Multi-mechanism adaptive fundus image segmentation method

Abstract

The invention discloses a multi-mechanism adaptive eye fundus image segmentation method, which belongs to the field of artificial intelligence medical image processing, constructs a multi-mechanism adaptive Faster R-CNN eye fundus image segmentation network, and adopts a network global loss function to guide optic disk and optic cup segmentation. The method specifically comprises the following steps: collecting an eye fundus image data set, and performing preprocessing; the preprocessed data set is input into the constructed multi-mechanism adaptive Faster R-CNN eye fundus image segmentation network; a network global loss function is adopted to guide accurate segmentation of an optic disk and an optic cup; eye fundus images are collected in real time and input into a multi-mechanism adaptive Faster R-CNN eye fundus image segmentation network, an optic disc and an optic cup are accurately segmented by using a global loss function in the network, and clinical diagnosis of doctors is assisted. According to the method, accurate segmentation of the optic disc and the optic cup in the eye fundus image is realized, and the method has relatively good generalization and robustness.

Description

technical field [0001] The invention belongs to the field of artificial intelligence medical image processing, and in particular relates to a multi-mechanism adaptive fundus image segmentation method based on Faster R-CNN. Background technique [0002] Glaucoma is an irreversible blinding fundus disease, generally manifested as a sudden increase in intraocular pressure, atrophy of the optic nerve in the fundus, and a sharp decline in vision. Because glaucoma has no obvious symptoms in the early stage and gradually loses vision as the disease progresses, it is often called the "invisible killer of vision". Therefore, early screening of glaucoma is very important. There are three current screening methods for glaucoma: intraocular pressure measurement, function-based visual field testing, and optic nerve head assessment. Among them, optic disc assessment is more suitable for large-scale fundus screening, and cup-to-disk ratio is often used as an important basis for optic ner...

AI Technical Summary

Problems solved by technology

However, the traditional segmentation method is easily limited by the illumination, contrast and edge definition of the fundus image, and the performance of the model depends largely on the selection and optimization of the initial point, so the robustness needs to be improved

In addition, due to the existence of the domain migration problem, most deep learning methods have a good segmentation effect on the training set, but it is difficult to achieve good segmentation performance on the new data set that is different from the appearance distribution of the training image.

Differences in scanner, image resolution, light source intensity, and parameter settings can all lead to significant differences in the appearance of fundus images

Images