Shingo Sakashita

SPATNIC is a variational autoencoder that identifies cancer cells from spatial and single-cell transcriptomic data in colorectal cancer, outperforming existing tools and identifying a rare cancer stem cell population.

The paper identifies POSTN-expressing cancer-associated fibroblasts (CAFs) linked to chemoradiotherapy resistance in rectal cancer using spatial multi-omics data.

This study investigates how label noise in pathology segmentation affects AI model performance, finding that boundary-altering noise leads to overestimation of model accuracy.

The paper introduces KuLGaP, a selective measure to assess therapy response in patient-derived xenografts by comparing treatment and control arms, improving accuracy over existing methods.