CVOct 18, 2024

DRACO: Differentiable Reconstruction for Arbitrary CBCT Orbits

arXiv:2410.14900v16 citationsh-index: 10Phys Med Biology
Originality Highly original
AI Analysis

This is a significant advancement for interventional medical imaging, particularly robotic C-arm CT systems, enabling faster and more accurate reconstructions with customized orbits.

The paper tackles the problem of computationally expensive and memory-intensive cone beam computed tomography (CBCT) reconstruction for arbitrary orbits by introducing a differentiable shift-variant filtered backprojection neural network, achieving a 38.6% reduction in MSE, a 7.7% increase in PSNR, a 5.0% improvement in SSIM, and a more than 97% reduction in computation time compared to conventional methods.

This paper introduces a novel method for reconstructing cone beam computed tomography (CBCT) images for arbitrary orbits using a differentiable shift-variant filtered backprojection (FBP) neural network. Traditional CBCT reconstruction methods for arbitrary orbits, like iterative reconstruction algorithms, are computationally expensive and memory-intensive. The proposed method addresses these challenges by employing a shift-variant FBP algorithm optimized for arbitrary trajectories through a deep learning approach that adapts to a specific orbit geometry. This approach overcomes the limitations of existing techniques by integrating known operators into the learning model, minimizing the number of parameters, and improving the interpretability of the model. The proposed method is a significant advancement in interventional medical imaging, particularly for robotic C-arm CT systems, enabling faster and more accurate CBCT reconstructions with customized orbits. Especially this method can also be used for the analytical reconstruction of non-continuous orbits like circular plus arc. The experimental results demonstrate that the proposed method significantly accelerates the reconstruction process compared to conventional iterative algorithms. It achieves comparable or superior image quality, as evidenced by metrics such as the mean squared error (MSE), the peak signal-to-noise ratio (PSNR), and the structural similarity index measure (SSIM). The validation experiments show that the method can handle data from different trajectories, demonstrating its flexibility and robustness across different scan geometries. Our method demonstrates a significant improvement, particularly for the sinusoidal trajectory, achieving a 38.6% reduction in MSE, a 7.7% increase in PSNR, and a 5.0% improvement in SSIM. Furthermore, the computation time for reconstruction was reduced by more than 97%.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes