Low-dose CT Reconstruction Assisted by a Global CT Image Manifold Prior

摘要

The use of X-ray Computed Tomography (CT) leads to the concern of lifetime cancer risk. Low-dose CTscan with reduced mAs can reduce the radiation exposure, but the image quality is usually degraded due to excessiveimage noise. Numerous studies have been conducted to regularize CT image during reconstruction for better imagequality. In this paper, we propose a fully data-driven manifold learning approach. An auto-encoder-decoder convolutionalneural network is established to map an entire CT image to the inherent low-dimensional manifold, and then torestore the CT image from its manifold representation. A novel reconstruction algorithm assisted by the leant manifoldprior is developed to achieve high quality low-dose CT reconstruction. We perform comprehensive simulation studiesusing patient abdomen CT images. The trained network is capable of restoring high-quality CT images with averageerror of ～20 HU. The manifold prior assisted reconstruction scheme achieves high-quality low-dose CT reconstruction,with average reconstruction error of ～38.5 HU, 4.6 times and 3 times lower than that of filtered back projectionmethod and total-variation based iterative reconstruction method, respectively.