Context attention and fusion network suitable for joint segmentation of multiple types of retinal effusion

Abstract

The invention discloses a context attention and fusion network suitable for joint segmentation of multiple types of retinal effusion, which comprises a feature coding module, a context contraction coding CSE module, a context pyramid guidance CPG module and a feature decoding module, and is characterized in that the context contraction coding CSE module is embedded in the feature coding module; the context pyramid guidance CPG module is arranged between the feature coding module and the feature decoding module, and the context contraction coding CSE module is in jump connection with the feature decoding module; according to the retina OCT image, each level feature is selectively aggregated through the feature coding module and the context contraction coding CSE module, multi-scale context information is obtained through the context pyramid guiding CPG module and input into the feature decoding module, and the feature decoding module outputs a segmentation result. According to the context attention and fusion network suitable for joint segmentation of multiple types of retina effusion, the problems that in the prior art, feature aggregation is free of selectivity, and the multi-scale information extraction capacity is low are solved.

Description

technical field [0001] This application relates to the technical field of medical image segmentation, specifically a context attention and fusion network suitable for joint segmentation of multiple retinal effusions. Background technique [0002] The segmentation techniques for retinal fluid in retinal optical coherence tomography (OCT) images are mainly divided into segmentation techniques based on traditional image processing methods and segmentation techniques based on deep learning. [0003] In the segmentation technology of traditional image processing, it is often necessary to manually design features, and use low-level visual information such as the size, location, and shape of the retinal effusion area to determine the contour of the retinal effusion. For example, in the traditional algorithm, the graph search method is used to automatically stratify the retina to obtain the initial segmentation result of the effusion area, and then the AdaBoost classification algori...

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to solve the above technical problems, provide a context attention and fusion network suitable for joint segmentation of multiple retinal effusions, and overcome the non-selective feature aggregation caused by the lack of context information extraction ability in the existing U-shaped structure network , low ability to extract multi-scale information, etc.

Images