Image processing methods and apparatus, storage media

Abstract

This application discloses an image processing method, apparatus, and storage medium. The method involves acquiring a CT image set including multi-slice CT images, determining the target slice interval, defining multiple groups based on the target slice interval, and then sequentially assigning the multi-slice CT images to the multiple groups according to the slice order and the target slice interval. Finally, one of the groups is randomly selected as the target image set. This process transforms a CT image set with smaller slice thicknesses into a CT image set with larger slice thicknesses, adapting to the slice thickness processing requirements of a 3D processing model. The technical solution of this application avoids the additional noise introduced by interpolation, thus preventing distortion of the CT image set. Furthermore, it enables model training and prediction to be compatible with CT image data of different slice thicknesses, thereby improving the accuracy of the 3D reconstruction results of the CT image set. Therefore, this application can be widely applied in image processing technology.

Images