Field of View Extension in Computed Tomography Using Deep Learning Prior
This addresses image quality issues in CT scans for medical imaging applications, representing an incremental improvement over existing deep learning post-processing methods.
The paper tackles the problem of data truncation in computed tomography, which causes artifacts and missing structures, by proposing a data-consistent reconstruction method that uses deep learning as a prior for extrapolating truncated projections and iterative reconstruction to ensure fidelity to measured data, achieving an average root-mean-square error of 24 HU inside the field of view and a structure similarity index of 0.993 for the whole body area.
In computed tomography (CT), data truncation is a common problem. Images reconstructed by the standard filtered back-projection algorithm from truncated data suffer from cupping artifacts inside the field-of-view (FOV), while anatomical structures are severely distorted or missing outside the FOV. Deep learning, particularly the U-Net, has been applied to extend the FOV as a post-processing method. Since image-to-image prediction neglects the data fidelity to measured projection data, incorrect structures, even inside the FOV, might be reconstructed by such an approach. Therefore, generating reconstructed images directly from a post-processing neural network is inadequate. In this work, we propose a data consistent reconstruction method, which utilizes deep learning reconstruction as prior for extrapolating truncated projections and a conventional iterative reconstruction to constrain the reconstruction consistent to measured raw data. Its efficacy is demonstrated in our study, achieving small average root-mean-square error of 24 HU inside the FOV and a high structure similarity index of 0.993 for the whole body area on a test patient's CT data.