The newest models, called Virchow2 and Virchow2G, were built on three million pathology slides from more than 40 different tissue types, according to an Aug. 8 news release from Paige.
The pathology slides were collected from 800 labs across 45 countries. The models, intended to help pathologists identify and diagnose cancer, were trained on data from more than 225,000 patients to “encompass a broad spectrum of gender, race, ethnicity, and geographical regions,” the release said.
“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,” Razik Yousfi, senior vice president of technology at Paige, said in the release.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
