Hongshen Ma

Regularized single-cell imaging in nanowells enables training of generalizable AI models for accurate, stain-free viability screening across previously unseen cell types and contexts.

This paper introduces a high-throughput single-cell motility assay using nanowell-in-microwell plates to analyze migration behavior and identify distinct motility phenotypes.

This paper develops a deep learning model to detect RBC deformability and storage-related changes in blood smears, showing high accuracy in categorizing deformability groups.

This paper introduces a microfluidic chemotaxis assay using centrifugal alignment to enable scalable, multiplexed end-point chemotaxis testing without continuous imaging.

This paper develops a deep learning method to phenotype cells using low-resolution microscopy images, achieving 94.6% accuracy in identifying cancer cell lines.