Eyeball segmentation method and device based on convolutional neural network and mixed loss function

Abstract

According to the eyeball segmentation method and device based on the convolutional neural network and the mixed loss function, the segmentation precision of eyeballs in a CT image can be improved. The method comprises the following steps: (1) in a data set manufacturing stage, drawing an eyeball segmentation gold standard through manual labeling, carrying out preprocessing operations of taking two-dimensional slices, downsampling and standardizing on original three-dimensional CT image data, and then integrally dividing a data set into three parts, namely a training set, a verification set and a test set for training and testing a network; (2) in a network training stage, establishing a convolutional neural network model cascaded by a coarse segmentation module and a U-shaped residual error fine tuning module, and performing multi-level supervised optimization on a network segmentation result by using a mixed loss function formed by cross entropy, intersection-to-union ratio and structural similarity measurement; and (3) in a test stage, feeding a test data set into the optimal segmentation model obtained by training for segmentation, and restoring an output result into three-dimensional data to obtain a final eyeball segmentation result.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to an eyeball segmentation method based on a convolutional neural network and a hybrid loss function, and an eyeball segmentation device based on a convolutional neural network and a hybrid loss function. Background technique [0002] In the head CT image, the position and shape of the eyeball are relatively fixed, but the edges are blurred and adhered to other surrounding tissues, accounting for a small proportion of the overall image. These characteristics make it difficult to automatically segment the eyeball in the CT image. Accurate eyeball segmentation can help doctors determine eyeball position, measure eyeball radius, volume, etc., and play an important role in auxiliary diagnosis, preoperative planning, intraoperative navigation, and postoperative treatment evaluation. Contents of the invention [0003] In order to overcome the defects of the prio...

AI Technical Summary

Problems solved by technology

[0002] In the head CT image, the position and shape of the eyeball are relatively fixed, but the edges are blurred and adhered to other surrounding tissues, accounting for a small proportion of the overall image. These characteristics make it difficult to automatically segment the eyeball in the CT image

Images