Image segmentation method and device, equipment and storage medium

The invention relates to artificial intelligence, and provides an image segmentation method and device, equipment and a storage medium. The method comprises the steps of preprocessing a medical image to obtain an image vector, performing feature extraction on the image vector based on a convolutional network layer to obtain an initial medical feature, performing iterative processing on the initial medical feature based on a backbone network layer until the execution frequency is greater than or equal to the configuration frequency, and obtaining a plurality of target medical features. The multiple target medical features are input to a segmentation network layer for segmentation processing, multiple output segmentation features are obtained, the multiple output segmentation features comprise target segmentation features, multi-level pooling processing is carried out on the target segmentation features based on a pyramid pooling layer, pooling features are obtained, and the pooling features are output; and inp