Reproduce “The DynaCell Evaluation Suite for Dynamic 3D Virtual Staining of Live Cells” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Alexandr A. Kalinin, Dihan Zheng, Taylla Milena Theodoro, Ivan Ivanov, Eduardo Hirata-Miyasaki, See-Chi Lee, Aofei Liu, Sricharan Reddy Varra and 7 more
DynaCell evaluates virtual staining models to determine whether predictions from label-free images preserve information for biological measurements. It compares regression, adversarial, and flow-matching methods using pixel, segmentation, and single-cell phenotype metrics. In the same-generator iPSC nucleus test, Pix2Pix3D scores higher on structure, while CELL-Diff3D has lower KID. CELL-Diff3D better matches infection-associated embedding shifts, without validating virtual stains as replacements for fluorescence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.