A1 Vertaisarvioitu alkuperäisartikkeli tieteellisessä lehdessä
Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge
Tekijät: Bulten Wouter, Kartasalo Kimmo, Chen Po-Hsuan Cameron, Ström Peter, Pinckaers Hans, Nagpal Kunal, Cai Yuannan, Steiner David F., van Boven Hester, Vink Robert, Hulsbergen-van de Kaa Christina, van der Laak Jeroen, Amin Mahul B., Evans Andrew J., van der Kwast Theodorus, Allan Robert, Humphrey Peter A., Grönberg Henrik, Samaratunga Hemamali, Delahunt Brett, Tsuzuki Toyonori, Häkkinen Tomi, Egevad Lars, Demkin Maggie, Dane Sohier, Tan Fraser, Valkonen Masi, Corrado Greg S., Peng Lily, Mermel Craig H., Ruusuvuori Pekka, Litjens Geert, Eklund Martin, the PANDA challenge consortium
Kustantaja: NATURE PORTFOLIO
Julkaisuvuosi: 2022
Journal: Nature Medicine
Tietokannassa oleva lehden nimi: NATURE MEDICINE
Lehden akronyymi: NAT MED
Vuosikerta: 28
Numero: 1
Aloitussivu: 154
Lopetussivu: 163
Sivujen määrä: 23
ISSN: 1078-8956
DOI: https://doi.org/10.1038/s41591-021-01620-2
Verkko-osoite: https://www.nature.com/articles/s41591-021-01620-2
Rinnakkaistallenteen osoite: https://research.utu.fi/converis/portal/detail/Publication/174759707
Through a community-driven competition, the PANDA challenge provides a curated diverse dataset and a catalog of models for prostate cancer pathology, and represents a blueprint for evaluating AI algorithms in digital pathology.Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge-the largest histopathology competition to date, joined by 1,290 developers-to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted kappa, 95% confidence interval (CI), 0.840-0.884) and 0.868 (95% CI, 0.835-0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.
Ladattava julkaisu This is an electronic reprint of the original article. |  |
