Precision Denoising in Medical Imaging via Generative Adversarial Network-Aided Low-Noise Discriminator Technique

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Precision Denoising in Medical Imaging via Generative Adversarial Network-Aided Low-Noise Discriminator Technique. / Alanazi, Turki M.; Mercorelli, Paolo.
In: Mathematics, Vol. 12, No. 23, 3705, 12.2024.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{0b71cfb2d360494a90179270ba34042e,
title = "Precision Denoising in Medical Imaging via Generative Adversarial Network-Aided Low-Noise Discriminator Technique",
abstract = "Medical imaging is significant for accurate diagnosis, and here, noise often degrades image quality, thus making it challenging to identify important information. Denoising is a component of traditional image pre-processing that helps prevent incorrect disease diagnosis. Mitigating the noise becomes difficult if there are differences in the low-level segment features. Therefore, a Generative Adversarial Network (GAN)-aided Low-Noise Discriminator (LND) is introduced to improve the denoising effectiveness in medical images with a balanced image resolution with noise mitigation. The LND function is a key that distinguishes between high- and low-noise areas based on segmented features, which are also achieved by tuning the peak signal-to-noise ratio (PSNR). Considering the training sequences, the LND-identified intervals lessen the sequences to improve the changes in pixel reconstruction. The generator function in this method is responsible for increasing the PSNR improvements over the different pixels cumulatively. The proposed method successfully improves the pixel reconstruction by 11.05% and PSNR by 9.75%, with 9.75% less reconstruction time and 13.11% less extraction error for the higher pixel distribution ratios than other contemporary methods.",
keywords = "generative adversarial network, image denoising, machine learning, medical diagnosis, neural networks, Engineering, Mathematics",
author = "Alanazi, {Turki M.} and Paolo Mercorelli",
note = "Publisher Copyright: {\textcopyright} 2024 by the authors.",
year = "2024",
month = dec,
doi = "10.3390/math12233705",
language = "English",
volume = "12",
journal = "Mathematics",
issn = "2227-7390",
publisher = "MDPI AG",
number = "23",

}

RIS

TY - JOUR

T1 - Precision Denoising in Medical Imaging via Generative Adversarial Network-Aided Low-Noise Discriminator Technique

AU - Alanazi, Turki M.

AU - Mercorelli, Paolo

N1 - Publisher Copyright: © 2024 by the authors.

PY - 2024/12

Y1 - 2024/12

N2 - Medical imaging is significant for accurate diagnosis, and here, noise often degrades image quality, thus making it challenging to identify important information. Denoising is a component of traditional image pre-processing that helps prevent incorrect disease diagnosis. Mitigating the noise becomes difficult if there are differences in the low-level segment features. Therefore, a Generative Adversarial Network (GAN)-aided Low-Noise Discriminator (LND) is introduced to improve the denoising effectiveness in medical images with a balanced image resolution with noise mitigation. The LND function is a key that distinguishes between high- and low-noise areas based on segmented features, which are also achieved by tuning the peak signal-to-noise ratio (PSNR). Considering the training sequences, the LND-identified intervals lessen the sequences to improve the changes in pixel reconstruction. The generator function in this method is responsible for increasing the PSNR improvements over the different pixels cumulatively. The proposed method successfully improves the pixel reconstruction by 11.05% and PSNR by 9.75%, with 9.75% less reconstruction time and 13.11% less extraction error for the higher pixel distribution ratios than other contemporary methods.

AB - Medical imaging is significant for accurate diagnosis, and here, noise often degrades image quality, thus making it challenging to identify important information. Denoising is a component of traditional image pre-processing that helps prevent incorrect disease diagnosis. Mitigating the noise becomes difficult if there are differences in the low-level segment features. Therefore, a Generative Adversarial Network (GAN)-aided Low-Noise Discriminator (LND) is introduced to improve the denoising effectiveness in medical images with a balanced image resolution with noise mitigation. The LND function is a key that distinguishes between high- and low-noise areas based on segmented features, which are also achieved by tuning the peak signal-to-noise ratio (PSNR). Considering the training sequences, the LND-identified intervals lessen the sequences to improve the changes in pixel reconstruction. The generator function in this method is responsible for increasing the PSNR improvements over the different pixels cumulatively. The proposed method successfully improves the pixel reconstruction by 11.05% and PSNR by 9.75%, with 9.75% less reconstruction time and 13.11% less extraction error for the higher pixel distribution ratios than other contemporary methods.

KW - generative adversarial network

KW - image denoising

KW - machine learning

KW - medical diagnosis

KW - neural networks

KW - Engineering

KW - Mathematics

UR - http://www.scopus.com/inward/record.url?scp=85211932290&partnerID=8YFLogxK

U2 - 10.3390/math12233705

DO - 10.3390/math12233705

M3 - Journal articles

AN - SCOPUS:85211932290

VL - 12

JO - Mathematics

JF - Mathematics

SN - 2227-7390

IS - 23

M1 - 3705

ER -

DOI

Recently viewed

Publications

  1. Digital technology in game-based approaches
  2. Measuring mathematics competence in international and national large scale assessments
  3. Prekäre Existenz
  4. Value creation in post-pandemic retailing
  5. Workplace mediation: Lessons from negotiation theory
  6. Methods and compositions relating to a vaccine against prostate cancer
  7. Introduction to the Psychology of Entrepreneurship
  8. On kites, comets, and stars. Sums of eigenvector coefficients in (molecular) graphs.
  9. Cultural Policies and Local Planning Strategies
  10. Normalitätskonstruktion und Selbstbilder erwachsener Reitender mit einer Körper- oder Sinnesbehinderung
  11. An Experimental Study on Corrupt Actions
  12. Explaining energy transition
  13. Microstructure and hardness evolution of laser metal deposited AA5087 wall-structures
  14. Lernen und Wiederlernen in chatbasiertem Computer-Supported Collaborative Learning
  15. Benefits of being ambivalent
  16. An image morphing method for 3D reconstruction and FE-analysis of pore networks in thermal spray coatings
  17. Formative assessment in mathematics
  18. Machine learning for optimization of energy and plastic consumption in the production of thermoplastic parts in SME
  19. Effect of laser peen forming process parameters on bending and surface quality of Ti-6Al-4V sheets
  20. Calibration of the Chemcatcher ® passive sampler for monitoring selected polar and semi-polar pesticides in surface water
  21. Investigation of the photochemistry and quantum yields of triazines using polychromatic irradiation and UV-spectroscopy as analytical tool
  22. A meta-analytic reliability generalization of the Physical Self-Description Questionnaire (PSDQ)
  23. Radicalisation of ‘lone actors’
  24. UE4SD - University Educators for Sustainable Development
  25. Amplifying actions for food system transformation: insights from the Stockholm region
  26. Spike-forging of AS-cast TX32 magnesium alloy
  27. Identität
  28. EEZ-adjacent distant-water fishing as a global security challenge
  29. Insights into PBDE Uptake, Body Burden, and Elimination Gained from Australian Age-Concentration Trends Observed Shortly after Peak Exposure
  30. Microstructural development in tension and compression creep of magnesium alloy AE42
  31. Live Sports, Piracy and Uncertainty: Understanding Illegal Streaming Aggregation Platforms