학술논문
Are synthetic cytology images ready for prime time? A comparative assessment of real and synthetic urine cytology images.
Document Type
Academic Journal
Author
McAlpine E; Division of Anatomical Pathology, School of Pathology, University of the Witwatersrand, Johannesburg, South Africa; Ampath National Laboratories, Johannesburg, South Africa. Electronic address: ewen.mcalpine@wits.ac.za.; Michelow P; Division of Anatomical Pathology, School of Pathology, University of the Witwatersrand, Johannesburg, South Africa; National Health Laboratory Services, Johannesburg, South Africa.; Liebenberg E; Division of Anatomical Pathology, School of Pathology, University of the Witwatersrand, Johannesburg, South Africa.; Celik T; School of Electrical and Information Engineering and Wits Institute of Data Science, University of the Witwatersrand, Johannesburg, South Africa.
Source
Publisher: Elsevier Country of Publication: United States NLM ID: 101613234 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2213-2945 (Print) Linking ISSN: 22132953 NLM ISO Abbreviation: J Am Soc Cytopathol Subsets: MEDLINE
Subject
Language
English
ISSN
2213-2945
Abstract
Introduction: The use of synthetic data in pathology has, to date, predominantly been augmenting existing pathology data to improve supervised machine learning algorithms. We present an alternative use case-using synthetic images to augment cytology training when the availability of real-world examples is limited. Moreover, we compare the assessment of real and synthetic urine cytology images by pathology personnel to explore the usefulness of this technology in a real-world setting.
Materials and Methods: Synthetic urine cytology images were generated using a custom-trained conditional StyleGAN3 model. A morphologically balanced 60-image data set of real and synthetic urine cytology images was created for an online image survey system to allow for the assessment of the differences in visual perception between real and synthetic urine cytology images by pathology personnel.
Results: A total of 12 participants were recruited to answer the 60-image survey. The study population had a median age of 36.5 years and a median of 5 years of pathology experience. There was no significant difference in diagnostic error rates between real and synthetic images, nor was there a significant difference between subjective image quality scores between real and synthetic images when assessed on an individual observer basis.
Conclusions: The ability of Generative Adversarial Networks technology to generate highly realistic urine cytology images was demonstrated. Furthermore, there was no difference in how pathology personnel perceived the subjective quality of synthetic images, nor was there a difference in diagnostic error rates between real and synthetic urine cytology images. This has important implications for the application of Generative Adversarial Networks technology to cytology teaching and learning.
(Copyright © 2022 American Society of Cytopathology. Published by Elsevier Inc. All rights reserved.)
Materials and Methods: Synthetic urine cytology images were generated using a custom-trained conditional StyleGAN3 model. A morphologically balanced 60-image data set of real and synthetic urine cytology images was created for an online image survey system to allow for the assessment of the differences in visual perception between real and synthetic urine cytology images by pathology personnel.
Results: A total of 12 participants were recruited to answer the 60-image survey. The study population had a median age of 36.5 years and a median of 5 years of pathology experience. There was no significant difference in diagnostic error rates between real and synthetic images, nor was there a significant difference between subjective image quality scores between real and synthetic images when assessed on an individual observer basis.
Conclusions: The ability of Generative Adversarial Networks technology to generate highly realistic urine cytology images was demonstrated. Furthermore, there was no difference in how pathology personnel perceived the subjective quality of synthetic images, nor was there a difference in diagnostic error rates between real and synthetic urine cytology images. This has important implications for the application of Generative Adversarial Networks technology to cytology teaching and learning.
(Copyright © 2022 American Society of Cytopathology. Published by Elsevier Inc. All rights reserved.)