Cancer Foundation Models: The Next Generation of Generalizable Artificial Intelligence for Precision Medicine

Abstract

Cancer remains one of the leading causes of morbidity and mortality worldwide despite remarkable advances in molecular diagnostics, targeted therapeutics, immunotherapy, and precision medicine. The rapid expansion of biomedical data generated from radiological imaging, digital pathology, genomic sequencing, transcriptomics, proteomics, metabolomics, laboratory investigations, wearable technologies, and electronic health records has created unprecedented opportunities for artificial intelligence (AI)-driven oncology while simultaneously presenting substantial computational challenges. Cancer foundation models have emerged as a transformative paradigm by enabling generalized representation learning across heterogeneous biomedical modalities using large-scale self-supervised pretraining. Unlike conventional machine learning systems designed for individual clinical tasks, foundation models learn transferable biomedical knowledge that can be adapted to diagnosis, molecular characterization, prognostic prediction, therapeutic optimization, radiogenomics, computational pathology, digital twins, clinical decision support, and precision therapeutics. Advances in transformer architectures, multimodal learning, contrastive learning, graph neural networks, retrieval-augmented generation, large language models, and generative AI have substantially accelerated development of oncology foundation models capable of integrating imaging, pathology, multiomics, longitudinal clinical information, and real-world healthcare data into unified patient representations. These intelligent systems demonstrate remarkable generalizability across diverse cancer types while supporting increasingly personalized medicine. Nevertheless, important challenges remain regarding multimodal data harmonization, computational scalability, explainability, interoperability, cybersecurity, regulatory validation, and equitable clinical implementation. This review provides a comprehensive overview of cancer foundation models, highlighting computational principles, clinical applications, implementation challenges, and future perspectives for next-generation precision oncology.