Image processing method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides an image processing method and device based on multiple neural network models, electronic equipment and a computer readable storage medium. The image processing method based onthe plurality of neural network models comprises the following steps: for an input image, generating a plurality of corresponding image preprocessing results by utilizing the plurality of neural network models; determining a corresponding feature representation image based on the plurality of image preprocessing results; selecting one neural network model in the plurality of neural network modelsas a benchmark model, taking the corresponding feature representation as a benchmark feature representation image, taking other neural network models in the plurality of neural network models as reference models, and taking the corresponding feature representation as a reference feature representation image; and adjusting the reference feature representation image based on the reference feature representation image to generate an output image.

Description

technical field [0001] The present disclosure relates to the field of image processing, and more specifically, the present disclosure relates to an image processing method based on multiple neural network models, an image processing device, electronic equipment, and a computer-readable storage medium. Background technique [0002] Neural networks are a tool for large-scale, multi-parameter optimization. Relying on a large amount of training data, the neural network can learn hidden features that are difficult to summarize in the data, thereby completing multiple complex tasks, such as face detection, image semantic segmentation, object detection, action tracking, natural language translation, etc. Currently, artificial intelligence technology using neural networks has been applied to the processing and analysis of medical images such as computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). For example, in the non-invasive corona...

AI Technical Summary

Problems solved by technology

At present, traditional algorithms or single-model neural networks are usually used to perform coronary artery segmentation, and it is difficult to solve the two problems of rupture and venous adhesion at the same time

Images