Deep Learning‐Based Super‐Resolution for Vessel Enhancement in Photoacoustic Microscopy Imaging
Journal of Biophotonics · 2026
DOI: 10.1002/jbio.70221 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Biophotonics, 2026. Verfasst von Thi Thu Ha Vu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Industry 4.0 Convergence Bionics Engineering, Pukyong National University, Busan, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Photoacoustic Techniques, Image Processing, Computer-Assisted, Microscopy. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: the Pukyong National University Industry-university Cooperation Foundation's 2024 Post-Doc support project, This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (no. 2022R1A5A8023404).
Abstract (Originalsprache)
Photoacoustic imaging (PAI) is an advanced imaging technique for high‐resolution (HR), non‐invasive visualization of vascular networks, offering distinct advantages in functional and structural imaging. However, its performance is often constrained by trade‐offs between spatial resolution and imaging depth, as well as noise and artifacts caused by system limitations and tissue properties. Here, we introduce GDSU‐Net, a fine‐tuned neural network designed for super‐resolution (SR) reconstruction of PAI. GDSU‐Net builds on the U‐Net architecture and incorporates four key components: group normalization, depthwise separable convolutions, squeeze‐and‐excitation (SE) blocks, and a pixelshuffle‐based decoder. Experimental results demonstrate that GDSU‐Net achieves a structural similarity index of 0.889 and a peak signal‐to‐noise ratio (PSNR) of 31.979 dB, while reducing the root mean square error (RMSE) to 0.032 and the mean absolute error (MAE) to 0.025. Visual evaluations confirm its effectiveness in restoring vascular details with preserved anatomical fidelity. These findings highlight GDSU‐Net as a computationally efficient solution for super‐resolution enhancement in PAI.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Industry 4.0 Convergence Bionics Engineering, Pukyong National University, Busan, Republic of Korea.
- Smart Gym-Based Translational Research Center for Active Senior's Healthcare, Pukyong National University, Busan, Republic of Korea.
- Digital Healthcare Research Center, Pukyong National University, Busan, Republic of Korea.
- Department of Biomedical Engineering, Pukyong National University, Busan, Republic of Korea.
- Ohlabs Corp., Busan, Republic of Korea.
ORCID-Profile: Sudip Mondal
Förderung
- the Pukyong National University Industry-university Cooperation Foundation's 2024 Post-Doc support project
- This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (no. 2022R1A5A8023404)
Zitieren
APA
Vu, T. T. H., Tak, S., Vo, T. H., Nguyen, V. B., Nguyen, D. T., Phan, L. K., Choi, J., Mondal, S., & Oh, J. (2026). Deep Learning‐Based Super‐Resolution for Vessel Enhancement in Photoacoustic Microscopy Imaging. Journal of Biophotonics. https://doi.org/10.1002/jbio.70221
Vancouver
Vu TTH, Tak S, Vo TH, Nguyen VB, Nguyen DT, Phan LK, et al. Deep Learning‐Based Super‐Resolution for Vessel Enhancement in Photoacoustic Microscopy Imaging. Journal of Biophotonics. 2026. doi:10.1002/jbio.70221
BibTeX
@article{Vu2026,
author = {Vu, Thi Thu Ha and Tak, Soonhyuk and Vo, Tan Hung and Nguyen, Van Bang and Nguyen, Dinh Tuan and Phan, Le Khuong and Choi, Jaeyeop and Mondal, Sudip and Oh, Junghwan},
title = {Deep Learning‐Based Super‐Resolution for Vessel Enhancement in Photoacoustic Microscopy Imaging},
journal = {Journal of Biophotonics},
year = {2026},
doi = {10.1002/jbio.70221}
}
EUVIMED