Differentiable Approximate Truncation Robust CBCT Reconstruction via Known Operator Learning

Ye C, Schneider LS, Sun Y, Mei S, Bayer S, Perez Toro PA, Maier A (2026)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2026

Publisher: Springer Science and Business Media Deutschland GmbH

Series: BVM Workshop

Pages Range: 328–333

Conference Proceedings Title: German Conference on Medical Image Computing

Event location: Lübeck

URI: https://link.springer.com/chapter/10.1007/978-3-658-51100-5_64

Open Access Link: https://link.springer.com/chapter/10.1007/978-3-658-51100-5_64

Abstract

The proposed algorithm is a differentiable approximate truncation robust computed tomography (ATRACT) reconstruction algorithm for end-to-end trainable cone-beam CT reconstruction, offering enhanced robustness to truncated geometries and a significant reduction of truncation artifacts. The proposed method utilizes known operator learning to map the analytical reconstruction into a neural network. This approach preserves physical consistency while enabling data-driven optimization of redundancy weights under the 180◦ limited-angle condition. The experimental results demonstrate that the proposed frame work surpasses the Parker-weighted analytical reconstruction, achieving a 1.5% higher SSIM and a 1.1% lower MSE. This outcome validates the accuracy and efficacy of the analytical-to-neural mapping procedure. The differentiable formulation integrates the interpretability of analytical reconstruction with the adaptability of learning-based methods, thereby providing a robust and extensible foundation for imaging applications under truncated geometries.

Authors with CRIS profile

How to cite

APA:

Ye, C., Schneider, L.-S., Sun, Y., Mei, S., Bayer, S., Perez Toro, P.A., & Maier, A. (2026). Differentiable Approximate Truncation Robust CBCT Reconstruction via Known Operator Learning. In Heinz Handels, Katharina Breininger, Thomas Deserno, Andreas Maier, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff (Eds.), German Conference on Medical Image Computing (pp. 328–333). Lübeck, DE: Springer Science and Business Media Deutschland GmbH.

MLA:

Ye, Chengze, et al. "Differentiable Approximate Truncation Robust CBCT Reconstruction via Known Operator Learning." Proceedings of the Bildverarbeitung für die Medizin 2026, Lübeck Ed. Heinz Handels, Katharina Breininger, Thomas Deserno, Andreas Maier, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff, Springer Science and Business Media Deutschland GmbH, 2026. 328–333.

BibTeX: Download