Unsupervised Segmentation of 3D Microvascular Photoacoustic Images Using Deep Generative Learning
Advanced Science · 2024
DOI: 10.1002/advs.202402195 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, 2024. Verfasst von Paul W Sweeney und 5 weiteren Autor:innen. Beteiligte Einrichtung: Cancer Research UK Cambridge Institute, University of Cambridge, Robinson Way, Cambridge, CB2 0RE, UK. Hauptthemen laut MEDLINE: Photoacoustic Techniques, Deep Learning, Imaging, Three-Dimensional. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 86 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CRUK, Walter Benjamin Stipendium of the Deutsche Forschungsgemeinschaft, NPL.
Abstract (Originalsprache)
Mesoscopic photoacoustic imaging (PAI) enables label‐free visualization of vascular networks in tissues with high contrast and resolution. Segmenting these networks from 3D PAI data and interpreting their physiological and pathological significance is crucial yet challenging due to the time‐consuming and error‐prone nature of current methods. Deep learning offers a potential solution; however, supervised analysis frameworks typically require human‐annotated ground‐truth labels. To address this, an unsupervised image‐to‐image translation deep learning model is introduced, the Vessel Segmentation Generative Adversarial Network (VAN‐GAN). VAN‐GAN integrates synthetic blood vessel networks that closely resemble real‐life anatomy into its training process and learns to replicate the underlying physics of the PAI system in order to learn how to segment vasculature from 3D photoacoustic images. Applied to a diverse range of in silico, in vitro, and in vivo data, including patient‐derived breast cancer xenograft models and 3D clinical angiograms, VAN‐GAN demonstrates its capability to facilitate accurate and unbiased segmentation of 3D vascular networks. By leveraging synthetic data, VAN‐GAN reduces the reliance on manual labeling, thus lowering the barrier to entry for high‐quality blood vessel segmentation (F1 score: VAN‐GAN vs. U‐Net = 0.84 vs. 0.87) and enhancing preclinical and clinical research into vascular structure and function.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cancer Research UK Cambridge Institute, University of Cambridge, Robinson Way, Cambridge, CB2 0RE, UK.
- Department of Physics, University of Cambridge, JJ Thomson Avenue, Cambridge, CB3 0HE, UK.
ORCID-Profile: Paul W Sweeney, Lina Hacker, Thierry L Lefebvre, Sarah E Bohndiek
Förderung
- CRUK
- Walter Benjamin Stipendium of the Deutsche Forschungsgemeinschaft
- NPL
- Wellcome Trust
- Cambridge Trust
- Cancer Research UK
- CRUK RadNet Cambridge
- Engineering and Physical Sciences Research Council
Zitieren
APA
Sweeney, P. W., Hacker, L., Lefebvre, T. L., Brown, E. L., Gröhl, J., & Bohndiek, S. E. (2024). Unsupervised Segmentation of 3D Microvascular Photoacoustic Images Using Deep Generative Learning. Advanced Science. https://doi.org/10.1002/advs.202402195
Vancouver
Sweeney PW, Hacker L, Lefebvre TL, Brown EL, Gröhl J, Bohndiek SE. Unsupervised Segmentation of 3D Microvascular Photoacoustic Images Using Deep Generative Learning. Advanced Science. 2024. doi:10.1002/advs.202402195
BibTeX
@article{Sweeney2024,
author = {Sweeney, Paul W and Hacker, Lina and Lefebvre, Thierry L and Brown, Emma L and Gröhl, Janek and Bohndiek, Sarah E},
title = {Unsupervised Segmentation of 3D Microvascular Photoacoustic Images Using Deep Generative Learning},
journal = {Advanced Science},
year = {2024},
doi = {10.1002/advs.202402195}
}
EUVIMED