2.5D cardiac segmentation algorithm based on deep learning
The automatic segmentation algorithm of cardiac dynamic MRI images can effectively reduce the pressure on cardiovascular doctors,and its segmentation results are the gold standard for evaluating cardiac function.This article proposes an automatic segmentation algorithm that effectively segments cardiac dynamic MRI images.According to the cardiac dynamic MRI image,the U-shaped neural network results are used by the proposed algorithm.The network structure is divided into a target image in the downsampling layer,an adjacent time slice in the downsampling layer,an upsampling layer and a connecting bridge.Compared with other segmentation algorithms,the proposed algorithm in this article can better segment cardiac images and the segmentation effect is more accurate.
万方数据
维普
