Two-Layer Residual Sparsifying Transform Learning for Image Reconstruction

Zheng, Xuehang; Ravishankar, Saiprasad; Long, Yong; Klasky, Marc L.; Wohlberg, Brendt

doi:10.1109/isbi45749.2020.9098653

Cited by 1 publication

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig. 5 shows the comparison of reconstructions that correspond to the results shown in [26]. PWLS-MRST2 significantly outperforms the conventional FBP method and the non-adaptive PWLS-EP method.…”

Section: Additional Experimental Resultsmentioning

confidence: 84%

Two-layer Residual Sparsifying Transform Learning for Image Reconstruction

Zheng

Ravishankar

Long

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Signal models based on sparsity, low-rank and other properties have been exploited for image reconstruction from limited and corrupted data in medical imaging and other computational imaging applications. In particular, sparsifying transform models have shown promise in various applications, and offer numerous advantages such as efficiencies in sparse coding and learning. This work investigates pre-learning a multilayer extension of the transform model for image reconstruction, wherein the transform domain or filtering residuals of the image are further sparsified over the layers. The residuals from multiple layers are jointly minimized during learning, and in the regularizer for reconstruction. The proposed block coordinate descent optimization algorithms involve highly efficient updates. Preliminary numerical experiments demonstrate the usefulness of a two-layer model over the previous related schemes for CT image reconstruction from low-dose measurements.

show abstract

Section: Additional Experimental Resultsmentioning

confidence: 84%