Adaptive Gaussian representation for differentiable cryo-electron tomography reconstruction

TY - JOUR

T1 - Adaptive Gaussian representation for differentiable cryo-electron tomography reconstruction

AU - Zhang, Chi

AU - Yang, Zhidong

AU - Han, Renmin

AU - Zhang, Fa

AU - Feng, Jieqing

N1 - Publisher Copyright: © 2025 Elsevier Inc.

PY - 2026/3

Y1 - 2026/3

N2 - Cryo-electron tomography (cryo-ET) enables 3D visualization of biological structures in their native state, but high-fidelity tomogram reconstruction remains challenging due to low signal-to-noise ratios and limited angular sampling. In this work, we present CryoETGS, a differentiable learning framework that reconstructs tomograms through adaptive 3D Gaussian representations of biological structures for cryo-ET. This representation enables efficient and interpretable reconstruction through a hardware-accelerated differentiable rendering pipeline aligned with the cryo-ET imaging geometry. CryoETGS incorporates hierarchical initialization, adaptive densification, and a tilt-weighted optimization strategy to enhance convergence and reconstruction fidelity. The framework further supports real-time projection synthesis and bidirectional conversion between voxel-based and Gaussian representations. Extensive experiments on both simulated and experimental datasets demonstrate that CryoETGS achieves state-of-the-art reconstruction performance, effectively mitigates missing wedge artifacts, and exhibits high computational efficiency. Source code is publicly available at https://github.com/JachyLikeCoding/ETGS.

AB - Cryo-electron tomography (cryo-ET) enables 3D visualization of biological structures in their native state, but high-fidelity tomogram reconstruction remains challenging due to low signal-to-noise ratios and limited angular sampling. In this work, we present CryoETGS, a differentiable learning framework that reconstructs tomograms through adaptive 3D Gaussian representations of biological structures for cryo-ET. This representation enables efficient and interpretable reconstruction through a hardware-accelerated differentiable rendering pipeline aligned with the cryo-ET imaging geometry. CryoETGS incorporates hierarchical initialization, adaptive densification, and a tilt-weighted optimization strategy to enhance convergence and reconstruction fidelity. The framework further supports real-time projection synthesis and bidirectional conversion between voxel-based and Gaussian representations. Extensive experiments on both simulated and experimental datasets demonstrate that CryoETGS achieves state-of-the-art reconstruction performance, effectively mitigates missing wedge artifacts, and exhibits high computational efficiency. Source code is publicly available at https://github.com/JachyLikeCoding/ETGS.

KW - 3D reconstruction

KW - Cryo-electron tomography

KW - Differentiable reconstruction

KW - Gaussian representation

KW - Missing wedge correction

UR - https://www.scopus.com/pages/publications/105025192012

U2 - 10.1016/j.jsb.2025.108281

DO - 10.1016/j.jsb.2025.108281

M3 - Article

AN - SCOPUS:105025192012

SN - 1047-8477

VL - 218

JO - Journal of Structural Biology

JF - Journal of Structural Biology

IS - 1

M1 - 108281

ER -