Microsoft has joined hands with Paige, a digital pathology provider, to build world’s largest image-based artificial intelligence (AI) models that can fight against cancer.AI 

Microsoft and Paige Team Up to Create AI-Powered Cancer Diagnosis Model

Tech giant Microsoft has joined hands with digital pathology provider Paige to build the world’s largest image-based artificial intelligence models that can fight cancer.

The new AI model is orders of magnitude larger than any other image-based AI model in existence today and is configured with billions of parameters, the companies said.

It helps capture the subtle complexities of cancer and serves as a cornerstone for next-generation clinical applications and computational biomarkers that push the boundaries of oncology and pathology.

The AI model can identify both common cancers and rare cancers that are notoriously difficult to diagnose.

“We are creating new artificial intelligence models that enable unprecedented insight into the pathology of cancer. Unleashing the power of AI is a game changer in advancing healthcare to improve lives,” said Desney Tan, vice president and CEO of Microsoft Health Futures.

Paige, a global leader in digital pathology solutions and clinical artificial intelligence, developed the first large-scale baseline model using more than a billion images from half a million pathology slides across cancer types.

In the next phase of development, Paige will include up to four million digitized microscope slides from an unparalleled petabyte-scale archive of clinical data across multiple cancer types. Paige leverages Microsoft’s advanced supercomputing infrastructure to train the technology at scale and eventually deploy it to hospitals and labs around the world using Azure.

“We strongly believe that we are significantly promoting the cutting-edge technology of cancer imaging. By developing this model, we are helping to improve the lives of millions of people living with cancer every day,” Paige CTO Razik Yousfi said in a statement.

Related posts

Leave a Comment