Back to Search
Start Over
Weakly supervised deep learning to predict recurrence in low-grade endometrial cancer from multiplexed immunofluorescence images.
- Source :
- NPJ Digital Medicine; 3/23/2023, Vol. 6 Issue 1, p1-15, 15p
- Publication Year :
- 2023
-
Abstract
- 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. [ABSTRACT FROM AUTHOR]
- Subjects :
- ANTIGEN analysis
DEEP learning
CONFIDENCE intervals
PROGRAMMED death-ligand 1
GENETIC mutation
CLINICAL decision support systems
STAINS & staining (Microscopy)
MICROSCOPY
RESEARCH methodology
IMMUNOHISTOCHEMISTRY
CANCER relapse
APOPTOSIS
CREATINE kinase
MOLECULAR pathology
RISK assessment
CANCER patients
ENDOMETRIAL tumors
FLUORESCENT antibody technique
RESEARCH funding
DNA-binding proteins
DESCRIPTIVE statistics
TISSUES
BIOCHIPS
PREDICTION models
SENSITIVITY & specificity (Statistics)
TUMOR markers
T cells
TRANSCRIPTION factors
RADIOTHERAPY
RADIOISOTOPE brachytherapy
CELL lines
PHENOTYPES
DISEASE risk factors
EVALUATION
Subjects
Details
- Language :
- English
- ISSN :
- 23986352
- Volume :
- 6
- Issue :
- 1
- Database :
- Complementary Index
- Journal :
- NPJ Digital Medicine
- Publication Type :
- Academic Journal
- Accession number :
- 162682504
- Full Text :
- https://doi.org/10.1038/s41746-023-00795-x