No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients

Samira Masoudi; Stephanie Harmon; Sherif Mehralivand; Nathan Lay; Ulas Bagci; Bradford J. Wood; Peter A. Pinto; Peter Choyke; Baris Turkbey

doi:10.1109/ISBI48211.2021.9434027

No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients

Samira Masoudi, Stephanie Harmon, Sherif Mehralivand, Nathan Lay, Ulas Bagci, Bradford J. Wood, Peter A. Pinto, Peter Choyke, Baris Turkbey

Radiology

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

13 Scopus citations

Abstract

No-reference image quality assessment in magnetic resonance (MR) imaging is a challenging task due to the variable nature of these images and lack of standard quantification methods, which makes the interpretation to be almost always subjective. In this study, we propose an architecture where we: (i) extended the no-reference image quality assessment problem of MRI into a full-reference image quality assessment using unpaired generative adversarial network (GAN) and (ii) employed a weaklysupervised trained deep classifier to determine the quality of MR images by comparing each image with its synthetic higher quality reference image. Using this approach, we achieved 11.28% improvement in the accuracy of our MR image quality assessment algorithm on an independent data test with FPR in detecting low quality images, reduced from 13% to 9.6%.

Original language	English (US)
Title of host publication	2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021
Publisher	IEEE Computer Society
Pages	1201-1205
Number of pages	5
ISBN (Electronic)	9781665412469
DOIs	https://doi.org/10.1109/ISBI48211.2021.9434027
State	Published - Apr 13 2021
Event	18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 - Nice, France Duration: Apr 13 2021 → Apr 16 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	4/13/21 → 4/16/21

Funding

This work is supported in part by the Intramural Research Program of the National Cancer Institute, National Institutes of Health. The content of this publication does not necessarily reflect the views or policies of the Department of Health and Human Services, nor does mention of trade names, commercial products, or organizations imply endorsement by the U.S. Government.

Keywords

Generative adversarial network
Magnetic resonance imaging
No-reference image quality assessment

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

UN SDGs

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

Access to Document

10.1109/ISBI48211.2021.9434027

Cite this

Masoudi, S., Harmon, S., Mehralivand, S., Lay, N., Bagci, U., Wood, B. J., Pinto, P. A., Choyke, P., & Turkbey, B. (2021). No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients. In 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021 (pp. 1201-1205). Article 9434027 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2021-April). IEEE Computer Society. https://doi.org/10.1109/ISBI48211.2021.9434027

@inproceedings{cd24f9b335704cd994e0ba2dc06ddb8e,

title = "No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients",

abstract = "No-reference image quality assessment in magnetic resonance (MR) imaging is a challenging task due to the variable nature of these images and lack of standard quantification methods, which makes the interpretation to be almost always subjective. In this study, we propose an architecture where we: (i) extended the no-reference image quality assessment problem of MRI into a full-reference image quality assessment using unpaired generative adversarial network (GAN) and (ii) employed a weaklysupervised trained deep classifier to determine the quality of MR images by comparing each image with its synthetic higher quality reference image. Using this approach, we achieved 11.28% improvement in the accuracy of our MR image quality assessment algorithm on an independent data test with FPR in detecting low quality images, reduced from 13% to 9.6%.",

keywords = "Generative adversarial network, Magnetic resonance imaging, No-reference image quality assessment",

author = "Samira Masoudi and Stephanie Harmon and Sherif Mehralivand and Nathan Lay and Ulas Bagci and Wood, {Bradford J.} and Pinto, {Peter A.} and Peter Choyke and Baris Turkbey",

note = "Funding Information: This work is supported in part by the Intramural Research Program of the National Cancer Institute, National Institutes of Health. The content of this publication does not necessarily reflect the views or policies of the Department of Health and Human Services, nor does mention of trade names, commercial products, or organizations imply endorsement by the U.S. Government. 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/ISBI48211.2021.9434027",

language = "English (US)",

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

publisher = "IEEE Computer Society",

pages = "1201--1205",

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

address = "United States",

}

Masoudi, S, Harmon, S, Mehralivand, S, Lay, N, Bagci, U, Wood, BJ, Pinto, PA, Choyke, P & Turkbey, B 2021, No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients. in 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021., 9434027, Proceedings - International Symposium on Biomedical Imaging, vol. 2021-April, IEEE Computer Society, pp. 1201-1205, 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021, Nice, France, 4/13/21. https://doi.org/10.1109/ISBI48211.2021.9434027

No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients. / Masoudi, Samira; Harmon, Stephanie; Mehralivand, Sherif et al.
2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021. IEEE Computer Society, 2021. p. 1201-1205 9434027 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2021-April).

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

TY - GEN

T1 - No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients

AU - Masoudi, Samira

AU - Harmon, Stephanie

AU - Mehralivand, Sherif

AU - Lay, Nathan

AU - Bagci, Ulas

AU - Wood, Bradford J.

AU - Pinto, Peter A.

AU - Choyke, Peter

AU - Turkbey, Baris

N1 - Funding Information: This work is supported in part by the Intramural Research Program of the National Cancer Institute, National Institutes of Health. The content of this publication does not necessarily reflect the views or policies of the Department of Health and Human Services, nor does mention of trade names, commercial products, or organizations imply endorsement by the U.S. Government. Publisher Copyright: © 2021 IEEE.

PY - 2021/4/13

Y1 - 2021/4/13

N2 - No-reference image quality assessment in magnetic resonance (MR) imaging is a challenging task due to the variable nature of these images and lack of standard quantification methods, which makes the interpretation to be almost always subjective. In this study, we propose an architecture where we: (i) extended the no-reference image quality assessment problem of MRI into a full-reference image quality assessment using unpaired generative adversarial network (GAN) and (ii) employed a weaklysupervised trained deep classifier to determine the quality of MR images by comparing each image with its synthetic higher quality reference image. Using this approach, we achieved 11.28% improvement in the accuracy of our MR image quality assessment algorithm on an independent data test with FPR in detecting low quality images, reduced from 13% to 9.6%.

AB - No-reference image quality assessment in magnetic resonance (MR) imaging is a challenging task due to the variable nature of these images and lack of standard quantification methods, which makes the interpretation to be almost always subjective. In this study, we propose an architecture where we: (i) extended the no-reference image quality assessment problem of MRI into a full-reference image quality assessment using unpaired generative adversarial network (GAN) and (ii) employed a weaklysupervised trained deep classifier to determine the quality of MR images by comparing each image with its synthetic higher quality reference image. Using this approach, we achieved 11.28% improvement in the accuracy of our MR image quality assessment algorithm on an independent data test with FPR in detecting low quality images, reduced from 13% to 9.6%.

KW - Generative adversarial network

KW - Magnetic resonance imaging

KW - No-reference image quality assessment

UR - http://www.scopus.com/inward/record.url?scp=85107235940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85107235940&partnerID=8YFLogxK

U2 - 10.1109/ISBI48211.2021.9434027

DO - 10.1109/ISBI48211.2021.9434027

M3 - Conference contribution

AN - SCOPUS:85107235940

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1201

EP - 1205

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 -

Masoudi S, Harmon S, Mehralivand S, Lay N, Bagci U, Wood BJ et al. No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients. In 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021. IEEE Computer Society. 2021. p. 1201-1205. 9434027. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/ISBI48211.2021.9434027

No-reference image quality assessment of T2-weighted magnetic resonance images in prostate cancer patients

Abstract

Publication series

Conference

Funding

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this