Macular edema lesion area segmentation method based on deep neural network

Abstract

The invention provides a macular edema lesion area segmentation method based on a deep neural network. The macular edema lesion area segmentation method comprises the steps of acquiring an OCT image of an fundus of a macular edema patient; and inputting the OCT image into a trained deep neural network segmentation model to obtain a focus area on the OCT image of the fundus of the macular edema patient. The OCT image is input into the trained deep neural network segmentation model to obtain the focus area on the OCT image of the fundus of the macular edema patient. Compared with the prior art,a lot of manpower and material resources are saved. Meanwhile, a focus area on the OCT image of the fundus of the macular edema patient is acquired through the trained deep neural network segmentationmodel. The problem that the evaluation error of macular edema is large due to the fact that at present, due to the fact that OCT image noise is large and experience differences between doctors are large, sketching results of different doctors are often large in difference can be solved.

Description

technical field [0001] The present application relates to the technical field of medical image processing, in particular, to a method, device, electronic equipment and storage medium for macular edema lesion region segmentation based on a deep neural network. Background technique [0002] The macular area is the most sensitive part of the fundus to light. Macular edema refers to the inflammatory reaction and fluid infiltration in the macular area of ​​the fundus, resulting in edema. Diseases include: retinal pigment epithelial detachment (Pigment Epithelium Detachment, PED), subretinal edema (Subretinal Fluid, SRF), etc. At present, patients are examined mainly by acquiring OCT (Optical coherencetomography, optical coherence tomography) images of the patients. In order to quantitatively evaluate the patient's condition, the doctor will outline the area of ​​macular edema based on the OCT image, such as the specific area of ​​PED and SRF. Afterwards, the volume of the macul...

AI Technical Summary

Problems solved by technology

In order to improve the above "manually delineating the macular edema area will consume huge time and labor costs. In addition, due to the large noise of the OCT image and the difference in experience between doctors, the delineation results of different doctors often vary greatly, which leads to the evaluation of macular edema. big error" problem

Images