New York-based startup Paige, which spun out of Memorial Sloan Kettering and is building what it calls the world’s largest image-based artificial intelligence models for digital pathology and oncology, is partnering with Microsoft on new AI models.
Paige, which develops end-to-end digital pathology solutions and clinical AI, has developed a Large Foundation Model using over one billion images from half a million pathology slides across multiple cancer types. With Microsoft, Paige is developing a new AI model that it claims is orders-of-magnitude larger than any other image-based AI model existing today, configured with billions of parameters. This model assists in capturing the subtle complexities of cancer. Paige said it could serve as the cornerstone for the next generation of clinical applications and computational biomarkers that push the boundaries of oncology and pathology.
In its next phase of development, Paige is incorporating up to four million digitized microscopy slides across multiple types of cancer from its petabyte-scale archive of clinical data. Paige will then use Microsoft’s advanced supercomputing infrastructure to train the technology at scale and ultimately deploy it to hospitals and laboratories across the globe using Azure.
“Paige technology already goes beyond what is humanly possible today and helps physicians deliver better cancer care with AI support. By realizing the potential of generative AI at unprecedented scale, the Paige model collaboration with Microsoft is a milestone in the history of oncology,” said Thomas Fuchs, Dr.Sc., founder and chief scientist of Paige. It opens a window into the microscopic world with extraordinary fidelity, allowing for not only much higher accuracy but completely novel capabilities.”
“By combining Microsoft’s world-class research and cloud infrastructure with Paige’s deep expertise and large-scale data, we are creating new AI models that will enable unprecedented insights into the pathology of cancer,” said Desney Tan, vice president and managing director of Microsoft Health Futures, in a statement.
Paige also recently announced a collaboration with Ohio State University Wexner Medical Center (OSWMC) and its affiliated community hospitals. They will conduct a multi-arm clinical utility and health economics study to measure the accuracy, efficiency and cost-savings impact of using AI tools in diagnosing cancer in a community hospital setting. OSWMC will use the Paige Prostate Suite, including Paige Prostate Detect, an FDA-approved AI-powered pathology algorithm, to assess the differences between diagnoses made with and without the use of AI.
Community hospital pathologists will be conducting a retrospective real-world data study to analyze differences in the accuracy and read efficiency with which general surgical pathologists detect, grade, and quantify prostate cancers with and without the assistance of the Paige Prostate Suite, compared to a subspecialist reference diagnosis. The study will also examine differences in time and resource utilization based on the use of AI. Qualitatively, this will help determine the impact of the Paige Prostate AI applications on community pathologists, factoring in subspecialist skill access, patient treatment and management pathways, and the level of confidence in diagnosis with and without Paige’s AI applications.