STResNet: Covid-19 Detection by ResNet Transfer Learning and Stochastic Pooling

Wei Wang; Shui Hua Wang; Yu Dong Zhang

doi:10.1007/978-981-16-6775-6_40

STResNet: Covid-19 Detection by ResNet Transfer Learning and Stochastic Pooling

Wei Wang, Shui Hua Wang, Yu Dong Zhang^*

^*Corresponding author for this work

University of Leicester

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

1 Citation (Scopus)

Abstract

Since 2019, COVID-19 has been spreading globally with a very rapid rate of transmission, resulting in a large number of confirmed diagnoses and deaths. The main interdiction measure currently in use for COVID-19 is the isolation of the confirmed population. For this reason, an effective and rapid diagnostic approach is particularly important. In this paper, we propose a deep learning framework (STResNet) for diagnosing COVID-19 from chest CT image slices. The proposed framework uses a modified residual network with 50 network layers as a backbone to extract features from chest CT slices and a support vector machine to classify the extracted features. Experiments show that the proposed framework has excellent performance. In the experiment based on a chest CT slices dataset, STResNet achieved accuracy of 93.81% ± 1.02%, MCC of 87.64% ± 2.02%, FMI of 93.83% ± 0.99%, sensitivity of 94.03% ± 1.07%, precision of 93.64% ± 1.54%, F1-score of 93.83% ± 0.99%, and specificity of 93.59% ± 1.67%. These demonstrate the excellent performance of the proposed framework with well balance and stability.

Original language	English
Title of host publication	Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022
Editors	Ruidan Su, Yudong Zhang, Han Liu, Alejandro F Frangi
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	489-502
Number of pages	14
ISBN (Print)	9789811667749
DOIs	https://doi.org/10.1007/978-981-16-6775-6_40
Publication status	Published - 2023
Externally published	Yes
Event	International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022 - Leicester, United Kingdom Duration: 20 Nov 2022 → 21 Nov 2022

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	810 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022
Country/Territory	United Kingdom
City	Leicester
Period	20/11/22 → 21/11/22

Keywords

ResNet-50
Stochastic pooling
Support vector machine

Access to Document

10.1007/978-981-16-6775-6_40

Cite this

Wang, W., Wang, S. H., & Zhang, Y. D. (2023). STResNet: Covid-19 Detection by ResNet Transfer Learning and Stochastic Pooling. In R. Su, Y. Zhang, H. Liu, & A. F Frangi (Eds.), Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022 (pp. 489-502). (Lecture Notes in Electrical Engineering; Vol. 810 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-6775-6_40

Wang, Wei ; Wang, Shui Hua ; Zhang, Yu Dong. / STResNet : Covid-19 Detection by ResNet Transfer Learning and Stochastic Pooling. Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022. editor / Ruidan Su ; Yudong Zhang ; Han Liu ; Alejandro F Frangi. Springer Science and Business Media Deutschland GmbH, 2023. pp. 489-502 (Lecture Notes in Electrical Engineering).

@inproceedings{bdd563de4b80459fb584009c1325cae4,

title = "STResNet: Covid-19 Detection by ResNet Transfer Learning and Stochastic Pooling",

abstract = "Since 2019, COVID-19 has been spreading globally with a very rapid rate of transmission, resulting in a large number of confirmed diagnoses and deaths. The main interdiction measure currently in use for COVID-19 is the isolation of the confirmed population. For this reason, an effective and rapid diagnostic approach is particularly important. In this paper, we propose a deep learning framework (STResNet) for diagnosing COVID-19 from chest CT image slices. The proposed framework uses a modified residual network with 50 network layers as a backbone to extract features from chest CT slices and a support vector machine to classify the extracted features. Experiments show that the proposed framework has excellent performance. In the experiment based on a chest CT slices dataset, STResNet achieved accuracy of 93.81% ± 1.02%, MCC of 87.64% ± 2.02%, FMI of 93.83% ± 0.99%, sensitivity of 94.03% ± 1.07%, precision of 93.64% ± 1.54%, F1-score of 93.83% ± 0.99%, and specificity of 93.59% ± 1.67%. These demonstrate the excellent performance of the proposed framework with well balance and stability.",

keywords = "ResNet-50, Stochastic pooling, Support vector machine",

author = "Wei Wang and Wang, {Shui Hua} and Zhang, {Yu Dong}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022 ; Conference date: 20-11-2022 Through 21-11-2022",

year = "2023",

doi = "10.1007/978-981-16-6775-6_40",

language = "English",

isbn = "9789811667749",

series = "Lecture Notes in Electrical Engineering",

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

pages = "489--502",

editor = "Ruidan Su and Yudong Zhang and Han Liu and {F Frangi}, Alejandro",

booktitle = "Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022",

}

Wang, W, Wang, SH & Zhang, YD 2023, STResNet: Covid-19 Detection by ResNet Transfer Learning and Stochastic Pooling. in R Su, Y Zhang, H Liu & A F Frangi (eds), Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022. Lecture Notes in Electrical Engineering, vol. 810 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 489-502, International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022, Leicester, United Kingdom, 20/11/22. https://doi.org/10.1007/978-981-16-6775-6_40

STResNet: Covid-19 Detection by ResNet Transfer Learning and Stochastic Pooling. / Wang, Wei; Wang, Shui Hua; Zhang, Yu Dong.
Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022. ed. / Ruidan Su; Yudong Zhang; Han Liu; Alejandro F Frangi. Springer Science and Business Media Deutschland GmbH, 2023. p. 489-502 (Lecture Notes in Electrical Engineering; Vol. 810 LNEE).

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

TY - GEN

T1 - STResNet

T2 - International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022

AU - Wang, Wei

AU - Wang, Shui Hua

AU - Zhang, Yu Dong

PY - 2023

Y1 - 2023

N2 - Since 2019, COVID-19 has been spreading globally with a very rapid rate of transmission, resulting in a large number of confirmed diagnoses and deaths. The main interdiction measure currently in use for COVID-19 is the isolation of the confirmed population. For this reason, an effective and rapid diagnostic approach is particularly important. In this paper, we propose a deep learning framework (STResNet) for diagnosing COVID-19 from chest CT image slices. The proposed framework uses a modified residual network with 50 network layers as a backbone to extract features from chest CT slices and a support vector machine to classify the extracted features. Experiments show that the proposed framework has excellent performance. In the experiment based on a chest CT slices dataset, STResNet achieved accuracy of 93.81% ± 1.02%, MCC of 87.64% ± 2.02%, FMI of 93.83% ± 0.99%, sensitivity of 94.03% ± 1.07%, precision of 93.64% ± 1.54%, F1-score of 93.83% ± 0.99%, and specificity of 93.59% ± 1.67%. These demonstrate the excellent performance of the proposed framework with well balance and stability.

AB - Since 2019, COVID-19 has been spreading globally with a very rapid rate of transmission, resulting in a large number of confirmed diagnoses and deaths. The main interdiction measure currently in use for COVID-19 is the isolation of the confirmed population. For this reason, an effective and rapid diagnostic approach is particularly important. In this paper, we propose a deep learning framework (STResNet) for diagnosing COVID-19 from chest CT image slices. The proposed framework uses a modified residual network with 50 network layers as a backbone to extract features from chest CT slices and a support vector machine to classify the extracted features. Experiments show that the proposed framework has excellent performance. In the experiment based on a chest CT slices dataset, STResNet achieved accuracy of 93.81% ± 1.02%, MCC of 87.64% ± 2.02%, FMI of 93.83% ± 0.99%, sensitivity of 94.03% ± 1.07%, precision of 93.64% ± 1.54%, F1-score of 93.83% ± 0.99%, and specificity of 93.59% ± 1.67%. These demonstrate the excellent performance of the proposed framework with well balance and stability.

KW - ResNet-50

KW - Stochastic pooling

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85180766104&partnerID=8YFLogxK

U2 - 10.1007/978-981-16-6775-6_40

DO - 10.1007/978-981-16-6775-6_40

M3 - Conference Proceeding

AN - SCOPUS:85180766104

SN - 9789811667749

T3 - Lecture Notes in Electrical Engineering

SP - 489

EP - 502

BT - Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022

A2 - Su, Ruidan

A2 - Zhang, Yudong

A2 - Liu, Han

A2 - F Frangi, Alejandro

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 20 November 2022 through 21 November 2022

ER -

Wang W, Wang SH, Zhang YD. STResNet: Covid-19 Detection by ResNet Transfer Learning and Stochastic Pooling. In Su R, Zhang Y, Liu H, F Frangi A, editors, Medical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022. Springer Science and Business Media Deutschland GmbH. 2023. p. 489-502. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-16-6775-6_40

STResNet: Covid-19 Detection by ResNet Transfer Learning and Stochastic Pooling

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this