Automated analysis of mouse rearing using deep learning.

Journal: Journal of pharmacological sciences
Published Date: Jun 13, 2025

Abstract

Rodent rearing behavior is frequently assessed as an indicator of anxiety and exploratory tendencies. This study developed a convolutional recurrent neural network (CRNN) model to detect mouse rearing using overhead videos. Behavioral data from C57BL/6 mice under light and dark conditions were manually labeled frame-by-frame and used to train the CRNN model. Model performance was evaluated on separate test videos, achieving a sensitivity of 89.2 %, comparable to human observation. The model reliably detected increased rearing following caffeine administration and distinguished differences between day and night activity patterns.

Authors

  • Naoaki Sakamoto
  • Masahiro Fukuda
    Animal Radiology, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo, Japan; Food and Animal Systemics, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo, Japan.
  • Yusuke Miyazaki
    Animal Radiology, Graduate School of Agricultural and Life Sciences, The University of Tokyo.
  • Keisuke Omori
    Animal Radiology, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo, Japan; Food and Animal Systemics, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo, Japan.
  • Koji Kobayashi
    Department of Animal Radiology, Graduate School of Agricultural and Life Sciences, The University of Tokyo, 1-1-1, Yayoi, Bunkyo-ku, Tokyo, 113-8657, Japan.
  • Takahisa Murata
    Department of Animal Radiology, Graduate School of Agricultural and Life Sciences, The University of Tokyo, 1-1-1, Yayoi, Bunkyo-ku, Tokyo, 113-8657, Japan. amurata@mail.ecc.u-tokyo.ac.jp.

Keywords

External Resources

Popular Topics
Recent Journals