Diffusion model-based image generation from rat brain activity
PLOS ONE · 2024
DOI: 10.1371/journal.pone.0309709 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Kotaro Yamashiro und 2 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Pharmaceutical Sciences, The University of Tokyo, Tokyo, Japan. Hauptthemen laut MEDLINE: Brain, Brain-Computer Interfaces. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: KOSÉ Cosmetology Research Foundation, JST ERATO, JSPS Grants-in-Aid for Scientific Research.
Abstract (Originalsprache)
Brain-computer interface (BCI) technology has gained recognition in various fields, including clinical applications, assistive technology, and human-computer interaction research. BCI enables communication, control, and monitoring of the affective/cognitive states of users. Recently, BCI has also found applications in the artistic field, enabling real-time art composition using brain activity signals, and engaging performers, spectators, or an entire audience with brain activity-based artistic environments. Existing techniques use specific features of brain activity, such as the P300 wave and SSVEPs, to control drawing tools, rather than directly reflecting brain activity in the output image. In this study, we present a novel approach that uses a latent diffusion model, a type of deep neural network, to generate images directly from continuous brain activity. We demonstrate this technology using local field potentials from the neocortex of freely moving rats. This system continuously converted the recorded brain activity into images. Our end-to-end method for generating images from brain activity opens new possibilities for creative expression and experimentation. Notably, our results show that the generated images successfully reflect the dynamic and stochastic nature of the underlying neural activity, providing a unique procedure for visualization of brain function.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Graduate School of Pharmaceutical Sciences, The University of Tokyo, Tokyo, Japan.
- Institute for AI and Beyond, The University of Tokyo, Tokyo, Japan.
- Center for Information and Neural Networks, National Institute of Information and Communications Technology, Suita City, Osaka, Japan.
ORCID-Profile: Kotaro Yamashiro, Nobuyoshi Matsumoto, Yuji Ikegaya
Förderung
- KOSÉ Cosmetology Research Foundation
- JST ERATO
- JSPS Grants-in-Aid for Scientific Research
- AMED CREST
Zitieren
APA
Yamashiro, K., Matsumoto, N., & Ikegaya, Y. (2024). Diffusion model-based image generation from rat brain activity. PLOS ONE. https://doi.org/10.1371/journal.pone.0309709
Vancouver
Yamashiro K, Matsumoto N, Ikegaya Y. Diffusion model-based image generation from rat brain activity. PLOS ONE. 2024. doi:10.1371/journal.pone.0309709
BibTeX
@article{Yamashiro2024,
author = {Yamashiro, Kotaro and Matsumoto, Nobuyoshi and Ikegaya, Yuji},
title = {Diffusion model-based image generation from rat brain activity},
journal = {PLOS ONE},
year = {2024},
doi = {10.1371/journal.pone.0309709}
}
EUVIMED