Oracle & Imagene launch CanvOI to advance cancer research

Oracle and Imagene have announced the launch of CanvOI, a pan-cancer foundation model designed to facilitate innovative research and development in digital pathology and oncology. Utilising Oracle Cloud Infrastructure (OCI), CanvOI aims to capture complex features and patterns within biopsy images to provide valuable oncology intelligence that could revolutionise cancer diagnosis and treatment globally.

CanvOI is a robust vision data backbone for developing downstream applications in oncology research. These applications include predicting treatment responses, discovering biomarkers, assessing disease prognosis, and identifying pathological features. It is reported to outperform leading existing models in digital pathology, delivering state-of-the-art results.

Imagene has partnered with Oracle to run CanvOI on OCI, employing the OCI Supercluster and OCI AI Infrastructure technology for AI inference computation and data processing at scale. Larry Ellison, Oracle Chairman and CTO, commented, "To transform cancer research, Imagene did what countless other leading AI startups have done—it turned to Oracle’s Gen2 AI infrastructure, which delivers the scale and performance required to power the world’s largest AI models and help solve humanity’s most difficult challenges. With CanvOI running on Oracle Cloud Infrastructure, Oracle and Imagene are providing scientists with new weapons in the fight against mankind’s deadliest adversary, cancer."

Dean Bitan, Co-founder and CEO of Imagene, stated, "The next decade holds immense potential for breakthroughs in cancer research driven by Artificial Intelligence. We designed CanvOI to inspire researchers to dare to explore beyond. This is a pivotal milestone in the fight against this complex and devastating disease. By opening doors for innovative research, we aim to fundamentally change the future of cancer care."

CanvOI is a 1.1 billion parameters foundation model that was pre-trained on a diverse dataset comprising more than 630,000 tissue images from over 100 sites, covering more than 40 major body organs and tissue types. By employing a new approach to digital pathology foundation models and addressing computational demands differently, CanvOI has achieved industry-leading performance in various cancer-related tasks. Even with minimal labelled data, its effective performance is vital in the biomedical field, where data availability can often be limited.

CanvOI is central to Imagene’s new OISuite, a platform designed to help researchers and diagnostics developers explore a wide range of questions. This platform enables independent, in-depth research without requiring AI expertise or extensive data acquisition. OISuite facilitates rapid discoveries while maintaining high standards of data privacy and security.

Dr David Agus, Founding Director and Co-CEO of the Ellison Institute of Technology and Imagene board member, remarked, "CanvOI transforms our approach to healthcare and disease understanding. Providing access to comprehensive oncology intelligence in the cloud enables researchers to develop answers quicker and more efficiently. EIT is committed to leveraging CanvOI to propel groundbreaking innovations in our research that improve patient lives. This technology marks a new era of cancer research that pushes us closer to a future where cancer is a manageable condition."