Mindpeak's in npj precsion oncology:  IHC foundation model helped pathologists identify >30% more gastric cancer patients to be eligible for IO therapies, while at the same time improving accuracy and concordance of readers

‍

npj Precision Oncology study shows pathologists find >30% more patients eligible for treatment using AI based on PeakFoundation, Mindpeak GmbH’s IHC foundation model

We are pleased to announce that the results of a large-scale study on Gastric PD-L1 scoring involving our IHC foundation model and expert pathologists from leading institutions including Mayo Clinic, Emory University, John Hopkins University, MD Anderson Cancer Center, Memorial Sloan Kettering Cancer Center and other clinics have been published in npj Precision Oncology (via Springer Nature).

Gastric PD-L1 assessment is a critical task for immunotherapy decisions, but often prone to variability among pathologists. The effect of AI assistance in this challenging task was investigated by a group of experts in an augmented-reality setting, resulting in these keyfindings:

-AI assistance improves pathologists’ scoring accuracy performance, both as a group and individually

-AI assistance may lead to identifying a larger number of patients eligible for therapy

-Cell-level interpretation guidelines by expert pathologists to direct AI development are key

‍

This study is an important step forward in our mission to provide personalised cancer treatment through AI tissue diagnostics and contribute to patient outcomes.Read the full paper here: https://lnkd.in/eKUukief