Kazuo Yamagata

The paper develops FL2-Net, a deep learning method for nuclear segmentation in bright-field microscopy images of mouse embryos, achieving higher birth prediction accuracy than existing methods and experts.

The paper reconstructs artificial nuclei with nuclear import activity in living mouse oocytes using T4 phage DNA, showing they can form functional nuclear structures similar to natural nuclei.

This paper develops a genetically encoded probe to visualize H4K20me1 in living cells and demonstrates its utility in knock-in mice.

This paper develops a method to count chromosomes in mouse embryos using CRISPR/dCas-mediated fluorescence in situ hybridization, improving accuracy over previous techniques.

The paper develops a deep learning algorithm to predict mouse embryo live birth potential from nuclear structural features in fluorescence images, achieving 83.87% accuracy.

This paper introduces a deep learning-based instance segmentation algorithm, QCA Net, which outperforms existing methods in segmenting nuclei in mouse embryos and provides quantitative developmental metrics.