Zachary Sims

miniMTI reduces the number of molecular markers needed for multiplex tissue imaging by combining H&E with a few measured markers, preserving biological and clinical information.

The paper introduces a computational method to synthesize marker stains from H&E images, improving marker prediction and reducing reliance on experimental data.

UniFORM normalizes multiplex tissue imaging data by aligning negative populations and preserving positive variation, outperforming existing methods in batch effect mitigation and downstream analysis.

The paper introduces a computational method to reduce CyCIF panel size while preserving information content through masked imaging modeling and imputation.

The paper introduces a method to evaluate segmentation performance in multiplex tissue imaging without ground truth labels by comparing segmentations from an ensemble of models.