Weakly supervised deep learning to predict recurrence in low-grade endometrial cancer from multiplexed immunofluorescence images.
Daniel Jiménez-SánchezÁlvaro López-JaneiroMaría Villalba-EsparzaMikel ArizEce KadiogluIvan MasettoVirginie GoubertMaria D LozanoIgnacio MeleroDavid HardissonCarlos Ortiz de SolórzanoCarlos E De AndreaPublished in: NPJ digital medicine (2023)
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.
Keyphrases
- low grade
- endometrial cancer
- deep learning
- regulatory t cells
- prognostic factors
- high grade
- machine learning
- early stage
- convolutional neural network
- free survival
- artificial intelligence
- end stage renal disease
- dendritic cells
- chronic kidney disease
- ejection fraction
- newly diagnosed
- single cell
- squamous cell carcinoma
- rna seq
- radiation therapy
- clinical practice
- patient reported outcomes
- high speed
- neoadjuvant chemotherapy