FOUNDATION MODELS FOR CANCER INTELLIGENCE: INTEGRATING RADIOLOGY, PATHOLOGY, MULTI-OMICS, AND CLINICAL DECISION SUPPORT

Abstract

Foundation artificial intelligence (AI) models are transforming modern oncology by enabling comprehensive cancer intelligence through the integration of radiology, pathology, multi-omics, and clinical information into unified computational ecosystems capable of supporting precision diagnosis, prognostic prediction, therapeutic optimization, and personalized clinical decision-making. Conventional artificial intelligence systems have demonstrated considerable success in isolated oncology applications; however, their dependence on task-specific training, fragmented biomedical data, and limited generalizability restrict widespread clinical implementation. Recent advances in foundation AI models, multimodal transformer architectures, graph neural networks, self-supervised learning, and generative artificial intelligence have enabled generalized biomedical representation learning across radiological imaging, digital pathology, genomics, transcriptomics, proteomics, metabolomics, epigenomics, spatial biology, laboratory biomarkers, circulating tumor DNA, wearable physiological monitoring, electronic health records, and longitudinal clinical outcomes. These intelligent computational systems support early cancer detection, molecular characterization, biomarker discovery, prognostic prediction, treatment optimization, immunotherapy selection, digital twin simulation, adaptive disease monitoring, and intelligent clinical decision support. Emerging technologies including multimodal large language models, federated learning, reinforcement learning, retrieval-augmented generation, explainable artificial intelligence, and agentic AI further strengthen cancer intelligence by enabling collaborative, privacy-preserving, transparent, and continuously adaptive biomedical reasoning. Despite remarkable technological advances, important scientific, technical, ethical, and regulatory challenges remain regarding multimodal data harmonization, computational scalability, interpretability, interoperability, cybersecurity, clinical validation, and equitable implementation. This review provides a comprehensive overview of foundation models for cancer intelligence, emphasizing integration of radiology, pathology, multi-omics, and clinical decision support as a transformative framework for personalized cancer medicine.