What question did this study set out to answer?

To develop and independently validate reproducible artificial intelligence algorithms for Gleason grading of prostate biopsies across international settings.

January 1, 2022Nature MedicineOpen Access

Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge

View Full Paper

Ask AI

Bookmark

To develop and independently validate reproducible artificial intelligence algorithms for Gleason grading of prostate biopsies across international settings.
Organized the PANDA challenge involving 1,290 algorithm developers using a development dataset of 10,616 digitized prostate biopsies.
Evaluated submitted algorithms on external validation cohorts from the United States and Europe under blinded conditions to the developers.
Measured diagnostic agreement between algorithm predictions and expert uropathologist reference standards.
Algorithms reached an agreement score of 0.862 (quadratically weighted κ, 95% CI, 0.840–0.884) with expert uropathologists on the United States external validation cohort.
Algorithms achieved an agreement score of 0.868 (quadratically weighted κ, 95% CI, 0.835–0.900) with expert uropathologists on the European external validation cohort.
Multiple algorithm architectures demonstrated generalization across diverse patient populations, tissue preparation laboratories, and reference standards.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Multicenter competition study demonstrates pathologist-level Gleason grading accuracy in prostate biopsy cohorts, suggesting readiness for prospective clinical trials.

Cite This Study

A 2022 study studied this question.

synapsesocial.com/papers/6a7e877d0af838441d0d1f78 https://doi.org/10.1038/s41591-021-01620-2

View Full Paper

Ask AI

Bookmark

Implication

Multicenter competition study demonstrates pathologist-level Gleason grading accuracy in prostate biopsy cohorts, suggesting readiness for prospective clinical trials.

Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge

Key Points

Discussion

Implication

Cite This Study

Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider