Image processing method and device

The invention provides an image processing method and device. The image processing method comprises the following steps: acquiring a sequence image, and acquiring local tubular information of a tubular object to be segmented; then, in the model training process, introducing contour information into a three-dimensional feature segmentation model obtained through calculation of a loss function; and performing segmentation processing on the tubular features corresponding to the local tubular information in the sequence image, thereby realizing more accurate segmentation processing on the tubular features through a three-dimensional feature segmentation model. Therefore, the display effect of the tubular feature image obtained after segmentation processing is improved. 本申请提供图像处理方法及装置，其中所述图像处理方法包括：获取序列图像，获取待分割管状物的局部管状信息，之后使用在模型训练过程中，将轮廓信息引入损失函数的计算获得的三维特征分割模型，对所述序列图像中所述局部管状信息对应的管状特征进行分割处理，实现通过三维特征分割模型可以更加精准的对管状特征进行分割处理，从而提高分割处理后获得的管状特征图像的展示效果。