Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists

Basit Öğe Kaydı
dc.authorid0000-0003-0128-6947
dc.contributor.authorBulten, Wouter
dc.contributor.authorBalkenhol, Maschenka
dc.contributor.authorBelinga, Jean-Joel Awoumou
dc.contributor.authorBrilhante, Americo
dc.contributor.authorÇakır, Aslı
dc.contributor.authorEgevad, Lars
dc.contributor.authorEklund, Martin
dc.contributor.authorFarre, Xavier
dc.contributor.authorGeronatsiou, Katerina
dc.contributor.authorMolinie, Vincent
dc.contributor.authorPereira, Guilherme
dc.contributor.authorRoy, Paromita
dc.contributor.authorSaile, Gunter
dc.contributor.authorSalles, Paulo
dc.contributor.authorSchaafsma, Ewout
dc.contributor.authorTschui, Joelle
dc.contributor.authorVos, Anne-Marie
dc.contributor.authorvan Boven, Hester
dc.contributor.authorVink, Robert
dc.contributor.authorvan der Laak, Jeroen
dc.contributor.authorHulsbergen-van der Kaa, Christina
dc.contributor.authorLitjens, Geert
dc.date.accessioned2021-03-18T05:50:31Z
dc.date.available2021-03-18T05:50:31Z
dc.date.issued2021
dc.departmentİstanbul Medipol Üniversitesi, Tıp Fakültesi, Cerrahi Tıp Bilimleri Bölümü, Tıbbi Patoloji Ana Bilim Dalı
dc.description.abstractThe Gleason score is the most important prognostic marker for prostate cancer patients, but it suffers from significant observer variability. Artificial intelligence (AI) systems based on deep learning can achieve pathologist-level performance at Gleason grading. However, the performance of such systems can degrade in the presence of artifacts, foreign tissue, or other anomalies. Pathologists integrating their expertise with feedback from an AI system could result in a synergy that outperforms both the individual pathologist and the system. Despite the hype around AI assistance, existing literature on this topic within the pathology domain is limited. We investigated the value of AI assistance for grading prostate biopsies. A panel of 14 observers graded 160 biopsies with and without AI assistance. Using AI, the agreement of the panel with an expert reference standard increased significantly (quadratically weighted Cohen's kappa, 0.799 vs. 0.872;p = 0.019). On an external validation set of 87 cases, the panel showed a significant increase in agreement with a panel of international experts in prostate pathology (quadratically weighted Cohen's kappa, 0.733 vs. 0.786;p = 0.003). In both experiments, on a group-level, AI-assisted pathologists outperformed the unassisted pathologists and the standalone AI system. Our results show the potential of AI systems for Gleason grading, but more importantly, show the benefits of pathologist-AI synergy.
dc.description.sponsorshipKWF Kankerbestrijdingen_US
dc.identifier.citationBulten, W., Balkenhol, M., Belinga, Jean-Joel A., Brilhante, A., Çakır, A., Egevad, L. ... Litjens, G. (2021). Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists. Modern Pathology, 34(3), 660-671. https://dx.doi.org/10.1038/s41379-020-0640-y
dc.identifier.doi10.1038/s41379-020-0640-y
dc.identifier.endpage671
dc.identifier.issn0893-3952
dc.identifier.issn1530-0285
dc.identifier.issue3
dc.identifier.scopusqualityQ1
dc.identifier.startpage660
dc.identifier.urihttps://dx.doi.org/10.1038/s41379-020-0640-y
dc.identifier.urihttps://hdl.handle.net/20.500.12511/6612
dc.identifier.volume34
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherSpringer Nature
dc.relation.ispartofModern Pathologyen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsAttribution 4.0 International*
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/*
dc.subjectGleason Grading
dc.subjectProstate Biopsies
dc.subjectArtificial Intelligence Assistance
dc.titleArtificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Cakir-Aslii-2021.pdf
Boyut:
1.93 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Makale Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu