October 21, 2020
Keio University
Kindai University
Institute of Industrial Science, The University of Tokyo
Sanyo-Onoda City University / Yamaguchi Tokyo University of Science
A group of researchers, including Yudai Tokuoka (a third-year student in the Doctoral Programs), Associate Professor Akira Funahashi, and Assistant Professor Takahiro Yamada from the Department of Biosciences and Informatics, Faculty of Science and Technology, Keio University; Associate Professor Kazuo Yamagata from the Faculty of Biology-Oriented Science and Technology, Kindai University; Associate Professor Tetsuya Kobayashi from the Institute of Industrial Science, The University of Tokyo; and Professor Yoshiko Hiroi from Sanyo-Onoda City University / Yamaguchi Tokyo University of Science, has successfully developed an algorithm (QCANet) that uses deep learning to accurately identify cell nuclei from 3D fluorescence microscopy images of mouse zygotes. Furthermore, QCANet has successfully surpassed 3D Mask R-CNN, known as the world's leading nucleus identification algorithm, in identifying the nuclei of embryos from three species (mice, nematodes, and Drosophila). The establishment of this foundational technology for quantitatively evaluating embryo quality is expected to have applications in areas such as regenerative medicine and fertility treatment.
The results of this research were published as an online preliminary report on the website of the academic journal *npj Systems Biology and Applications* on October 20 (UK time).
Please see below for the full press release.