Yinyin Yuan

The paper introduces a modular AI framework for ROI selection in spatial profiling, showing hybrid generalist-specialist strategies balance signal preservation, concordance, consistency, and efficiency.

This paper develops an interpretable AI framework for leukocyte morphology classification in peripheral blood smears, achieving high accuracy with reduced annotation needs and providing clinical tools for integration.

The paper develops DeMixNB, a deconvolution model for sparse-count RNA sequencing data, showing its utility in analyzing tumor cell plasticity in breast and lung cancer.

The paper shows that epithelial-mesenchymal plasticity is regulated by inflammatory signalling networks linked to cell morphology through changes in microtubule and nuclear organization.