MultiSurv: A Multimodal Deep Survival Framework for Prostrate and Bladder Cancer

2025-09-05

AI Summary

This study addresses personalized survival prediction for prostate cancer (time to biochemical recurrence) and bladder cancer (time to recurrence) by proposing a multimodal deep survival analysis framework integrating clinical data, MRI, RNA-seq, and whole-slide histopathological images. Methodologically, it innovatively combines the DeepHit survival model with a cross-modal cross-attention–driven projection layer to dynamically align and complementarily model prognostic signals across heterogeneous modalities, balancing predictive accuracy and interpretability. In the CHIMERA challenge, the model achieves a C-index of 0.843 (5-fold cross-validation) and 0.818 (development set) for prostate cancer, while demonstrating strong generalizability and clinical translational potential on bladder cancer. These results establish a novel paradigm for precision prognosis leveraging multi-source biomedical data.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Accurate prediction of time-to-event outcomes is a central challenge in oncology, with significant implications for treatment planning and patient management. In this work, we present MultiSurv, a multimodal deep survival model utilising DeepHit with a projection layer and inter-modality cross-attention, which integrates heterogeneous patient data, including clinical, MRI, RNA-seq and whole-slide pathology features. The model is designed to capture complementary prognostic signals across modalities and estimate individualised time-to-biochemical recurrence in prostate cancer and time-to-cancer recurrence in bladder cancer. Our approach was evaluated in the context of the CHIMERA Grand Challenge, across two of the three provided tasks. For Task 1 (prostate cancer bio-chemical recurrence prediction), the proposed framework achieved a concordance index (C-index) of 0.843 on 5-folds cross-validation and 0.818 on CHIMERA development set, demonstrating robust discriminatory ability. For Task 3 (bladder cancer recurrence prediction), the model obtained a C-index of 0.662 on 5-folds cross-validation and 0.457 on development set, highlighting its adaptability and potential for clinical translation. These results suggest that leveraging multimodal integration with deep survival learning provides a promising pathway toward personalised risk stratification in prostate and bladder cancer. Beyond the challenge setting, our framework is broadly applicable to survival prediction tasks involving heterogeneous biomedical data.

Problem

• Predicting time-to-event outcomes for prostate and bladder cancer
• Integrating multimodal data including clinical, MRI, RNA-seq, and pathology
• Estimating individualized recurrence risks using deep survival learning

Innovation

• Integrates multimodal data with cross-attention mechanisms
• Uses DeepHit with projection layer for survival analysis
• Predicts recurrence in prostate and bladder cancer