TY - JOUR
T1 - GI-SleepNet
T2 - A Highly Versatile Image-Based Sleep Classification Using a Deep Learning Algorithm
AU - Gao, Tianxiang
AU - Li, Jiayi
AU - Watanabe, Yuji
AU - Hung, Chijung
AU - Yamanaka, Akihiro
AU - Horie, Kazumasa
AU - Yanagisawa, Masashi
AU - Ohsawa, Masahiro
AU - Kume, Kazuhiko
N1 - Funding Information:
This research was funded in part by the Japan Society for the Promotion of Science (JSPS) KAKENHI Grant Numbers JP18H02481,21H02529 to K.K.
Publisher Copyright:
© 2021 by the authors.
PY - 2021/12
Y1 - 2021/12
N2 - 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.
AB - 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.
KW - 2D-CNN
KW - EEG
KW - GANs
KW - sleep scoring
KW - tiny dataset
UR - http://www.scopus.com/inward/record.url?scp=85135814801&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135814801&partnerID=8YFLogxK
U2 - 10.3390/clockssleep3040041
DO - 10.3390/clockssleep3040041
M3 - Article
C2 - 34842647
AN - SCOPUS:85135814801
SN - 2624-5175
VL - 3
SP - 581
EP - 597
JO - Clocks and Sleep
JF - Clocks and Sleep
IS - 4
ER -