A CT image reconstruction method and system, terminal and readable storage medium

Abstract

The invention belongs to the technical field of medical and industrial CT imaging, and in particular relates to a CT image reconstruction method and system, a terminal and a computer-readable storage medium. This method uses traditional CT image reconstruction methods to generate original reconstructed images, removes artifacts and optimizes noise on the original reconstructed images, and extracts some detailed structural data lost due to optimization. At the same time, using the optimized original reconstruction The image obtains a feature operator, convolves the lost part of the detailed structure data with the feature operator, thereby extracting useful detailed structures from the lost information, and then adds the obtained convolution data back to the optimized original reconstructed image. Finally, CT reconstructed images are obtained. On the basis of reducing artifacts and noise, this method retains structural details, thereby reconstructing the image of the complete data, so that the final CT reconstructed image has a very high quality and improves the accuracy of the CT reconstructed image.

Description

technical field [0001] The invention belongs to the technical field of medical and industrial CT imaging, and in particular relates to a CT image reconstruction method and system, a terminal and a readable storage medium. Background technique [0002] The clinical value of computerized tomography (Computed Tomography, CT) is beyond doubt, but X-ray exposure is harmful to patients. At present, in the CT field, the dose of CT radiation is usually reduced by reducing the number of samples, such as under-sampling or sparse sampling methods. However, both undersampling and sparse sampling methods are incomplete sampling. [0003] To solve the problem of incomplete sampling, it is necessary to use CT algorithm to reconstruct the incomplete sampling data. At present, many hardware-based scanning protocols and reconstruction algorithms for processing low-dose sampling data have been proposed. However, when the traditional CT algorithm reconstructs incomplete sampling data, it will...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a CT image reconstruction method and system, a terminal and a readable storage medium, aiming to solve the problem that the existing reconstruction algorithm will cause the loss of structural details of the image, and the quality of the reconstructed image is low

Images