technologies",

address = "Germany",

}

Sivakumar, R, Kadry, S, Krishnamoorthy, S, Balaji, G, Nethrra, SU, Varsha, J & Rajinikanth, V 2023, Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features. in Lecture Notes on Data Engineering and Communications Technologies. Lecture Notes on Data Engineering and Communications Technologies, vol. 175, Springer Science and Business Media Deutschland GmbH, pp. 359-369. https://doi.org/10.1007/978-981-99-3432-4_28

Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features. / Sivakumar, R.; Kadry, Seifedine; Krishnamoorthy, Sujatha et al.
Lecture Notes on Data Engineering and Communications Technologies. Springer Science and Business Media Deutschland GmbH, 2023. p. 359-369 (Lecture Notes on Data Engineering and Communications Technologies; Vol. 175).

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

TY - CHAP

T1 - Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features

AU - Sivakumar, R.

AU - Kadry, Seifedine

AU - Krishnamoorthy, Sujatha

AU - Balaji, Gangadharam

AU - Nethrra, S. U.

AU - Varsha, J.

AU - Rajinikanth, Venkatesan

PY - 2023

Y1 - 2023

N2 - This research proposes and implements an automatic diagnostic scheme for detecting COVID-19 infection using lung CT slices to decrease the diagnostic burden. The proposed framework consists of (i) Image collection and preprocessing, (ii) Deep feature mining using the chosen scheme, (iii) Feature reduction and serial integration, and (iv) Classification and validation. A pre-trained deep-learning scheme is implemented in this scheme to obtain the necessary deep features from the CT slices selected and then to reduce these features by 50%. A CT image classification task is initially performed with SoftMax, and the outcome is then verified with other binary classifiers. Finally, we present and discuss the results of the proposed classification work using (i) single PDS and (ii) dual-deep features. With a single PDS, the Random Forest (RF) classifier provided a detection accuracy of 94%, and the K-Nearest Neighbor (KNN) classifier provided an accuracy of 99%.

AB - This research proposes and implements an automatic diagnostic scheme for detecting COVID-19 infection using lung CT slices to decrease the diagnostic burden. The proposed framework consists of (i) Image collection and preprocessing, (ii) Deep feature mining using the chosen scheme, (iii) Feature reduction and serial integration, and (iv) Classification and validation. A pre-trained deep-learning scheme is implemented in this scheme to obtain the necessary deep features from the CT slices selected and then to reduce these features by 50%. A CT image classification task is initially performed with SoftMax, and the outcome is then verified with other binary classifiers. Finally, we present and discuss the results of the proposed classification work using (i) single PDS and (ii) dual-deep features. With a single PDS, the Random Forest (RF) classifier provided a detection accuracy of 94%, and the K-Nearest Neighbor (KNN) classifier provided an accuracy of 99%.

KW - COVID-19

KW - Classification

KW - Deep-learning

KW - Lung CT

KW - SoftMax

UR - https://www.scopus.com/pages/publications/85168678161

U2 - 10.1007/978-981-99-3432-4_28

DO - 10.1007/978-981-99-3432-4_28

M3 - Chapter

AN - SCOPUS:85168678161

T3 - Lecture Notes on Data Engineering and Communications Technologies

SP - 359

EP - 369

BT - Lecture Notes on Data Engineering and Communications Technologies

PB - Springer Science and Business Media Deutschland GmbH

ER -

Sivakumar R, Kadry S, Krishnamoorthy S, Balaji G, Nethrra SU, Varsha J et al. Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features. In Lecture Notes on Data Engineering and Communications Technologies. Springer Science and Business Media Deutschland GmbH. 2023. p. 359-369. (Lecture Notes on Data Engineering and Communications Technologies). doi: 10.1007/978-981-99-3432-4_28

Deep-Learning Supported Detection of COVID-19 in Lung CT Slices with Concatenated Deep Features

Abstract

Publication series

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this