# Integrating Pathology and CT Imaging for Personalized Recurrence Risk Prediction in Renal Cancer

## TL;DR

This study demonstrates that integrating preoperative CT scans with postoperative pathology images using deep learning improves personalized recurrence risk prediction in renal cancer, outperforming traditional clinical scores.

## Contribution

It introduces a modular deep learning framework for multimodal data integration that enhances recurrence risk prediction accuracy in ccRCC.

## Key findings

- WSI-based models outperform CT-only models
- Intermediate fusion improves prediction performance
- The best model approaches the performance of the Leibovich score

## Abstract

Recurrence risk estimation in clear cell renal cell carcinoma (ccRCC) is essential for guiding postoperative surveillance and treatment. The Leibovich score remains widely used for stratifying distant recurrence risk but offers limited patient-level resolution and excludes imaging information. This study evaluates multimodal recurrence prediction by integrating preoperative computed tomography (CT) and postoperative histopathology whole-slide images (WSIs). A modular deep learning framework with pretrained encoders and Cox-based survival modeling was tested across unimodal, late fusion, and intermediate fusion setups. In a real-world ccRCC cohort, WSI-based models consistently outperformed CT-only models, underscoring the prognostic strength of pathology. Intermediate fusion further improved performance, with the best model (TITAN-CONCH with ResNet-18) approaching the adjusted Leibovich score. Random tie-breaking narrowed the gap between the clinical baseline and learned models, suggesting discretization may overstate individualized performance. Using simple embedding concatenation, radiology added value primarily through fusion. These findings demonstrate the feasibility of foundation model-based multimodal integration for personalized ccRCC risk prediction. Future work should explore more expressive fusion strategies, larger multimodal datasets, and general-purpose CT encoders to better match pathology modeling capacity.