image: Composite of Figures 1 and 2: Summary of the weakly supervised learning approach for directly predicting disease specific survival and Kaplan Meier curves for DLS risk groups. view more
Credit: Wulczyn et al, 2020 (PLOS ONE, CC BY)
A machine-learning model shows promise in predicting cancer prognosis and survival by analyzing histopathology slides, according to a new study published June 17 in PLOS ONE by Ellery Wulczyn and David F. Steiner from Google Health, California, and colleagues.
###
Citation: Wulczyn E, Steiner DF, Xu Z, Sadhwani A, Wang H, Flament-Auvigne I, et al. (2020) Deep learning-based survival prediction for multiple cancer types using histopathology images. PLoS ONE 15(6): e0233678. https://doi.org/10.1371/journal.pone.0233678
Funding: This study was funded by Google LLC. All authors contributed to this work while employed at or performing work at Google. Most authors own Alphabet stock. Google did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific roles of each author is articulated in the 'author contributions' section.
Competing interests: This work was done while all authors were employed at or performing work at Google. Tempus did not play any role in this work. Most authors own Google stock and are co-inventors on patents for machine learning for cancer detection in histopathology images. This does not alter our adherence to PLOS ONE policies on sharing data and materials.
In your coverage please use this URL to provide access to the freely available article in PLOS ONE: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0233678
Journal
PLoS ONE