EUVIMEDEUVIMED entdecken
Crossref

Hybrid Physics-Driven Deep Learning for Enhanced Ultrasound Image Quality and Speckle Noise Suppression

Taher Slimi iD, Nahla Majdoub Bhiri, Hajer Chtioui, Anouar Ben Khalifa

Ultrasonic Imaging · 23.06.2026

DOI: 10.1177/01617346261452679 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ultrasonic Imaging, online erschienen am 23.06.2026. Verfasst von Taher Slimi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institut National des Technologies et des Sciences du Kef, Université de Jendouba, Tunisie. Die Arbeit nennt 28 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ultrasound imaging is widely used in clinical practice due to its non-invasive, real-time, and cost-effective nature. However, speckle noise often degrades image quality, obscuring fine anatomical structures and reducing diagnostic confidence. Existing denoising methods struggle to remove noise effectively while preserving critical details, limiting their clinical utility. Although recent deep learning architectures excel at capturing both local details and global structure, they remain inherently limited in handling speckle noise, as its physical characteristics are not explicitly incorporated. To address this limitation, a Physics-Regularized Self-Supervised Denoising U-Net (PR-SSD-Net) is introduced to reinforce the U-Net’s capability for high-quality image restoration. The physics-based constraint guides the network to produce residual noise patterns that align with expected statistical behavior, enhancing image clarity and preserving critical structures. Comprehensive evaluations were conducted on six diverse ultrasound datasets. Significant improvements in Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) were observed, accompanied by reduced variability, as reflected in their standard deviations (SD). An ablation study confirmed the pivotal role of physics-guided regularization, and expert assessments demonstrated high inter-rater agreement (Fleiss), supporting the clinical relevance of the approach. These results highlight the proposed PR-SSD-Net approach as a robust, physically grounded solution for speckle noise reduction, enhancing both the reliability and clinical utility of ultrasound imaging.

Schlagwörter

Stichwörter der Autor:innen

physics-guided regularizationself-supervised learningspeckle noiseultrasound denoising

Autor:innen und Institutionen

  • Institut National des Technologies et des Sciences du Kef, Université de Jendouba, Tunisie.
  • Ecole Nationale d'Ingénieurs de Sousse, LATIS - Laboratory of Advanced Technology and Intelligent Systems, Université de Sousse, Tunisie.

ORCID-Profile: Taher Slimi

Zitieren

APA

Slimi, T., Majdoub Bhiri, N., Chtioui, H., & Ben Khalifa, A. (2026). Hybrid Physics-Driven Deep Learning for Enhanced Ultrasound Image Quality and Speckle Noise Suppression. Ultrasonic Imaging. https://doi.org/10.1177/01617346261452679

Vancouver

Slimi T, Majdoub Bhiri N, Chtioui H, Ben Khalifa A. Hybrid Physics-Driven Deep Learning for Enhanced Ultrasound Image Quality and Speckle Noise Suppression. Ultrasonic Imaging. 2026. doi:10.1177/01617346261452679

BibTeX
@article{Slimi2026,
  author = {Slimi, Taher and Majdoub Bhiri, Nahla and Chtioui, Hajer and Ben Khalifa, Anouar},
  title = {Hybrid Physics-Driven Deep Learning for Enhanced Ultrasound Image Quality and Speckle Noise Suppression},
  journal = {Ultrasonic Imaging},
  year = {2026},
  doi = {10.1177/01617346261452679}
}
Kostenlos starten →