Self-supervised large-scale kidney abnormality detection in drug safety assessment studies
This addresses the costly and time-consuming process of preclinical drug development for pharmaceutical companies, though it appears incremental as it builds on existing foundation model features.
The researchers tackled the problem of detecting kidney abnormalities in drug safety assessment studies, which requires examining hundreds to thousands of whole-slide images, by developing a self-supervised model that achieved an area under the ROC curve of 0.62 and a negative predictive value of 89%.
Kidney abnormality detection is required for all preclinical drug development. It involves a time-consuming and costly examination of hundreds to thousands of whole-slide images per drug safety study, most of which are normal, to detect any subtle changes indicating toxic effects. In this study, we present the first large-scale self-supervised abnormality detection model for kidney toxicologic pathology, spanning drug safety assessment studies from 158 compounds. We explore the complexity of kidney abnormality detection on this scale using features extracted from the UNI foundation model (FM) and show that a simple k-nearest neighbor classifier on these features performs at chance, demonstrating that the FM-generated features alone are insufficient for detecting abnormalities. We then demonstrate that a self-supervised method applied to the same features can achieve better-than-chance performance, with an area under the receiver operating characteristic curve of 0.62 and a negative predictive value of 89%. With further development, such a model can be used to rule out normal slides in drug safety assessment studies, reducing the costs and time associated with drug development.