Learning from our neighbours: a novel approach on sinogram completion using bin-sharing and deep learning to reconstruct high quality 4DCBCT

TL;DR

This paper introduces a deep learning-based method combining bin-sharing and CNNs to improve 4DCBCT image quality from sparse data, reducing artifacts and noise while maintaining tumor motion accuracy.

Contribution

The novel Sino-Net model integrates bin-sharing with deep learning for high-quality 4DCBCT reconstruction from sparse datasets, outperforming traditional methods.

Findings

Significant reduction in streak artifacts and noise in reconstructed images.

Tumor centroid deviations around 0.5 mm, indicating high motion accuracy.

Promising preliminary results encouraging further research.

Abstract

Inspired by the success of deep learning applications on restoration of low-dose and sparse CT images, we propose a novel method to reconstruct high-quality 4D cone-beam CT (4DCBCT) images from sparse datasets. Our approach combines the idea of 'bin-sharing' with a deep convolutional neural network (CNN) model. More specifically, for each respiratory bin, an initial estimate of the patient sinogram is obtained by taking projections from adjacent bins and performing linear interpolation. Subsequently, the estimated sinogram is propagated through a CNN that predicts a full, high-quality sinogram. Lastly, the predicted sinogram is reconstructed with traditional CBCT algorithms such as the Feldkamp, Davis and Kress (FDK) method. The CNN model, which we referred to as the Sino-Net, was trained under different loss functions. We assessed the performance of the proposed method in terms of image quality metrics (mean square error, mean absolute error, peak signal-to-noise ratio and structural similarity) and tumor motion accuracy (tumor centroid deviation with respect to the ground truth). Overall, the presented prototype model was able to substantially improve the quality of 4DCBCT images, removing most of the streak artifacts and decreasing the noise with respect to the standard FDK reconstructions. The tumor centroid deviations with respect to the ground truth predicted by our method were approximately 0.5 mm, on average (maximum deviation was approximately 2 mm). These preliminary results are promising and encourage us to further investigate the performance of our model under more challenging imaging conditions and compare it against the state-of-the-art CBCT reconstruction algorithms.