Artificial intelligence-based image segmentation method, device, equipment and medium

Abstract

The application relates to the field of digital medical technology, in particular to an image segmentation method and device based on artificial intelligence, equipment and medium. The method uses a first MRI brain image set to train a preset first model, uses model parameters of the first model to update a second model, uses the updated second model to cut a target MRI brain image to be segmented to obtain M sub-images, classifies and predicts each sub-image to obtain a target classification category, clusters sub-images with adjacent pixel positions and the same target classification category in the target MRI brain image, obtains clustering results of all the sub-images, segments the target MRI brain image based on the clustering results, realizes training of a model using less labeled images, updates the model for image segmentation in a parameter optimization mode, and further realizes training of the model and segmentation of the image, reduces the influence of problems such as high cost and low efficiency caused by manual labeling, and helps to improve the application effect of digital medical treatment in auxiliary diagnosis and treatment.

Images