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 pheno...

Full description

Saved in:
Bibliographic Details
Published in:NPJ digital medicine 2023-03, Vol.6 (1), p.48-48, Article 48
Main Authors: Jiménez-Sánchez, Daniel, López-Janeiro, Álvaro, Villalba-Esparza, María, Ariz, Mikel, Kadioglu, Ece, Masetto, Ivan, Goubert, Virginie, Lozano, Maria D., Melero, Ignacio, Hardisson, David, Ortiz-de-Solórzano, Carlos, de Andrea, Carlos E.
Format: Article
Language:English
Subjects:
631/114/1305
631/114/1564
631/250/2503
639/705/117
692/53/2423
Biomedicine
Biotechnology
Deep learning
Digital technology
Endometrial cancer
Fluorescence
Medical prognosis
Medical technology
Medicine
Medicine & Public Health
Radiology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2398-6352
2398-6352
DOI:10.1038/s41746-023-00795-x