Virtual tissue microstructure reconstruction across species using generative deep learning
PLOS ONE · 12.07.2024 · 19 (7) · e0306073
DOI: 10.1371/journal.pone.0306073 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 12.07.2024. Verfasst von Nicolás Bettancourt und 7 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Biological Sciences, Department of Cell Biology, Universidad de Concepción, Concepción, Chile. Hauptthemen laut MEDLINE: Deep Learning, Liver. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fondo Nacional de Desarrollo Científico y Tecnológico.
Abstract (Originalsprache)
Analyzing tissue microstructure is essential for understanding complex biological systems in different species. Tissue functions largely depend on their intrinsic tissue architecture. Therefore, studying the three-dimensional (3D) microstructure of tissues, such as the liver, is particularly fascinating due to its conserved essential roles in metabolic processes and detoxification. Here, we present TiMiGNet, a novel deep learning approach for virtual 3D tissue microstructure reconstruction using Generative Adversarial Networks and fluorescence microscopy. TiMiGNet overcomes challenges such as poor antibody penetration and time-intensive procedures by generating accurate, high-resolution predictions of tissue components across large volumes without the need of paired images as input. We applied TiMiGNet to analyze tissue microstructure in mouse and human liver tissue. TiMiGNet shows high performance in predicting structures like bile canaliculi, sinusoids, and Kupffer cell shapes from actin meshwork images. Remarkably, using TiMiGNet we were able to computationally reconstruct tissue structures that cannot be directly imaged due experimental limitations in deep dense tissues, a significant advancement in deep tissue imaging. Our open-source virtual prediction tool facilitates accessible and efficient multi-species tissue microstructure analysis, accommodating researchers with varying expertise levels. Overall, our method represents a powerful approach for studying tissue microstructure, with far-reaching applications in diverse biological contexts and species.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Faculty of Biological Sciences, Department of Cell Biology, Universidad de Concepción, Concepción, Chile.
- Faculty of Biological Sciences, Grupo de Procesos en Biología del Desarrollo (GDeP), Universidad de Concepción, Concepción, Chile.
- Faculty of Engineering, Department of Electrical Engineering, Universidad de Concepción, Concepción, Chile.
- Max Planck Institute of Molecular Cell Biology and Genetics, Dresden, Germany.
- Department of Systems Biology of Development, University of Konstanz, Konstanz, Germany.
- Facultad de Ciencias Técnicas, Universidad Internacional Del Ecuador UIDE, Quito, Ecuador.
ORCID-Profile: Pamela Guevara, Fabián Segovia-Miranda, Hernán Morales-Navarrete
Förderung
- Fondo Nacional de Desarrollo Científico y Tecnológico
Zitieren
APA
Bettancourt, N., Pérez-Gallardo, C., Candia, V., Guevara, P., Kalaidzidis, Y., Zerial, M., Segovia-Miranda, F., & Morales-Navarrete, H. (2024). Virtual tissue microstructure reconstruction across species using generative deep learning. PLOS ONE, 19(7), e0306073. https://doi.org/10.1371/journal.pone.0306073
Vancouver
Bettancourt N, Pérez-Gallardo C, Candia V, Guevara P, Kalaidzidis Y, Zerial M, et al. Virtual tissue microstructure reconstruction across species using generative deep learning. PLOS ONE. 2024;19(7):e0306073. doi:10.1371/journal.pone.0306073
BibTeX
@article{Bettancourt2024,
author = {Bettancourt, Nicolás and Pérez-Gallardo, Cristian and Candia, Valeria and Guevara, Pamela and Kalaidzidis, Yannis and Zerial, Marino and Segovia-Miranda, Fabián and Morales-Navarrete, Hernán},
title = {Virtual tissue microstructure reconstruction across species using generative deep learning},
journal = {PLOS ONE},
year = {2024},
volume = {19},
number = {7},
pages = {e0306073},
doi = {10.1371/journal.pone.0306073}
}
EUVIMED