Prior information-based high-resolution tomography image reconstruction from single digitally reconstruction radiograph.

Researchers

Journal

Modalities

Models

Abstract

Tomography image is essential for clinical diagnosis and trauma surgery, which promotes doctors understand the internal information of patients in more detail. Since a large amount of X-ray radiation of continuous imaging in the process of computed tomography scanning can cause serious harm to the human body, reconstructing tomographic images from sparse view becomes a potential solution to this problem. Here we present a deep-learning framework for tomography image reconstruction, namely TIReconNet, which defines image reconstruction as a data-driven supervised learning task that allows a mapping between the 2D projection view and the 3D volume to emerge from corpus. Proposed framework consists of four parts: feature extraction module, shape mapping module, volume generation module and super resolution module. The proposed framework combines 2D and 3D operations， which can generate high-resolution tomographic images with a relatively small amount of computing resources and maintain spatial information. Proposed method is verified on chest digitally reconstructed radiographs, and the reconstructed tomography images have achieved PSNR value of 18.621±1.228dB and SSIM value of 0.872±0.041 when compared against the ground truth. In conclusion, an innovational convolutional neural network architecture was proposed and validated in this study, which proved that it is potential to generate a 3D high-resolution tomographic image from single 2D image by deep learning. This method may actively promote the application of reconstruction technology in radiation reduction, and further exploration of intraoperative guidance in trauma and orthopedics.© 2022 Institute of Physics and Engineering in Medicine.