Retinal vessel segmentation method, device and storage medium based on vessel feature

Abstract

The present application relates to a retinal vessel segmentation method, device and storage medium based on vessel features. Including obtaining the dataset of retinal vessel segmentation, and performing data enhancement operations on the dataset; establishing a deep convolutional neural network intelligent model based on multi-scale semantic information fusion, inputting the enhanced data into the intelligent model, and obtaining the output of the model; Use the image morphology method to detect blood vessel breakpoints and areas with inconsistent thickness in the output results; increase the weight of the loss function on the breakpoints and areas with inconsistent thickness, and iterate and optimize the intelligent model through the cross-entropy loss function of dynamic weights to achieve Accurate segmentation of retinal vessels. This method combines multi-scale semantic information and breakpoint information to solve vascular connectivity, and improves the loss function by extracting vascular thickness information to solve the problem of inconsistency in vascular thickness, effectively improving the accuracy of retinal vascular segmentation, which is of great significance for computer medical intelligent diagnosis .

Description

technical field [0001] The present application relates to the field of medical diagnosis, in particular to a retinal vessel segmentation method, device and storage medium based on vessel features. Background technique [0002] In the diagnosis of modern medical diseases, the fundus retinal blood vessels are of great significance. Many diseases can be detected and prevented through the morphological changes of the fundus retinal blood vessels. Through retinal vessel segmentation, information such as the curvature, length and width of retinal vessels can be obtained, which is of great significance for the analysis of diseases such as diabetes and hypertension. [0003] However, the retinal vascular tree has a very complex structure. First, the retinal vascular pixels in the fundus image only account for 30%, and the length of the capillary accounts for 70% of the entire vascular tree, and the width of the capillary is very different from that of the main blood vessels. Large,...

AI Technical Summary

Problems solved by technology

[0003] However, the retinal vascular tree has a very complex structure. First, the retinal vascular pixels in the fundus image only account for 30%, and the length of the capillary accounts for 70% of the entire vascular tree, and the width of the capillary is very different from that of the main blood vessels. Large, capillary vessels are often only one or two pixels wide, while major blood vessels are tens of pixels wide

Images