Paige Expands Single AI Application to Detect Common, Rare Variants, and Precursor Lesions to Cancer Across More Than 40 Organs and Tissues
Newly Updated Paige PanCancer Detect*, Powered by Virchow V2, Adds to Potential Cancer Detection Capabilities
NEW YORK-(BUSINESS WIRE)-Paige, a leader in next-generation AI technology, today announced an expansion of Paige PanCancer Detect, the first AI application capable of identifying cancer across a wide range of tissue and organ types. Originally launched in early 2024 with the ability to help pathologists detect cancer in over 17 different tissues, Paige PanCancer Detect capabilities have now extended to more than 40 tissue and organ types. This enhancement has been made possible by using Virchow V2, one of Paige’s state-of-the-art foundation models. Virchow V2 is trained on an unprecedented 3 million digitized slides and 1.8 billion parameters1.
“By leveraging the tissue-agnostic capabilities of Virchow V2, Paige PanCancer Detect transforms cancer detection into a broad, scalable AI solution that generalizes the concept of ‘cancer’ across tissues,” said Siqi Liu, Director of AI Science at Paige. “This unique approach, originally demonstrated in our research published in Nature Medicine, has shown in our studies to be effective in detecting both rare cancer variants, low-prevalence cancers, and even precancerous lesions—challenges that traditional task-specific AI models often struggle to address2.”
Paige PanCancer Detect has the potential to support pathology labs by automatically screening cases, prioritizing those with cancer, and allowing pathologists to focus on the most critical cases—reducing time to diagnosis. It also could be used to enhance quality control (QC) by quickly screening every case, flagging potential diagnostic discrepancies, and minimizing errors to alleviate resource constraints within the lab and ultimately improve patient care.
The first version of Paige PanCancer Detect has already been utilized and independently tested in a study assessing 62 challenging cases across 16 tissue types3. During the study, the software flagged one case with a discrepant result, which was ultimately resolved in favor of the AI’s assessment. Dr. Catarina Eloy, head of the Pathology Department at Ipatimup (Porto, Portugal), and main author of the study, concluded that “Paige PanCancer Detect identifies slides suspicious for malignancy with strong overall performance in H&E-stained WSIs, paving the way for a clinically applicable multi-organ screening tool.”
Paige PanCancer Detect is currently available through Paige’s FullFocus image viewer and will soon be accessible through Paige’s established platform partners, including PathPresenter, Aiforia, Indica Labs, PathAI, and Gestalt.