DIGS: Dynamic CBCT Reconstruction using Deformation-Informed 4D Gaussian Splatting and a Low-Rank Free-Form Deformation Model

2025-06-27

AI Summary

To address respiratory motion-induced artifacts in 3D cone-beam CT (CBCT) for radiotherapy, existing phase-binned reconstruction methods struggle with respiratory variability, while implicit dynamic modeling approaches (e.g., HexPlane) incur prohibitive computational cost, and explicit low-rank models lack spatial regularization, leading to inconsistent Gaussian motion. This paper proposes a deformation-guided 4D Gaussian lattice dynamic reconstruction framework that integrates a low-rank free-form deformation (FFD) model with spatial regularization. By explicitly coupling Gaussian positions, scales, and rotations through a unified deformation field, the method enhances motion consistency and suppresses irregular respiratory interference. Evaluated on six clinical CBCT datasets, the proposed method achieves superior image quality compared to state-of-the-art approaches and operates at six times the reconstruction speed of HexPlane.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

3D Cone-Beam CT (CBCT) is widely used in radiotherapy but suffers from motion artifacts due to breathing. A common clinical approach mitigates this by sorting projections into respiratory phases and reconstructing images per phase, but this does not account for breathing variability. Dynamic CBCT instead reconstructs images at each projection, capturing continuous motion without phase sorting. Recent advancements in 4D Gaussian Splatting (4DGS) offer powerful tools for modeling dynamic scenes, yet their application to dynamic CBCT remains underexplored. Existing 4DGS methods, such as HexPlane, use implicit motion representations, which are computationally expensive. While explicit low-rank motion models have been proposed, they lack spatial regularization, leading to inconsistencies in Gaussian motion. To address these limitations, we introduce a free-form deformation (FFD)-based spatial basis function and a deformation-informed framework that enforces consistency by coupling the temporal evolution of Gaussian's mean position, scale, and rotation under a unified deformation field. We evaluate our approach on six CBCT datasets, demonstrating superior image quality with a 6x speedup over HexPlane. These results highlight the potential of deformation-informed 4DGS for efficient, motion-compensated CBCT reconstruction. The code is available at https://github.com/Yuliang-Huang/DIGS.

Problem

• Reduces motion artifacts in CBCT caused by breathing variability
• Improves dynamic CBCT reconstruction efficiency and image quality
• Integrates deformation-informed 4D Gaussian Splatting for motion compensation

Innovation

• Uses 4D Gaussian Splatting for dynamic CBCT
• Employs low-rank free-form deformation model
• Enforces Gaussian motion consistency via deformation