Our scientist Petr Holub and his colleagues from the European research infrastructure BBMRI published a new article in the prestigious journal Nature Communications. In it, they focus on the security risks of image sharing in the field of digital pathology.
Access to large volumes of so-called whole-slide images —high-resolution scans of complete pathological slides — has become a cornerstone of the development of novel artificial intelligence methods in pathology for diagnostic use, education and training of pathologists, and research. Nevertheless, a methodology based on risk analysis for evaluating the privacy risks associated with sharing such imaging data and applying the principle “as open as possible and as closed as necessary” is still lacking. In this article, researchers develop a model for privacy risk analysis for whole-slide images which focuses primarily on identity disclosure attacks, as these are the most important from a regulatory perspective.
Lead author Petr Holub said: „The raison d'être of this paper is to stimulate development of easy-to-access collections of histopathological data, by demonstrating privacy risks and developing guidelines for anonymisation and sharing of anonymised and pseudonymised WSI (whole slide imaging) data - namely for AI purposes in digital pathology, since AI is really transforming this field.“
The full article is available Nature Communications website.
