CROSS-MODAL ARTIFICIAL INTELLIGENCE FOR PRECISION ONCOLOGY: BRIDGING RADIOLOGY, HISTOPATHOLOGY, GENOMICS, AND CLINICAL RECORDS

Abstract

Precision oncology has entered an era in which artificial intelligence (AI) is no longer confined to individual diagnostic tasks but instead functions as an integrative computational framework capable of unifying heterogeneous biomedical information across the entire cancer care continuum. Conventional machine learning approaches have achieved remarkable success in isolated domains such as radiology, digital pathology, genomics, or electronic health records; however, their modality-specific design frequently limits comprehensive understanding of tumor biology and clinical decision-making. Recent advances in cross-modal artificial intelligence, including foundation models, multimodal transformers, graph neural networks, self-supervised learning, and generative AI, have enabled seamless integration of radiological imaging, histopathology, genomics, transcriptomics, proteomics, metabolomics, epigenomics, laboratory biomarkers, electronic health records, wearable technologies, and longitudinal clinical outcomes into unified patient-centered computational representations. These intelligent systems facilitate molecular characterization, biomarker discovery, prognostic prediction, therapeutic optimization, immunotherapy selection, digital twin simulation, adaptive disease monitoring, and clinical decision support while accelerating precision medicine. Emerging technologies such as multimodal large language models, federated learning, reinforcement learning, retrieval-augmented generation, explainable artificial intelligence, and agentic AI further strengthen cross-modal computational oncology by enabling collaborative, privacy-preserving, and continuously adaptive learning across diverse healthcare environments. Despite extraordinary technological progress, 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 cross-modal artificial intelligence for precision oncology, emphasizing integration of radiology, histopathology, genomics, and clinical records as the foundation for future intelligent cancer medicine.