Variational Quantum Denoising Technique for Medical Images
Tudor Barbu · 2020 International Conference on e-Health and Bioengineering (EHB) · 2020
A novel variational restoration framework for the medical images corrupted by quantum, or Poisson, noise is proposed in this research paper. The considered approach is using a variational scheme that leads to a nonlinear fourth-order PDE-based model. That partial differential equation model is then solved numerically by developing a consistent finite difference-based numerical approximation scheme converging to its variational solution. The obtained numerical algorithm removes successfully the quantum noise from the medical images, preserves their details, and outperforms other shot noise filtering solutions.