Show simple item record

dc.contributor.authorLi, Dongguang
dc.contributor.authorBledsoe, Jacob R.
dc.contributor.authorZeng, Yu
dc.contributor.authorLiu, Wei
dc.contributor.authorHu, Yiguo
dc.contributor.authorBi, Ke
dc.contributor.authorLiang, Aibin
dc.contributor.authorLi, Shaoguang
dc.date2022-08-11T08:09:58.000
dc.date.accessioned2022-08-23T16:50:34Z
dc.date.available2022-08-23T16:50:34Z
dc.date.issued2020-11-26
dc.date.submitted2021-01-15
dc.identifier.citation<p>Li D, Bledsoe JR, Zeng Y, Liu W, Hu Y, Bi K, Liang A, Li S. A deep learning diagnostic platform for diffuse large B-cell lymphoma with high accuracy across multiple hospitals. Nat Commun. 2020 Nov 26;11(1):6004. doi: 10.1038/s41467-020-19817-3. PMID: 33244018; PMCID: PMC7691991. <a href="https://doi.org/10.1038/s41467-020-19817-3">Link to article on publisher's site</a></p>
dc.identifier.issn2041-1723 (Linking)
dc.identifier.doi10.1038/s41467-020-19817-3
dc.identifier.pmid33244018
dc.identifier.urihttp://hdl.handle.net/20.500.14038/41684
dc.description.abstractDiagnostic histopathology is a gold standard for diagnosing hematopoietic malignancies. Pathologic diagnosis requires labor-intensive reading of a large number of tissue slides with high diagnostic accuracy equal or close to 100 percent to guide treatment options, but this requirement is difficult to meet. Although artificial intelligence (AI) helps to reduce the labor of reading pathologic slides, diagnostic accuracy has not reached a clinically usable level. Establishment of an AI model often demands big datasets and an ability to handle large variations in sample preparation and image collection. Here, we establish a highly accurate deep learning platform, consisting of multiple convolutional neural networks, to classify pathologic images by using smaller datasets. We analyze human diffuse large B-cell lymphoma (DLBCL) and non-DLBCL pathologic images from three hospitals separately using AI models, and obtain a diagnostic rate of close to 100 percent (100% for hospital A, 99.71% for hospital B and 100% for hospital C). The technical variability introduced by slide preparation and image collection reduces AI model performance in cross-hospital tests, but the 100% diagnostic accuracy is maintained after its elimination. It is now clinically practical to utilize deep learning models for diagnosis of DLBCL and ultimately other human hematopoietic malignancies.
dc.language.isoen_US
dc.relation<p><a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=pubmed&cmd=Retrieve&list_uids=33244018&dopt=Abstract">Link to Article in PubMed</a></p>
dc.rightsCopyright © The Author(s) 2020. Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectLymphoma
dc.subjectMachine learning
dc.subjectCancer imaging
dc.subjectArtificial Intelligence and Robotics
dc.subjectDiagnosis
dc.subjectHemic and Lymphatic Diseases
dc.subjectNeoplasms
dc.titleA deep learning diagnostic platform for diffuse large B-cell lymphoma with high accuracy across multiple hospitals
dc.typeJournal Article
dc.source.journaltitleNature communications
dc.source.volume11
dc.source.issue1
dc.identifier.legacyfulltexthttps://escholarship.umassmed.edu/cgi/viewcontent.cgi?article=5504&amp;context=oapubs&amp;unstamped=1
dc.identifier.legacycoverpagehttps://escholarship.umassmed.edu/oapubs/4474
dc.identifier.contextkey21101556
refterms.dateFOA2022-08-23T16:50:34Z
html.description.abstract<p>Diagnostic histopathology is a gold standard for diagnosing hematopoietic malignancies. Pathologic diagnosis requires labor-intensive reading of a large number of tissue slides with high diagnostic accuracy equal or close to 100 percent to guide treatment options, but this requirement is difficult to meet. Although artificial intelligence (AI) helps to reduce the labor of reading pathologic slides, diagnostic accuracy has not reached a clinically usable level. Establishment of an AI model often demands big datasets and an ability to handle large variations in sample preparation and image collection. Here, we establish a highly accurate deep learning platform, consisting of multiple convolutional neural networks, to classify pathologic images by using smaller datasets. We analyze human diffuse large B-cell lymphoma (DLBCL) and non-DLBCL pathologic images from three hospitals separately using AI models, and obtain a diagnostic rate of close to 100 percent (100% for hospital A, 99.71% for hospital B and 100% for hospital C). The technical variability introduced by slide preparation and image collection reduces AI model performance in cross-hospital tests, but the 100% diagnostic accuracy is maintained after its elimination. It is now clinically practical to utilize deep learning models for diagnosis of DLBCL and ultimately other human hematopoietic malignancies.</p>
dc.identifier.submissionpathoapubs/4474
dc.contributor.departmentDepartment of Pathology
dc.contributor.departmentDivision of Hematology Oncology, Department of Medicine
dc.source.pages6004


Files in this item

Thumbnail
Name:
s41467_020_19817_3.pdf
Size:
1.809Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

Copyright © The Author(s) 2020. Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
Except where otherwise noted, this item's license is described as Copyright © The Author(s) 2020. Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.