EUVIMEDEUVIMED entdecken
Video/Audio

Energy-Efficient Machine Learning Based Denoising Techniques for Sustainable Medical Imaging

Vidula V Meshram, Vishal A Meshram, Pallavi Rege, Kailas Patil, Shrikant Jadhav, Gandharva Thite

Journal of Visualized Experiments · 2025

DOI: 10.3791/68968 ↗

Kurz gefasst

Video/Audio in der Zeitschrift Journal of Visualized Experiments, 2025. Verfasst von Vidula V Meshram und 5 weiteren Autor:innen. Beteiligte Einrichtung: Vishwakarma University; Vishwakarma Institute of Technology. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Machine Learning, Image Processing, Computer-Assisted, Image Enhancement. Die Arbeit nennt 36 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional deep learning models have demonstrated denoising potential, but face challenges such as extensive computational load, energy usage, and training time. This study presents an energy-efficient denoising methodology that integrates image enhancement and K-means clustering as preprocessing techniques to improve input quality before applying neural networks. This study proposes an energy-efficient denoising pipeline integrating image enhancement using sharpening kernels and image segmentation through K-means clustering before the application of a convolutional autoencoder. The preprocessing steps enabled the model to identify anatomical boundaries and separate noise-affected regions, thereby improving the input quality and enhancing training convergence. Preprocessing sharpens key image features and distinguishes noise-affected regions, enabling adaptive thresholding and more effective denoising with reduced computational cost. The proposed model was evaluated using publicly available CT and MRI datasets. Performance was assessed through Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and classification accuracy. The results showed that PSNR improved from 21.52 dB to 28.14 dB; SSIM increased from 0.7619 to 0.8690, and validation accuracy also improved. The integrated preprocessing reduced training time by ~20% and lowered GPU utilization, thus supporting reproducibility and deployment in computationally constrained environments. The methodology supports sustainable medical imaging practices by minimizing radiation exposure, reducing repeat scans, and extending the lifespan of older imaging equipment. This pipeline contributes to sustainable medical imaging by minimizing radiation exposure, reducing repeat scans, and extending the lifespan of legacy imaging equipment. It is also suitable for remote diagnostics, enhancing telemedicine workflows in low-resource settings. Additionally, the approach supports remote diagnostics, making it suitable for telemedicine applications in low-resource settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingMachine LearningImage Processing, Computer-AssistedImage EnhancementHumansSignal-To-Noise RatioTomography, X-Ray ComputedDeep LearningNeural Networks, Computer

Autor:innen und Institutionen

  • Vishwakarma University; Vishwakarma Institute of Technology.
  • Vishwakarma Institute of Technology.
  • Vishwakarma University; kailas.patil@vupune.ac.in.
  • San Jose State University; shrikant.jadhav@sjsu.edu.

Zitieren

APA

Meshram, V. V., Meshram, V. A., Rege, P., Patil, K., Jadhav, S., & Thite, G. (2025). Energy-Efficient Machine Learning Based Denoising Techniques for Sustainable Medical Imaging. Journal of Visualized Experiments. https://doi.org/10.3791/68968

Vancouver

Meshram VV, Meshram VA, Rege P, Patil K, Jadhav S, Thite G. Energy-Efficient Machine Learning Based Denoising Techniques for Sustainable Medical Imaging. Journal of Visualized Experiments. 2025. doi:10.3791/68968

BibTeX
@article{Meshram2025,
  author = {Meshram, Vidula V and Meshram, Vishal A and Rege, Pallavi and Patil, Kailas and Jadhav, Shrikant and Thite, Gandharva},
  title = {Energy-Efficient Machine Learning Based Denoising Techniques for Sustainable Medical Imaging},
  journal = {Journal of Visualized Experiments},
  year = {2025},
  doi = {10.3791/68968}
}
Kostenlos starten →