Dose Images Reconstruction Based on X-ray-Induced Acoustic Computed Tomography

The accurate reconstruction of the in vivo dose is a critical step radiation therapy. X-ray-induced acoustic imaging promising technology for reconstruction, as it enables nonradiative and noninvasive monitoring dose. However, current X-ray methods suffer from several limitations, including high signal-to-noise ratio, poor quality massive loss structural information. To address these we propose image method based on tensor sparse dictionary learning. Specifically, combine coding with compressed sensing data, extend two-dimensional learning to three-dimensional by using product, then utilize spatial information signal more efficiently. reduce artifacts images caused spare sampling, design alternate iterative solution coefficient dictionary. In addition, build system, simulate signals patients’ Sichuan Cancer Hospital, create simulated datasets. Compared some typical state-of-the art methods, experimental results demonstrate that our can significantly improve reconstructed accuracy distribution.