Deep Unfolding RPCA for High-Resolution Flow Estimation - Computational Imaging and Vision Access content directly
Conference Papers Year : 2022

Deep Unfolding RPCA for High-Resolution Flow Estimation

Vassili Pustovalov
  • Function : Author
  • PersonId : 1111426
Duong-Hung Pham
Denis Kouamé


Numerous techniques have been proposed to produce high precision blood flow or contrast-enhanced ultrasound estimates from fast ultrasound sequences. Among them, robust principal component analysis (RPCA)-based methods are known as superior to most state-of-the-art techniques. In particular, these techniques may include a deconvolution step which allows for further improvement of the resolution of the estimated blood flow images. However, they rely on many hyperparameters that have to be manually adjusted to obtain the optimal solution. To overcome this limitation, we propose a new deep unfolding neural network based on the DRPCA iterative algorithm, which enables the reconstruction of high-resolution and high-sensitivity blood flow components. Compared to other state-of-the-art methods, the proposed algorithm showed interesting performances, in terms of PSNR and SSIM on simulation data.
Fichier principal
Vignette du fichier
IUS2022_1965_Deep_Unfolding_RPCA_for_High_Resolution_Flow_Estimation.pdf (480.27 Ko) Télécharger le fichier
IUS_2022_DRPCA.pdf (17.54 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Comment : Paper
Origin : Files produced by the author(s)
Comment : Presentation

Dates and versions

hal-03787159 , version 1 (24-10-2022)


  • HAL Id : hal-03787159 , version 1


Vassili Pustovalov, Duong-Hung Pham, Denis Kouamé. Deep Unfolding RPCA for High-Resolution Flow Estimation. IEEE International Ultrasonics Symposium (IUS 2022), Oct 2022, Venise, Italy. à paraître. ⟨hal-03787159⟩
134 View
125 Download


Gmail Facebook X LinkedIn More