biostudies-literatureJimenez-Sanchez DMinistry of Economy and Competitiveness | Instituto de Salud Carlos III (Institute of Health Carlos III)Ministry of Economy and Competitiveness | Instituto de Salud Carlos III48https://www.ebi.ac.uk/biostudies/studies/S-EPMC10036616biostudies-literatureUnknown6(1)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.NPJ digital medicineWeakly supervised deep learning to predict recurrence in low-grade endometrial cancer from multiplexed immunofluorescence images.PMC10036616PI17/01723 and PI21/00920Jimenez-Sanchez DMasetto ILopez-Janeiro AVillalba-Esparza MOrtiz-de-Solorzano CMelero IHardisson DAriz MGoubert VLozano MDde Andrea CEKadioglu EfalseWeakly 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.2023-01-01T00:00:00Z2023 Mar2025-04-18T17:20:26.779Z2025-04-07T04:52:53.06ZS-EPMC100366163695923410.1038/s41746-023-00795-x