Image segmentation method based on pyramid fusion learning, device and computer readable storage medium

Abstract

The invention discloses an image segmentation method based on feature pyramid fusion, which is used for analyzing a magnetic resonance image and segmenting edema and necrosis tissues and normal tissues. A method for remove edema without inclusion by preprocessing that data, Magnetic resonance imaging of necrotic tissue information, data enhancement is then performed to prevent over-fitting, and then the data is put into the depth learning model with characteristic pyramid fusion, Firstly, the feature of the data is extracted by the downsampling process, and then the resolution of the input data is recovered gradually in the upsampling process. Finally, the segmentation results are obtained by the pyramid fusion of the information extracted from the upsampling process at various scales. Experiments are performed using BraTS 2015 and BraTS 2017 datasets, and five cross validations are performed. Compared with the depth learning model without pyramid fusion, the segmentation accuracy of the method proposed by the invention is obviously improved, which indicates that the method proposed by the invention is effective.

Description

technical field [0001] The invention relates to an image segmentation method, device and computer-readable storage medium based on pyramid fusion learning, belonging to the field of image processing. Background technique [0002] The semantic segmentation of images is one of the important basic problems in computer vision. Its goal is to classify each pixel of the image and divide the image into several visually meaningful or interesting regions for the benefit of subsequent images. Analysis and visual understanding. It can be used for automatic driving, beautifying pictures, face modeling, 3D map reconstruction, etc. [0003] Traditional image automatic segmentation algorithms can be generally divided into threshold method, edge detection method, region growth method, watershed algorithm, model-based method (level set) or a combination of multiple methods. The threshold method needs to manually select the threshold, while ignoring the spatial information of the image. Th...

AI Technical Summary

Problems solved by technology

However, if the deep learning method is used for segmentation, the input data undergoes multiple convolutions and downsampling, and the lesion tissue information loses the spatial position information after multiple downsampling, so that in the subsequent process of upsampling to restore the image resolution, It is difficult to accurately segment the complete diseased tissue, and in medical imaging, there are multiple scales of diseased tissue information. Therefore, how to effectively use the location information and multi-scale information of the diseased tissue to complete the precise segmentation of the diseased tissue is a important questions to address now

Images