Paige developed the AI application using one of the largest libraries of digitised images, and unique computational resources offered by Microsoft Research, to detect multiple tumour types in more than 17 different tissue types
Paige unveils AI pathology cancer detection solution. (Credit: National Cancer Institute on Unsplash)
US-based digital pathology solutions provider Paige has unveiled an advanced AI-powered cancer detection solution, developed using its Pathology Foundation Model, Virchow.
Paige developed the AI application using one of the largest libraries of digitised images, and unique computational resources offered by Microsoft Research.
The new solution combines the outputs of the Foundation Model with data types from other modalities to provide insights into the nature of cancer, its behaviour, and responses.
It is the first application that can detect cancer in more than 17 different tissue types including skin, lung, and the gastrointestinal tract, along with multiple rare tumour types, said Paige.
Paige AI Science director Siqi Liu said: “The early success of our Foundation Model has been possible due to the size, quality, and diversity of the datasets we used to build it.
“Paige has access to one of the largest and most highly regarded pathology datasets globally, which allows us to leverage cutting-edge deep-learning approaches to train systems to detect common, complex, and even very rare cancer entities.
“Paige’s development provides the pathology community with the most powerful tools for diagnosis, prognosis, biomarker development, and targeted selection of patients for precision therapy.”
The development of conventional AI cancer detection applications needs large datasets, one tissue type at a time, and often requires months or years to build at clinical grade.
Paige has addressed the limitations by using its Virchow Foundation Model, and data derived from more than four million digitised slides.
The superior performance of the AI multi-cancer detection application across various tissue types is considered the most advanced in cancer pathology.
Furthermore, the pathology company said that it will continue to seek FDA regulatory oversight for products based on the Foundation Model technology.
Paige CEO Andy Moye said: “We see FDA clearance as being critical to ensure that regulatory and safety standards are being upheld in the application of AI in cancer diagnostics across tumour types.
“Paige remains at the forefront of innovation and regulatory milestones, and we expect this multi-tissue detection model to benefit patients, pathologists, and the broader medical community.”
Paige technology senior vice president Razik Yousfi said: “Beyond its multi-tissue capabilities, the Foundation Model and the use of its embeddings can also be leveraged as a critical building block in a variety of upstream and downstream applications across the entire healthcare continuum.”