Image segmentation method and device and computer readable storage medium

The invention discloses an image segmentation method and apparatus, and a computer readable storage medium. The method comprises the steps of constructing a training sample set based on a target bloodvessel image data set and a corresponding label set; training a hybrid deep learning network comprising a full convolutional neural network and U-net by adopting the training sample set to obtain animage segmentation model; and inputting the to-be-segmented blood vessel image into the image segmentation model for image segmentation. Through the implementation of the invention, the blood vessel image segmentation is carried out by adopting the hybrid deep learning network, emphasizing on the overall characteristics of the image, and the blood vessel segmentation precision and robustness are effectively improved. 本发明公开了一种图像分割方法、装置及计算机可读存储介质，基于目标血管图像数据集以及对应的标签集构建训练样本集；采用训练样本集对包括全卷积神经网络和U-net的混合深度学习网络进行训练，得到图像分割模型；将待分割血管图像输入至图像分割模型进行图像分割。通过本发明的实施，采用混合深度学习网络进行血管图像分割，侧重于图像的整体特征，有效提高了血管分割精度和鲁棒性。