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

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: L773:0893 3952 > (2020-2023) > Artificial intellig...

LIBRIS Formathandbok (Information om MARC21)

Fältnamn	Indikatorer	Metadata
000		04907naa a2200601 4500
001		oai:DiVA.org:liu-168778
003		SwePub
008		200831s2021 \| \|\|\|\|\|\|\|\|\|\|\|000 \|\|eng\|
009		oai:prod.swepub.kib.ki.se:144351123
024	7	a https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-1687782 URI
024	7	a https://doi.org/10.1038/s41379-020-0640-y2 DOI
024	7	a http://kipublications.ki.se/Default.aspx?queryparsed=id:1443511232 URI
040		a (SwePub)liud (SwePub)ki
041		a engb eng
042		9 SwePub
072	7	a ref2 swepub-contenttype
072	7	a art2 swepub-publicationtype
100	1	a Bulten, Wouteru Radboud Univ Nijmegen, Netherlands4 aut
245	1 0	a Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists
264	1	b NATURE PUBLISHING GROUP,c 2021
338		a electronic2 rdacarrier
500		a Funding Agencies\|Dutch Cancer Society (KWF)KWF Kankerbestrijding [KUN 2015-7970]
520		a The 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 Cohens 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 Cohens 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.
650	7	a MEDICIN OCH HÄLSOVETENSKAPx Klinisk medicinx Cancer och onkologi0 (SwePub)302032 hsv//swe
650	7	a MEDICAL AND HEALTH SCIENCESx Clinical Medicinex Cancer and Oncology0 (SwePub)302032 hsv//eng
700	1	a Balkenhol, Maschenkau Radboud Univ Nijmegen, Netherlands4 aut
700	1	a Belinga, Jean-Joel Awoumouu Univ Yaounde I, Cameroon4 aut
700	1	a Brilhante, Americou Salomao Zoppi Diagnost DASA, Brazil4 aut
700	1	a Cakir, Asliu Istanbul Medipol Univ, Turkey4 aut
700	1	a Egevad, Larsu Karolinska Institutet4 aut
700	1	a Eklund, Martinu Karolinska Institutet4 aut
700	1	a Farre, Xavieru Publ Hlth Agcy Catalonia, Spain4 aut
700	1	a Geronatsiou, Katerinau Hop Diaconat Mulhouse, France4 aut
700	1	a Molinie, Vincentu Aix en Provence Hosp, France4 aut
700	1	a Pereira, Guilhermeu Histo Patol Cirarg & Citol, Brazil4 aut
700	1	a Roy, Paromitau Tata Med Ctr, India4 aut
700	1	a Saile, Gunteru Abt Histopathol & Zytol, Switzerland4 aut
700	1	a Salles, Paulou Inst Mario Penna, Brazil4 aut
700	1	a Schaafsma, Ewoutu Radboud Univ Nijmegen, Netherlands4 aut
700	1	a Tschui, Joelleu Med Pathol, Switzerland4 aut
700	1	a Vos, Anne-Marieu Radboud Univ Nijmegen, Netherlands4 aut
700	1	a van Boven, Hesteru Antoni van Leeuwenhoek Hosp, Netherlands4 aut
700	1	a Vink, Robertu Lab Pathol East Netherlands, Netherlands4 aut
700	1	a van der Laak, Jeroenu Linköpings universitet,Avdelningen för diagnostik och specialistmedicin,Medicinska fakulteten,Region Östergötland, Klinisk patologi,Radboud Univ Nijmegen, Netherlands4 aut0 (Swepub:liu)jerva26
700	1	a Hulsbergen-van der Kaa, Christinau Lab Pathol East Netherlands, Netherlands4 aut
700	1	a Litjens, Geertu Radboud Univ Nijmegen, Netherlands4 aut
710	2	a Radboud Univ Nijmegen, Netherlandsb Univ Yaounde I, Cameroon4 org
773	0	t Modern Pathologyd : NATURE PUBLISHING GROUPg 34, s. 660-671q 34<660-671x 0893-3952x 1530-0285
856	4	u https://liu.diva-portal.org/smash/get/diva2:1462799/FULLTEXT01.pdfx primaryx Raw objecty fulltext:print
856	4	u https://www.nature.com/articles/s41379-020-0640-y.pdf
856	4 8	u https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-168778
856	4 8	u https://doi.org/10.1038/s41379-020-0640-y
856	4 8	u http://kipublications.ki.se/Default.aspx?queryparsed=id:144351123

Hitta via bibliotek

Modern Pathology (Sök värdpublikationen i LIBRIS)

Till lärosätets databas

Hitta mer i SwePub

Om ämnet

MEDICIN OCH HÄLSOVETENSKAP: MEDICIN OCH HÄLS ...; och Klinisk medicin; och Cancer och onkol ...

Artiklar i publikationen: Modern Pathology

Av lärosätet: Linköpings universitet; Karolinska Institutet

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se