Frequency-regularized Neural Representation Method for Sparse-view Tomographic Reconstruction

TL;DR

This paper introduces Freq-NAF, a frequency-regularized neural method for sparse-view tomographic reconstruction that balances high- and low-frequency information, reducing overfitting and achieving state-of-the-art accuracy.

Contribution

The paper proposes a novel frequency regularization technique in neural networks for sparse-view tomography, addressing high-frequency bias and overfitting issues.

Findings

Achieves state-of-the-art accuracy on CBCT and SPECT datasets.

Effectively balances frequency information to improve reconstruction quality.

Reduces overfitting at edges and boundaries in reconstructed images.

Abstract

Sparse-view tomographic reconstruction is a pivotal direction for reducing radiation dose and augmenting clinical applicability. While many research works have proposed the reconstruction of tomographic images from sparse 2D projections, existing models tend to excessively focus on high-frequency information while overlooking low-frequency components within the sparse input images. This bias towards high-frequency information often leads to overfitting, particularly intense at edges and boundaries in the reconstructed slices. In this paper, we introduce the Frequency Regularized Neural Attenuation/Activity Field (Freq-NAF) for self-supervised sparse-view tomographic reconstruction. Freq-NAF mitigates overfitting by incorporating frequency regularization, directly controlling the visible frequency bands in the neural network input. This approach effectively balances high-frequency and low-frequency information. We conducted numerical experiments on CBCT and SPECT datasets, and our method demonstrates state-of-the-art accuracy.