Sinogram interpolation for sparse-view micro-CT with deep learning neural network

TL;DR

This paper presents a deep learning-based sinogram interpolation method using U-Net and residual learning for sparse-view micro-CT, significantly improving image quality at high sparsity levels compared to traditional methods.

Contribution

The study introduces a novel deep learning approach for sinogram interpolation in micro-CT, tested on real experimental data with up to 90% sparsity, outperforming standard linear interpolation.

Findings

Improved RMSE and SSIM in reconstructed images

Effective at 90% sparsity levels in micro-CT data

Outperforms traditional linear interpolation methods

Abstract

In sparse-view Computed Tomography (CT), only a small number of projection images are taken around the object, and sinogram interpolation method has a significant impact on final image quality. When the amount of sparsity (the amount of missing views in sinogram data) is not high, conventional interpolation methods have yielded good results. When the amount of sparsity is high, more advanced sinogram interpolation methods are needed. Recently, several deep learning (DL) based sinogram interpolation methods have been proposed. However, those DL-based methods have mostly tested so far on computer simulated sinogram data rather experimentally acquired sinogram data. In this study, we developed a sinogram interpolation method for sparse-view micro-CT based on the combination of U-Net and residual learning. We applied the method to sinogram data obtained from sparse-view micro-CT experiments, where the sparsity reached 90%. The interpolated sinogram by the DL neural network was fed to FBP algorithm for reconstruction. The result shows that both RMSE and SSIM of CT image are greatly improved. The experimental results demonstrate that this sinogram interpolation method produce significantly better results over standard linear interpolation methods when the sinogram data are extremely sparse.