Digital pathology firm PathAI has announced a new partnership with University Medical Center Utrecht, one of Europe’s leading academic medical centres, to deploy AISight Dx, PathAI’s digital pathology image management system, to accelerate the adoption of AI algorithms.
University Medical Center (UMC) Utrecht was one of the first adopters of digital pathology globally. In choosing AISight Dx, UMC Utrecht’s researchers will use AISight Dx to evaluate and deploy algorithms from PathAI and other commercial developers for a variety of applications including PD-L1, HER2, Ki-67, MASH, tumor microenvironment, and others.
AISight Dx is an AI-native and open digital pathology platform and image management system. It allows both PathAI’s own AI models and PathAI partner algorithms to be deployed natively within the same user interface. Built on a secure cloud infrastructure, AISight Dx provides laboratories and academic centres such as UMC Utrecht with elastic computing resources to scale AI use seamlessly, while ensuring that all data storage and processing remain entirely within Europe. This and AISight Dx’s robust cell-level AI visualisation enables users to easily test, compare, and adopt the best-performing tools across a wide spectrum of clinical and research applications without additional integration work or fragmented workflows.
“We are excited to collaborate with UMC Utrecht, Paul van Diest, and his team,” said Eric Walk, MD, Chief Medical Officer of PathAI. “UMC Utrecht has long been a global pioneer in digital pathology, and their leadership makes them an ideal partner as we advance the use of AI in pathology. We look forward to supporting their efforts to evaluate and deploy a diverse range of algorithms on AISight Dx.”
“AISight Dx gives our researchers easy access to a wide portfolio of AI algorithms through a single platform,” said Professor Paul van Diest, Head of the Department of Pathology at UMC Utrecht. “Being able to deploy, test, and compare multiple algorithms without complex integrations helps us focus on what matters: Understanding their performance and how they can bring us closer to routine, AI-supported pathology workflows.”