Advocacy group Friends of Cancer Research on Thursday launched a research project focused on improving biomarker assessment across computational pathology platforms.
The Digital and Computational Pathology Tool Harmonization (Digital PATH) Project aims to identify factors that may contribute to variability in biomarker assessment across computational pathology platforms, propose areas for alignment in the field, and provide insights for shaping regulatory processes.
The nonprofit has convened different groups to address variability in biomarker assessment and propose solutions for the field, including algorithm developers, patient advocates, government officials, pathologists, and drug developers. The organizations, institutions, and companies that will be partnering on the Digital PATH Project include 4D Path, Amgen, AstraZeneca, Bristol Myers Squibb, EMD Serono, GlaxoSmithKline, Indica Labs, Johnson & Johnson Innovative Medicine, Loxo@Lilly, Lunit, Massachusetts General Hospital, MD Anderson Cancer Center, Merck, National Cancer Institute, Nucleai, PathAI, Patient Advocates, Roche Diagnostics, Sanofi, Tempus AI, the University of North Carolina, Verily, ZAS Hospitals Antwerp, and the US Food and Drug Administration.
The project will initially focus on HER2 biomarkers by assessing concordance of HER2 expression measurements from breast cancer samples across testing platforms and identifying factors that contribute to variability between tests. Samples for this research are being provided by the department of pathology at ZAS Hospitals in Antwerp, Belgium.
“As artificial intelligence tools increasingly become part of healthcare, their use in digital and computational pathology open remarkable opportunities for enhanced diagnostic insights,” Friends of Cancer Research CEO Jeff Allen said in a statement. “This new collaborative research partnership will help inform future policies toward optimal regulation and utilization of these advanced technologies.”
Friends of Cancer Research has spearheaded similar projects aimed at understanding the differences between genomic testing platforms assessing complex biomarkers such as homologous recombination deficiency (HRD) and tumor mutational burden (TMB).