Breathing exercise correction method and device, computer device and storage medium

Abstract

The invention provides a breathing exercise correction method. The breathing exercise correction method comprises the steps that multiple groups of sample images including respiratory organs are obtained, a compound expirationdeformational field set and a compound inspirationdeformational field set are obtained according to the multiple groups of sample images; according to the compound expirationdeformational field set, an expirationanalog image set is obtained, and according to the compound inspirationdeformational field set, an inspirationanalog image set is obtained; according to the multiple groups of sample images, the expirationanalog image set and the inspirationanalog image set, a preset convolutional neural network is trained to obtain a trained convolutional neural network; images to be corrected are obtained, the trained convolutional neural network is utilized to correctbreathing exercises of the respiratory organs in the images to be corrected. By adopting the breathing exercise correction method and device, a computer device and a storage medium, the preset convolutional neural network is trained, accordingly the trained convolutional neural networkcan be utilized tocorrect thebreathing exercises of the respiratory organs in the images to be corrected, and the accuracy of correcting the breathing exercises is improved.

Description

technical field [0001] The present invention relates to the field of medical technology, in particular to a respiratory motion correction method, device, computer equipment and storage medium. Background technique [0002] The comparison of preoperative liver images and postoperative liver images is an important means to verify the accuracy of treatment in postoperative evaluation of liver cancer surgery. Since the preoperative liver image and postoperative liver image are collected, it is impossible to ensure that the patient is at the same respiratory node, and the liver is affected by breathing to produce sliding deformation, so there is respiratory motion deformation between the obtained preoperative liver image and postoperative liver image . In order to correct the respiratory deformation of the liver, the preoperative liver image must be registered with the postoperative liver image, that is, the liver respiratory motion in the postoperative liver image must be corre...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to solve the technical problem of low accuracy in correcting respiratory motion in the prior art, aiming at improving the accuracy of correcting respiratory motion

Images