Todd Sheridan

DIANNE enables rapid training and inference of spatial differential attributes in histology images without manual annotations, using mixup augmentation and foundation models.

This study uses spatial transcriptomics and deep learning to analyze melanoma treatment resistance, identifying persister states and resistance mechanisms with spatiotemporal resolution.

SAMPLER provides a statistical method to generate efficient whole slide image representations, achieving comparable or better accuracy than attention models while being significantly faster.

The paper presents a pan-cancer PDX histology image repository with genomic and pathological annotations for deep learning analysis of tumor regions and xenograft-transplant lymphoproliferative disorder prediction.

This paper introduces 'mones' as interpretable CNN features from H&E images that correlate with biological phenotypes and can accurately classify tumors and normals.