NAB: Neural Adaptive Binning for Sparse-View CT reconstruction

TL;DR

NAB introduces a neural adaptive binning method that incorporates rectangular shape priors into sparse-view CT reconstruction, improving accuracy and generalization by end-to-end optimizing a novel coordinate mapping mechanism.

Contribution

The paper proposes a new neural adaptive binning approach that effectively integrates shape priors into neural network-based CT reconstruction, enabling end-to-end optimization and improved performance.

Findings

NAB outperforms existing methods on industrial datasets.

The method maintains robustness on medical datasets with extended binning functions.

End-to-end training enhances reconstruction accuracy.

Abstract

Computed Tomography (CT) plays a vital role in inspecting the internal structures of industrial objects. Furthermore, achieving high-quality CT reconstruction from sparse views is essential for reducing production costs. While classic implicit neural networks have shown promising results for sparse reconstruction, they are unable to leverage shape priors of objects. Motivated by the observation that numerous industrial objects exhibit rectangular structures, we propose a novel Neural Adaptive Binning (NAB) method that effectively integrates rectangular priors into the reconstruction process. Specifically, our approach first maps coordinate space into a binned vector space. This mapping relies on an innovative binning mechanism based on differences between shifted hyperbolic tangent functions, with our extension enabling rotations around the input-plane normal vector. The resulting representations are then processed by a neural network to predict CT attenuation coefficients. This design enables end-to-end optimization of the encoding parameters -- including position, size, steepness, and rotation -- via gradient flow from the projection data, thus enhancing reconstruction accuracy. By adjusting the smoothness of the binning function, NAB can generalize to objects with more complex geometries. This research provides a new perspective on integrating shape priors into neural network-based reconstruction. Extensive experiments demonstrate that NAB achieves superior performance on two industrial datasets. It also maintains robust on medical datasets when the binning function is extended to more general expression. The code is available at https://github.com/Wangduo-Xie/NAB_CT_reconstruction.