Abstract: BigReg: An Efficient Registration Pipeline for High-resolution X-ray and Light-sheet Fluorescence Microscopy

Mei S, Fan F, Thies M, Gu M, Wagner F, Aust O, Erceg I, Mirzaei Z, Neag G, Sun Y, Huang Y, Maier A (2026)

Publication Type: Conference contribution

Publication year: 2026

Journal

Informatik aktuell Gesellschaft für Informatik (GI)

Publisher: Springer Science and Business Media Deutschland GmbH

Pages Range: 400-400

Conference Proceedings Title: Informatik aktuell

Event location: Lübeck DE

ISBN: 9783658510992

DOI: 10.1007/978-3-658-51100-5_77

Abstract

X-ray microscopy (XRM) and light-sheet fluorescence microscopy (LSFM) have emerged as pivotal tools in preclinical research, particularly for studying bone remodeling diseases such as osteoporosis. To enable micrometer-level structural correspondence and facilitate functional analysis, we introduce BigReg, an automatic, two-stage registration pipeline optimized for high-resolution XRM and LSFM volumes [1]. The first stage involves extracting surface features and applying two successive global-to-local point cloud-based methods for coarse alignment. The subsequent stage refines this alignment in the 3D Fourier domain using a modified cross-correlation technique, achieving precise volumetric registration. Evaluations using expert-annotated landmarks and augmented test data demonstrate that BigReg approaches the accuracy of landmark-based registration with a landmark distance (LMD) of 8.36 μm ± 0.12 μm and a landmark fitness (LM fitness) of 85.71% ± 1.02%. Moreover, BigReg can provide an optimal initialization for mutual information-based methods which otherwise fail independently, further reducing LMD to 7.24 μm ± 0.11 μm and increasing LM fitness to 93.90% ± 0.77%. To the best of our knowledge, BigReg is the first automated method to successfully register XRM and LSFM volumes without requiring manual intervention or prior alignment cues, thus opening up newavenues for multimodal analysis of bone microarchitecture and disease pathology.

Authors with CRIS profile

Siyuan Mei Lehrstuhl für Informatik 5 (Mustererkennung) Fuxin Fan Lehrstuhl für Informatik 5 (Mustererkennung) Mareike Thies Lehrstuhl für Informatik 5 (Mustererkennung) Mingxuan Gu Lehrstuhl für Informatik 5 (Mustererkennung) Fabian Wagner Lehrstuhl für Informatik 5 (Mustererkennung) Oliver Aust Department of Medicine 3 – Rheumatology and Immunology Georgiana Neag Department of Medicine 3 – Rheumatology and Immunology Yipeng Sun Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung) Anatol Maier Lehrstuhl für Informatik 1 (IT-Sicherheitsinfrastrukturen)

Involved external institutions

Innovations-Institut für Nanotechnologie und korrelative Mikroskopie e.V. (INAM) / Institute for Nanotechnology and Correlative Microscopy DE Germany (DE) Peking University Health Science Center CN China (CN) Fraunhofer-Institut für Keramische Technologien und Systeme (IKTS) DE Germany (DE)

How to cite

APA:

Mei, S., Fan, F., Thies, M., Gu, M., Wagner, F., Aust, O.,... Maier, A. (2026). Abstract: BigReg: An Efficient Registration Pipeline for High-resolution X-ray and Light-sheet Fluorescence Microscopy. In Heinz Handels, Katharina Breininger, Thomas Deserno, Andreas Maier, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff (Eds.), Informatik aktuell (pp. 400-400). Lübeck, DE: Springer Science and Business Media Deutschland GmbH.

MLA:

Mei, Siyuan, et al. "Abstract: BigReg: An Efficient Registration Pipeline for High-resolution X-ray and Light-sheet Fluorescence Microscopy." Proceedings of the Bildverarbeitung für die Medizin Workshop, BVM 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. 400-400.

BibTeX: Download