File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Synthesis of diagnostic quality cancer pathology images by generative adversarial networks

TitleSynthesis of diagnostic quality cancer pathology images by generative adversarial networks
Authors
Keywordscancer
pathology
deep learning
artificial intelligence
quality assurance
Issue Date2020
PublisherJohn Wiley & Sons. The Journal's web site is located at http://www3.interscience.wiley.com/cgi-bin/jhome/1130
Citation
Journal of Pathology, 2020, Epub 2020-07-19 How to Cite?
AbstractDeep learning‐based computer vision methods have recently made remarkable breakthroughs in the analysis and classification of cancer pathology images. However, there has been relatively little investigation of the utility of deep neural networks to synthesize medical images. In this study, we evaluated the efficacy of generative adversarial networks to synthesize high‐resolution pathology images of 10 histological types of cancer, including five cancer types from The Cancer Genome Atlas and the five major histological subtypes of ovarian carcinoma. The quality of these images was assessed using a comprehensive survey of board‐certified pathologists (n = 9) and pathology trainees (n = 6). Our results show that the real and synthetic images are classified by histotype with comparable accuracies and the synthetic images are visually indistinguishable from real images. Furthermore, we trained deep convolutional neural networks to diagnose the different cancer types and determined that the synthetic images perform as well as additional real images when used to supplement a small training set. These findings have important applications in proficiency testing of medical practitioners and quality assurance in clinical laboratories. Furthermore, training of computer‐aided diagnostic systems can benefit from synthetic images where labeled datasets are limited (e.g. rare cancers). We have created a publicly available website where clinicians and researchers can attempt questions from the image survey (http://gan.aimlab.ca/). © 2020 Pathological Society of Great Britain and Ireland.
Persistent Identifierhttp://hdl.handle.net/10722/284627
ISSN
2023 Impact Factor: 5.6
2023 SCImago Journal Rankings: 2.426
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLevine, AB-
dc.contributor.authorPeng, J-
dc.contributor.authorFarnell, D-
dc.contributor.authorNursey, M-
dc.contributor.authorWang, Y-
dc.contributor.authorNaso, JR-
dc.contributor.authorRen, HZ-
dc.contributor.authorFarahani, H-
dc.contributor.authorChen, C-
dc.contributor.authorChiu, D-
dc.contributor.authorTalhouk, A-
dc.contributor.authorSheffield, B-
dc.contributor.authorRiazy, M-
dc.contributor.authorIp, PP-
dc.contributor.authorParran-Herran, C-
dc.contributor.authorMills, A-
dc.contributor.authorSingh, N-
dc.contributor.authorTessier‐Cloutier, B-
dc.contributor.authorSalisbury, T-
dc.contributor.authorLee, J-
dc.contributor.authorSalcudean, T-
dc.contributor.authorJones, SJM-
dc.contributor.authorHuntsman, DG-
dc.contributor.authorGilks, CB-
dc.contributor.authorYip, S-
dc.contributor.authorBashashati, A-
dc.date.accessioned2020-08-07T09:00:21Z-
dc.date.available2020-08-07T09:00:21Z-
dc.date.issued2020-
dc.identifier.citationJournal of Pathology, 2020, Epub 2020-07-19-
dc.identifier.issn0022-3417-
dc.identifier.urihttp://hdl.handle.net/10722/284627-
dc.description.abstractDeep learning‐based computer vision methods have recently made remarkable breakthroughs in the analysis and classification of cancer pathology images. However, there has been relatively little investigation of the utility of deep neural networks to synthesize medical images. In this study, we evaluated the efficacy of generative adversarial networks to synthesize high‐resolution pathology images of 10 histological types of cancer, including five cancer types from The Cancer Genome Atlas and the five major histological subtypes of ovarian carcinoma. The quality of these images was assessed using a comprehensive survey of board‐certified pathologists (n = 9) and pathology trainees (n = 6). Our results show that the real and synthetic images are classified by histotype with comparable accuracies and the synthetic images are visually indistinguishable from real images. Furthermore, we trained deep convolutional neural networks to diagnose the different cancer types and determined that the synthetic images perform as well as additional real images when used to supplement a small training set. These findings have important applications in proficiency testing of medical practitioners and quality assurance in clinical laboratories. Furthermore, training of computer‐aided diagnostic systems can benefit from synthetic images where labeled datasets are limited (e.g. rare cancers). We have created a publicly available website where clinicians and researchers can attempt questions from the image survey (http://gan.aimlab.ca/). © 2020 Pathological Society of Great Britain and Ireland.-
dc.languageeng-
dc.publisherJohn Wiley & Sons. The Journal's web site is located at http://www3.interscience.wiley.com/cgi-bin/jhome/1130-
dc.relation.ispartofJournal of Pathology-
dc.rightsPreprint This is the pre-peer reviewed version of the following article: [FULL CITE], which has been published in final form at [Link to final article using the DOI]. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions. Postprint This is the peer reviewed version of the following article: [FULL CITE], which has been published in final form at [Link to final article using the DOI]. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions.-
dc.subjectcancer-
dc.subjectpathology-
dc.subjectdeep learning-
dc.subjectartificial intelligence-
dc.subjectquality assurance-
dc.titleSynthesis of diagnostic quality cancer pathology images by generative adversarial networks-
dc.typeArticle-
dc.identifier.emailIp, PP: philipip@hku.hk-
dc.identifier.authorityIp, PP=rp01890-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1002/path.5509-
dc.identifier.pmid32686118-
dc.identifier.scopuseid_2-s2.0-85090459120-
dc.identifier.hkuros311914-
dc.identifier.volumeEpub 2020-07-19-
dc.identifier.isiWOS:000566823300001-
dc.publisher.placeUnited Kingdom-
dc.identifier.issnl0022-3417-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats