Vicky Goh

This study benchmarks the accuracy and cost-effectiveness of federated learning and consensus-based learning in medical data analysis, finding that consensus-based learning is more cost-effective with comparable accuracy.

This paper introduces WSUnet, a weakly supervised Unet that generates voxel-level explanations for image-level predictions, outperforming existing methods in lung cancer detection.

The paper introduces conliga, a method for inferring high-resolution SCNA profiles from a low-cost and simple assay, addressing the need for affordable SCNA analysis in clinical settings.