EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An end-to-end implicit neural representation architecture for medical volume data

Armin Sheibanifard, Hongchuan Yu iD, Zongcai Ruan, Jian J Zhang

PLOS ONE · 2025

DOI: 10.1371/journal.pone.0314944 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2025. Verfasst von Armin Sheibanifard und 3 weiteren Autor:innen. Beteiligte Einrichtung: NCCA, Bournemouth University, Poole, United Kingdom. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Data Compression, Neural Networks, Computer. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EU Horizon Project-ACMod.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Medical volume data are rapidly increasing, growing from gigabytes to petabytes, which presents significant challenges in organisation, storage, transmission, manipulation, and rendering. To address the challenges, we propose an end-to-end architecture for data compression, leveraging advanced deep learning technologies. This architecture consists of three key modules: downsampling, implicit neural representation (INR), and super-resolution (SR). We employ a trade-off point method to optimise each module’s performance and achieve the best balance between high compression rates and reconstruction quality. Experimental results on multi-parametric MRI data demonstrate that our method achieves a high compression rate of up to 97.5% while maintaining superior reconstruction accuracy, with a Peak Signal-to-Noise Ratio (PSNR) of 40.05 dB and Structural Similarity Index (SSIM) of 0.96. This approach significantly reduces GPU memory requirements and processing time, making it a practical solution for handling large medical datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingData CompressionNeural Networks, ComputerHumansDeep LearningSignal-To-Noise RatioImage Processing, Computer-AssistedAlgorithms

Autor:innen und Institutionen

  • NCCA, Bournemouth University, Poole, United Kingdom.
  • Key Laboratory of Child Development and Learning Science, South-East University, Nanjing, China.

ORCID-Profile: Hongchuan Yu

Förderung

  • EU Horizon Project-ACMod

Zitieren

APA

Sheibanifard, A., Yu, H., Ruan, Z., & Zhang, J. J. (2025). An end-to-end implicit neural representation architecture for medical volume data. PLOS ONE. https://doi.org/10.1371/journal.pone.0314944

Vancouver

Sheibanifard A, Yu H, Ruan Z, Zhang JJ. An end-to-end implicit neural representation architecture for medical volume data. PLOS ONE. 2025. doi:10.1371/journal.pone.0314944

BibTeX
@article{Sheibanifard2025,
  author = {Sheibanifard, Armin and Yu, Hongchuan and Ruan, Zongcai and Zhang, Jian J},
  title = {An end-to-end implicit neural representation architecture for medical volume data},
  journal = {PLOS ONE},
  year = {2025},
  doi = {10.1371/journal.pone.0314944}
}
Kostenlos starten →