Summary
Develop novel computational markers and models for more accurate detection and forecasting of aggressive prostate cancer, aiming to reduce overdiagnosis and overtreatment.
Computational Feature Profiling and Modeling for Prostate Cancer Detection and Risk Stratification
US · IL
National Institutes of Health (NIH)
grant
awarded
#nih-5R01CA279666-03
What they want
The project aims to identify novel pathomic and germline features indicative of aggressive prostate cancer or its precursors using a large patient cohort. It will then implement an integrative graph convolutional network (GCN) combined with a convolutional neural network (CNN) to create multi-modal representations from multiparametric magnetic resonance imaging (mpMRI), digital histology images, germline features, biomarkers, and other predictors. The project will also develop and compare new nomogram risk models incorporating these identified features.
Deliverables
- Novel pathomic and germline features indicating aggressive cancer
- Integrative GCN and CNN framework for multi-modal cancer representation
- New nomogram risk models for prostate cancer detection and risk stratification
Technical requirements
- Graph Convolutional Network (GCN)
- Convolutional Neural Network (CNN)
- Multiparametric Magnetic Resonance Imaging (mpMRI) data analysis
- Digital histology image analysis
- Germline feature analysis
- Biomarker analysis
- Nomogram risk modeling
Market context
inferred from NAICSR&D in Physical, Engineering, Life Sciences (except Nanotech & Biotech)
NAICS 541715
- US market size
- $95B
- Typical award
- $100K – $50M+
Typical buyers
DoDNSFNIHNASADOE
Commonly required
DCAA-compliant accountingITARCMMC L2
