Radiopathological System for Quantifying the Tumor Microenvironment and Predicting Prognosis in Osteosarcoma: A Multicenter Study

Motivation: Current quantification methods for osteosarcoma tumors and their tumor microenvironment (TME) are often ineffective, resulting in treatment failures and poor patient prognosis. Goal(s): To develop an automated system integrating MRI and WSI data for precise, quantitative assessment of tumors and TME to improve prognostic predictions. Approach: We developed a system utilizing MRI and WSI data from a 185-patient, multisite cohort, enabling independent assessment of tumors and TME. Results: Combined radiopathomic features significantly improve patient outcome predictions. Impact: This model provides a comprehensive prognostic assessment, essential for advancing predictive tools and extensive validation before clinical application.