PulseAugur
EN
LIVE 10:48:52

Differentiable SV-FBP for Cone-Beam CT Shows Robustness to Trajectory Irregularities

Researchers have analyzed the Differentiable Shift-Variant FBP (SV-FBP) framework for cone-beam CT reconstruction, finding it robust to irregular and discontinuous source trajectories. The framework's performance is more dependent on the spatial distribution of sampling points than trajectory continuity. While competitive in sparse-view conditions with significantly reduced computation time, it degrades under severe undersampling due to the lack of iterative data consistency. The SV-FBP model also proved applicable to non-planar multi-isocenter geometries without architectural changes. AI

IMPACT Provides insights into the behavior and limitations of a data-driven CT reconstruction model, highlighting its efficiency for non-standard acquisition scenarios.

RANK_REASON Academic paper detailing a new analysis of an existing framework. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Differentiable SV-FBP for Cone-Beam CT Shows Robustness to Trajectory Irregularities

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Chengze Ye, Linda-Sophie Schneider, Yipeng Sun, Mareike Thies, Siyuan Mei, Paula Andrea P\'erez-Toro, Siming Bayer, Andreas Maier ·

    Robustness and Stability Analysis of Differentiable Shift-Variant FBP for Cone-Beam CT under Challenging Acquisition Settings

    arXiv:2607.09828v1 Announce Type: cross Abstract: The differentiable shift-variant filtered backprojection (SV-FBP) framework enables data-driven estimation of redundancy weights for cone-beam CT reconstruction under general source trajectories, removing the need for analytically…