LSTT: Latent Spatio-Temporal Transformer for Non-rigid Motion Compensation in CBCT

Sun Y, Schneider LS, Schwarz A, Gu M, Mei S, Ye C, Bayer S, Maier A (2026)

Publication Type: Conference contribution

Publication year: 2026

Journal

Publisher: Springer Science and Business Media Deutschland GmbH

Book Volume: 16150 LNCS

Pages Range: 76-86

Conference Proceedings Title: Lecture Notes in Computer Science

Event location: Daejeon

ISBN: 9783032061027

DOI: 10.1007/978-3-032-06103-4_8

Abstract

Non-rigid physiological motion during Cone-Beam Computed Tomography (CBCT) acquisitions remains a significant clinical challenge. To address this, we introduce the Latent Spatio-Temporal Transformer (LSTT), an end-to-end framework designed to directly correct motion artifacts from projection data. Our entirely image-based approach requires only the original CBCT projections and imaging geometry, eliminating the necessity for respiratory or ECG gating and external monitoring devices. The LSTT architecture integrates a VQ-VAE to tokenize projections into a robust latent space, a temporal Transformer to capture global motion dynamics, and a decoder to produce explicit 2D displacement fields. Central to our framework is a differentiable Feldkamp-Davis-Kress (FDK) reconstruction layer, which enables true end-to-end training by optimizing the objective function on the final reconstructed volume. This approach compels the network to learn a physically meaningful policy for non-rigid motion, explicitly tailored for high-fidelity volumetric reconstruction. We validate our framework using a realistic respiratory motion phantom, demonstrating significant improvements over the standard clinical baseline in both artifact suppression and structural preservation.

Authors with CRIS profile

How to cite

APA:

Sun, Y., Schneider, L.-S., Schwarz, A., Gu, M., Mei, S., Ye, C.,... Maier, A. (2026). LSTT: Latent Spatio-Temporal Transformer for Non-rigid Motion Compensation in CBCT. In Lina Felsner, Thomas Küstner, Andreas Maier, Chen Qin, Seyed-Ahmad Ahmadi, Anees Kazi, Xiaoling Hu (Eds.), Lecture Notes in Computer Science (pp. 76-86). Daejeon, KR: Springer Science and Business Media Deutschland GmbH.

MLA:

Sun, Yipeng, et al. "LSTT: Latent Spatio-Temporal Transformer for Non-rigid Motion Compensation in CBCT." Proceedings of the 1st International Workshop on Reconstruction and Imaging Motion Estimation, RIME 2025, and 7th International Workshop on Graphs in Biomedical Image Analysis, GRAIL 2025, held in conjunction with the 28th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2025, Daejeon Ed. Lina Felsner, Thomas Küstner, Andreas Maier, Chen Qin, Seyed-Ahmad Ahmadi, Anees Kazi, Xiaoling Hu, Springer Science and Business Media Deutschland GmbH, 2026. 76-86.

BibTeX: Download