An open-source Fiji pipeline for automated yeast cell image processing and deterministic classification of cell-cycle, spindle and protein dynamics is presented and demonstrates a 50-fold acceleration with ∼6% deviation from manual analysis.
How embryos adapt their internal cellular machinery to reductions in cell size during development remains a fundamental question in cell biology. Here, we use high-resolution lattice light-sheet fluorescence microscopy and automated image analysis to quantify lineage-resolved mitotic spindle and chromosome segregation...
Chukwuebuka William Okafornta, R. Farhadifar, G. Fabig et al.· Nature Communications· 0 citations
FOCUS-3D is introduced, a robust, broadly generalizable volumetric cell segmentation framework built on a large, diverse manually annotated cell resource and advanced AI designs that achieves state-of-the-art performance across diverse species, tissues, fluorescent reporters and imaging modalities.
Qing-Hua Zhang, Ze-Yu Mu, Bo-Qi Liu et al.· bioRxiv· 0 citations
A robust pipeline for MS2 tagging of endogenous transcripts in human induced pluripotent stem cells is established, coupled with single-particle tracking and Hidden Markov Modelling to map mRNA mobility landscapes during differentiation and cell state transitions, revealing a conserved principle.
The results suggest that temporal context is not automatically sufficient to improve early S detection, and more careful temporal model design, training strategy, and evaluation using consistent data splits are needed to determine whether temporal information can improve Hoechst-based cell-cycle segmentation.
By separating reusable analysis logic from project-specific configuration, CellColoc offers an extensible foundation for community-driven microscopy workflows that need transparent per-cell overlap classification, morphology readouts, and reusable batch analysis.
F. Musacchio, Henrike Antony, Arush Baijal et al.· bioRxiv· 1 citation
The proposed HOCT is easier to fine-tune, quickly reducing tracking errors by 59% with 400 annotations in a human-in-the-loop setting, outperforming LoRA fine-tuning of competing transformer baselines (6.75% improvement).
Jordão Bragantini, Ilan Theodoro, L. Royer· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
