Utility of Pathology Imagebase for standardisation of prostate cancer grading

Egevad, Lars; Delahunt, Brett; Berney, Daniel M.; Bostwick, David G.; Cheville, John C.; Compérat, Éva; Evans, Andrew; Fine, Samson W.; Grignon, David J.; Humphrey, Peter A.; Hörnblad, Jonas; Iczkowski, Kenneth A.; Kench, James G.; Kristiansen, Glen; Leite, Kátia R. M.; Magi‐Galluzzi, Cristina; McKenney, Jesse K.; Oxley, Jon; Pan, Chin Chen; Samaratunga, Hemamali; Srigley, John R.; Takahashi, Hiroyuki; True, Lawrence D.; Tsuzuki, Toyonori; Kwast, Theo van der; Varma, Murali; Zhou, Ming; Clements, Mark

doi:10.1111/his.13471

Cited by 41 publications

(47 citation statements)

References 25 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ISUP now has an image database for urological pathology, which can be accessed online (www.isup.org) and provides an invaluable resource of renal tumour images for reference and promotes standardisation of diagnosis and tumour grading [138, 139]. The capacity to annotate digital images enhances the educational value.…”

Section: Resultsmentioning

confidence: 99%

WHO/ISUP classification, grading and pathological staging of renal cell carcinoma: standards and controversies

2018

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

WHO/ISUP classification, grading and pathological staging of renal cell carcinoma: standards and controversies

2018

View full text Add to dashboard Cite

show abstract

“…The average kappa of ISUP grades of the prostate cancer cases that were uploaded in Imagebase was 0.67 . The highest agreement was achieved in cases uploaded as ISUP grades 1 or 5, while the worst reproducibility was seen in ISUP grade 3, i.e.…”

Section: Future Perspectivesmentioning

confidence: 97%

Evolution, controversies and the future of prostate cancer grading

Egevad

Delahunt

Yaxley

et al. 2019

Pathology International

Self Cite

View full text Add to dashboard Cite

Histological grading of prostate cancer is one of the most important tissue‐based parameters for prediction of outcome and treatment response. Gleason grading remains the foundation of prostate cancer grading, but has undergone a series of changes in the past 30 years, often initiated by consensus conference decisions. This review summarizes the most important modifications that were introduced by the 2005 and 2014 International Society of Urological Pathology (ISUP) revisions of Gleason grading and discusses the impact that these have had on current grading practices. A considerable inflation in Gleason scores has been observed, especially following the ISUP 2005 revision, and the effects of this are discussed. ISUP 2014 grading recommendations are described, including the reporting of ISUP grades 1–5. Controversial issues include methods for reporting of grades on needle biopsies, reporting of percent Gleason grades 4/5 and grading of cribriform and intraductal carcinoma of the prostate. Educational programs developed recently to promote standardization of grading are described and their results assessed.

show abstract

“…The time between the main experiment, and this external validation was 6 months. For this external validation, we made use of the Imagebase dataset [22]. The Imagebase set consists of 90 cases of prostate needle biopsies with cancer independently graded by 24 international experts in prostate pathology.…”

Section: External Datasetmentioning

confidence: 99%

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

Bulten¹,

Balkenhol²,

Belinga

et al. 2021

Modern Pathology

Self Cite

113

View full text Add to dashboard Cite

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 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 grouplevel, 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. Members of the ISUP Pathology Imagebase Expert Panel are listed below Acknowledgements.

show abstract

Utility of Pathology Imagebase for standardisation of prostate cancer grading

Abstract: It is anticipated that the database will assist pathologists to calibrate their grading and, hence, decrease interobserver variability. It will also help to identify instances where definitions of grades need to be clarified.

Cited by 41 publications

References 25 publications

WHO/ISUP classification, grading and pathological staging of renal cell carcinoma: standards and controversies

WHO/ISUP classification, grading and pathological staging of renal cell carcinoma: standards and controversies

Evolution, controversies and the future of prostate cancer grading

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

Contact Info

Product

Resources

About