GI-SleepNet: A Highly Versatile Image-Based Sleep Classification Using a Deep Learning Algorithm

Tianxiang Gao, Jiayi Li, Yuji Watanabe, Chijung Hung, Akihiro Yamanaka, Kazumasa Horie, Masashi Yanagisawa, Masahiro Ohsawa, Kazuhiko Kume

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Sleep-stage classification is essential for sleep research. Various automatic judgment programs, including deep learning algorithms using artificial intelligence (AI), have been developed, but have limitations with regard to data format compatibility, human interpretability, cost, and technical requirements. We developed a novel program called GI-SleepNet, generative adversarial network (GAN)-assisted image-based sleep staging for mice that is accurate, versatile, compact, and easy to use. In this program, electroencephalogram and electromyography data are first visualized as images, and then classified into three stages (wake, NREM, and REM) by a supervised image learning algorithm. To increase its accuracy, we adopted GAN and artificially generated fake REM sleep data to equalize the number of stages. This resulted in improved accuracy, and as little as one mouse’s data yielded significant accuracy. Due to its image-based nature, the program is easy to apply to data of different formats, different species of animals, and even outside sleep research. Image data can be easily understood; thus, confirmation by experts is easily obtained, even when there are prediction anomalies. As deep learning in image processing is one of the leading fields in AI, numerous algorithms are also available.

Original languageEnglish (US)
Pages (from-to)581-597
Number of pages17
JournalClocks and Sleep
Issue number4
StatePublished - Dec 2021
Externally publishedYes


  • 2D-CNN
  • EEG
  • GANs
  • sleep scoring
  • tiny dataset

ASJC Scopus subject areas

  • Neuroscience (miscellaneous)
  • Neurology


Dive into the research topics of 'GI-SleepNet: A Highly Versatile Image-Based Sleep Classification Using a Deep Learning Algorithm'. Together they form a unique fingerprint.

Cite this