01 Oct 2025
A new model, PSScreen, was developed to screen for multiple retinal diseases using partially labeled datasets from diverse medical sites, addressing challenges like domain shifts and incomplete annotations. The method established a new benchmark in partially supervised learning, achieving superior domain generalization on unseen data compared to prior state-of-the-art approaches and outperforming leading vision-language foundation models in zero-shot screening.
There are no more papers matching your filters at the moment.
