US-based digital pathology company Paige, in collaboration with Microsoft, has launched the second generation of Virchow, its million-slide foundation model for cancer.
In September last year, Paige partnered with Microsoft, to develop the world’s largest image-based AI models for digital pathology and oncology, to help fight against cancer.
According to the company, the second-generation AI foundation models, Virchow2 and Virchow2G, are the world’s largest and most advanced AI models in clinical pathology.
Paige developed the updated AI models using a diverse dataset of more than three million pathology slides from over 800 labs and 45 countries.
They offer superior data diversity and depth, along with a deeper understanding of cells and tissue, aiming to redefine cancer diagnosis and treatment, said the digital pathology company.
Paige founder and chief scientist Thomas Fuchs said: “Our collaboration with Microsoft has been pivotal in the development of Virchow, which has already earned recognition in Nature Medicine.
“We are merely scratching the surface of what these foundation models can achieve in transforming our understanding of cancer through computational pathology.
“Virchow’s immense scale unlocks key information that can be used to drive groundbreaking innovations, enabling precise diagnostics, targeted treatments, and personalised patient care.
“This is the beginning of a new era in oncology, where technology and science converge to combat cancer more effectively than ever before.”
Paige trained the new AI models using data from over 225,000 patients, involving a broad spectrum of gender, race, ethnicity, and region, to provide a holistic understanding of cancer.
The dataset also includes more than 40 different tissue types stained with H&E and diverse immune stains (IHC), making it useful for diverse applications.
Virchow2G, which involves 1.8 billion parameters, is the largest pathology model ever created.
Paige said that its models, trained using Microsoft’s researchers and its advanced supercomputing infrastructure, have created a new record in AI training scale.
The company has used its technology to develop a universal clinical AI application that supports pathologists in identifying and diagnosing cancer across over 40 tissue types.
Furthermore, Paige has developed AI modules as pre-built solutions for life sciences, pharmaceutical, and research entities, to better understand the genetic markers of cancer.
Paige Technology senior vice president Razik Yousfi said: “This second generation of Paige’s Virchow model outperforms anything in the industry and continues to grow in knowledge and capability, bringing us closer to making precision medicine a reality.
“We are not only expanding capabilities, increasing accuracy, and reducing time in the cancer diagnosis process, but also pushing the boundaries of what’s possible.
“Our goal is to continue to bring the most advanced AI to pathology, leading to better patient outcomes and significant advancements in disease understanding and treatment.”
