Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publication
Artículo científico (JournalArticle)
Weakly supervised deep learning to predict recurrence in low-grade endometrial cancer from multiplexed immunofluorescence images
Predicting recurrence in low-grade, early-stage endometrial cancer (EC) is both challenging and clinically relevant. We present a weakly-supervised deep learning framework, NaroNet, that can learn, without manual expert annotation, the complex tumor-immune interrelations at three levels: local phenotypes, cellular neighborhoods, and tissue areas. It uses multiplexed immunofluorescence for the simultaneous visualization and quantification of CD68 + macrophages, CD8 + T cells, FOXP3 + regulatory T cells, PD-L1/PD-1 protein expression, and tumor cells. We used 489 tumor cores from 250 patients to train a multilevel deep-learning model to predict tumor recurrence. Using a tenfold cross-validation strategy, our model achieved an area under the curve of 0.90 with a 95% confidence interval of 0.83–0.95. Our model predictions resulted in concordance for 96,8% of cases (κ = 0.88). This method could accurately assess the risk of recurrence in EC, outperforming current prognostic factors, including molecular subtyping., This work was supported by Instituto de Salud Carlos III and Fondo Europeo de Desarrollo Regional (ISCIII and FEDER; grants PI21/01547—M.D.L. and C.E.A.; PI17/01723 and PI21/00920—A.L.-J and D.V.), and Fundació La Marató de TV3 (I.M., M.D.L., and C.E.A.). The funders had no role in study design, data collection and analysis, the decision to publish, or preparation of the paper. We would like to thank Raphaël Sandoz for technical support and troubleshooting.
Project:
ISCIII / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 (ISCIII) PI21-01547
,
ISCIII / Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 (ISCIII) PI17-01723
,
ISCIII / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 (ISCIII) PI21-00920
View at: https://hdl.handle.net/2454/56414