DEEP LEARNING-BASED CARDIAC CT IMAGE SEGMENTATION METHOD AND APPARATUS, DEVICE, AND MEDIUM

摘要

The present invention is applicable to the technical field of medical image processing and provides a deep learning-based cardiac CT image segmentation method and apparatus, a device, and a medium. The method comprises: when a cardiac CT image segmentation request is received, obtaining a cardiac CT image input by a user; performing preprocessing on the obtained cardiac CT image to obtain a corresponding preprocessed image; and performing, by means of a pre-trained V-Net model, image segmentation on a preset cardiac tissue area in the preprocessed image to obtain a segmented cardiac tissue area image corresponding to the cardiac CT image. Therefore, the accuracy of the image segmentation performed on a cardiac CT image is improved, such that a highly accurate segmented image is obtained, thereby improving the safety of surgery.