Motion artifact correction method and device, computer equipment and readable storage medium

Abstract

The invention relates to a motion artifact correction method and device, computer equipment and a readable storage medium. The method comprises the steps of obtaining a to-be-corrected image; inputting the to-be-corrected image into a trained target neural network model to obtain a corrected image, the target neural network model being a neural network model obtained by training according to an image with motion artifact and an image without motion artifact. The image with the motion artifact is an image obtained by performing motion simulation on the image without the motion artifact. According to the motion artifact correction method provided by the invention, the image without the motion artifact is used as the gold standard of the network, the real motion of the human body is forwardlysimulated on the image without the motion artifact, and the generated motion artifact image is used as the input of the network to train the network. Since the motion simulation of the motion artifact-free image is established on the basis of the real motion of the human body, the obtained motion artifact-containing image better conforms to the real scene, the trained neural network model is morestable, and the motion artifact correction effect is improved.

Description

technical field [0001] The invention relates to the technical field of medical imaging, in particular to a motion artifact correction method, device, computer equipment and readable storage medium. Background technique [0002] Computed tomography equipment typically includes a gantry, a scanning table, and a console for a doctor to operate. A ball tube is arranged on one side of the rack, and a detector is arranged on the side opposite to the ball tube. The console is a computer device that controls the ball tube and the detector to scan, and the computer device is also used to receive the projection data collected by the detector, process and reconstruct the projection data, and finally form an image. When using scanning, the patient lies on the scanning bed, and the scanning bed sends the patient into the aperture of the frame, and the ball tube set on the frame emits X-rays, and the X-rays pass through the patient and are received by the detector to form projection data...

AI Technical Summary

Problems solved by technology

[0004] Traditionally, motion artifacts have been suppressed by directly reducing scan time, but this is a significant challenge for mechanical performance

In addition, the motion artifact correction technology based on motion parameter estimation is also used to suppress motion artifacts, but most of them have not realized the correction of rigid motion artifacts, and the ability to resist noise is not strong

Images