One Network to Solve All ROIs: Deep Learning CT for Any ROI using Differentiated Backprojection
This provides a general CT reconstruction engine for practical applications, reducing radiation dose and enabling use of small detectors, though it appears incremental as it builds on prior deep learning approaches for artifact correction.
The paper tackled the problem of region-of-interest (ROI) computed tomography reconstruction, which suffers from cupping artifacts and high computational costs, by proposing a deep neural network that learns to invert the finite Hilbert transform from truncated differentiated backprojection data, resulting in significantly outperforming existing iterative methods for any ROI size with reduced run-time complexity.
Computed tomography for region-of-interest (ROI) reconstruction has advantages of reducing X-ray radiation dose and using a small detector. However, standard analytic reconstruction methods suffer from severe cupping artifacts, and existing model-based iterative reconstruction methods require extensive computations. Recently, we proposed a deep neural network to learn the cupping artifact, but the network is not well generalized for different ROIs due to the singularities in the corrupted images. Therefore, there is an increasing demand for a neural network that works well for any ROI sizes. In this paper, two types of neural networks are designed. The first type learns ROI size-specific cupping artifacts from the analytic reconstruction images, whereas the second type network is to learn to invert the finite Hilbert transform from the truncated differentiated backprojection (DBP) data. Their generalizability for any ROI sizes is then examined. Experimental results show that the new type of neural network significantly outperforms the existing iterative methods for any ROI size in spite of significantly reduced run-time complexity. Since the proposed method consistently surpasses existing methods for any ROIs, it can be used as a general CT reconstruction engine for many practical applications without compromising possible detector truncation.