Microsoft to Build Largest Image-Based AI Model to Detect Cancer


Microsoft is planning to build the largest image-based artificial intelligence (AI) model to fight cancer — with up to four million digitized microscopy slides of different types of cancer being used in the groundbreaking project.

On Thursday, Microsoft announced that it would be collaborating with digital pathology provider Paige to build the world’s largest image-based artificial intelligence model for identifying cancer.

According to a press release shared by Microsoft and Paige, the AI model is training on an unprecedented amount of data that includes billions of images.

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

CNBC News reports that to diagnose cancer, pathologists will usually have to examine a piece of tissue on a glass slide under a microscope.

However, if pathologists miss something when examining a piece of tissue under a microscope, it can have dire consequences for patients.

Researchers hope Microsoft’s and Paige’s image-based AI model will help medical professionals detect cancers earlier and come up with treatment options efficiently.

“We strongly believe we will significantly advance the state-of-the-art in cancer imaging. Through the development of this model, we will help improve the lives of the millions of people who are affected by cancer every day,” Razik Yousfi, SVP of Technology at Paige, says in the statement.

Paige developed the first large foundation model using over one billion images from half a million pathology slides across multiple cancer types.

The company says it will now be incorporating up to four million digitized microscopy slides across multiple types of cancer in its project with Microsoft.

Paige will utilize Microsoft’s advanced supercomputing infrastructure to train the technology at scale and ultimately deploy it to hospitals and laboratories across the globe using Azure.

In June, PetaPixel reported on a new smartphone camera lens that takes detailed photos of moles or skin lesions which could be used to diagnose tens of thousands of skin cancer patients faster.

The small camera lens attaches to a smartphone and essentially turns the phone into a microscope that provides high-resolution photos to doctors without the patient having to attend hospital.

Image credits: Header photo licensed via Depositphotos.