A deep learning approach to predict differentiation outcomes in hypothalamic-pituitary organoids.

Journal: Communications biology
PMID:

Abstract

We use three-dimensional culture systems of human pluripotent stem cells for differentiation into pituitary organoids. Three-dimensional culture is inherently characterized by its ability to induce heterogeneous cell populations, making it difficult to maintain constant differentiation efficiency. That is why the culture process involves empirical aspects. In this study, we use deep-learning technology to create a model that can predict from images of organoids whether differentiation is progressing appropriately. Our models using EfficientNetV2-S or Vision Transformer, employing VENUS-coupled RAX expression, predictively class bright-field images of organoids into three categories with 70% accuracy, superior to expert-observer predictions. Furthermore, the model obtained by ensemble learning with the two algorithms can predict RAX expression in cells without RAX::VENUS, suggesting that our model can be deployed in clinical applications such as transplantation.

Authors

  • Tomoyoshi Asano
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Hidetaka Suga
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan. sugahide@med.nagoya-u.ac.jp.
  • Hirohiko Niioka
    Graduate School of Engineering Science, Osaka University, 1-3 Machikane-Yama, Toyonaka, Osaka, 560-8531, Japan.
  • Hiroshi Yukawa
    Institutes of Innovation for Future Society, Nagoya University, Nagoya, 464-8601, Japan.
  • Mayu Sakakibara
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Shiori Taga
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Mika Soen
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Tsutomu Miwata
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Hiroo Sasaki
    Department of Neurosurgery, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Tomomi Seki
    Department of Obstetrics and Gynecology, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Saki Hasegawa
    Department of Animal Sciences, Nagoya University Graduate School of Bioagricultural Sciences, Nagoya, 464-8601, Japan.
  • Sou Murakami
    Department of Science, Osaka University, Osaka, 560-0043, Japan.
  • Masatoshi Abe
    Department of Pathology, Osaka University Graduate School of Medicine, Osaka, Japan.
  • Yoshinori Yasuda
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Takashi Miyata
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Tomoko Kobayashi
    Tohoku Medical Megabank Organization (ToMMo), Tohoku University, Sendai, Miyagi, Japan.
  • Mariko Sugiyama
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Takeshi Onoue
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Daisuke Hagiwara
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya 466-8550, Japan.
  • Shintaro Iwama
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, 466-8550, Japan.
  • Yoshinobu Baba
    Department of Biomolecular Engineering, Graduate School of Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya 464-8603, Japan.
  • Hiroshi Arima
    Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya 466-8550, Japan.