EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BDNet: A Real-Time Biomedical Image Denoising Network with Gradient Information Enhancement Loss

Lemin Shi iD, Xin Feng, Ping Gong, Dianxin Song, Hao Zhang, Langxi Liu, Yuqiang Zhang, Mingye Li iD

Biosensors · 01.01.2026 · 16 (1) · 26

DOI: 10.3390/bios16010026 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biosensors, online erschienen am 01.01.2026. Verfasst von Lemin Shi und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Changchun University of Science and Technology, No. 7186 Weixing Road, Changchun 130022, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Provincial Scientific and Technological Development Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Biomedical imaging plays a critical role in medical diagnostics and research, yet image noise remains a significant challenge that hinders accurate analysis. To address this issue, we propose BDNet, a real-time biomedical image denoising network optimized for enhancing gradient and high-frequency information while effectively suppressing noise. The network adopts a lightweight U-Net-inspired encoder–decoder architecture, incorporating a Convolutional Block Attention Module at the bottleneck to refine spatial and channel-wise feature extraction. A novel gradient-based loss function—combining Sobel operator-derived gradient loss with L1, L2, and LSSIM losses—ensures faithful preservation of fine structural details. Extensive experiments on the Fluorescence Microscopy Denoising (FMD) dataset demonstrate that BDNet achieves state-of-the-art performance across multiple metrics, including PSNR, RMSE, SSIM, and LPIPS, outperforming both convolutional and Transformer-based models in accuracy and efficiency. With its superior denoising capability and real-time inference speed, BDNet provides an effective and practical solution for improving biomedical image quality, particularly in fluorescence microscopy applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedMicroscopy, FluorescenceSignal-To-Noise RatioAlgorithmsHumansConvolutional Neural Networks

Stichwörter der Autor:innen

attention mechanismbiomedical image denoisingfluorescence microscopygradient-based losslightweight U-Net

Autor:innen und Institutionen

  • School of Computer Science and Technology, Changchun University of Science and Technology, No. 7186 Weixing Road, Changchun 130022, China.
  • School of Life Science and Technology, Changchun University of Science and Technology, No. 7186 Weixing Road, Changchun 130022, China.
  • School of Mathematics and Statistics, Changchun University of Science and Technology, No. 7186 Weixing Road, Changchun 130022, China.
  • Modern Industrial College, Jilin Jianzhu University, No. 5088, Xincheng Street, Changchun 130118, China.
  • School of Computing and Information Systems, University of Melbourne, Parkville, VIC 3010, Australia.

ORCID-Profile: Lemin Shi, Mingye Li

Förderung

  • Jilin Provincial Scientific and Technological Development Program

Zitieren

APA

Shi, L., Feng, X., Gong, P., Song, D., Zhang, H., Liu, L., Zhang, Y., & Li, M. (2026). BDNet: A Real-Time Biomedical Image Denoising Network with Gradient Information Enhancement Loss. Biosensors, 16(1), 26. https://doi.org/10.3390/bios16010026

Vancouver

Shi L, Feng X, Gong P, Song D, Zhang H, Liu L, et al. BDNet: A Real-Time Biomedical Image Denoising Network with Gradient Information Enhancement Loss. Biosensors. 2026;16(1):26. doi:10.3390/bios16010026

BibTeX
@article{Shi2026,
  author = {Shi, Lemin and Feng, Xin and Gong, Ping and Song, Dianxin and Zhang, Hao and Liu, Langxi and Zhang, Yuqiang and Li, Mingye},
  title = {BDNet: A Real-Time Biomedical Image Denoising Network with Gradient Information Enhancement Loss},
  journal = {Biosensors},
  year = {2026},
  volume = {16},
  number = {1},
  pages = {26},
  doi = {10.3390/bios16010026}
}
Kostenlos starten →