Cone-cell density calculation method based on image identification

Abstract

The invention relates to a cone-cell density calculation method based on image identification. The method mainly solves the prior problem that density counting of cone cells is performed manually and an eye-ground adaptive confocal laser scanning ophthalmoscope is used to obtain a visual cone-cell image and after the response frequency of the cone cells is determined, low-pass filtering is used for denoising processing so as to establish a two-valued sequence. A local maximum value corresponding to a non-zero area is searched for so that the central position of the cone cells is found. After automatic identification of the visual cone cells in the image is completed, the number of the cone cells in the image is obtained with the assistance of manual correction and finally the density counting of the cone cells is achieved. When the function which adopts a computer to counting automatically is compared with a manual counting method, the automatic calculation method is accurate, high in statistical speed, high in automation degree, checkable in analysis result and improved in detection efficiency. At the same time, a manual correction function is added so that on the basis of software analysis, error identification can be removed manually and missed cone cells can be added and thus caused result deviation is prevented.

Description

technical field [0001] The invention belongs to the fields of fundus microscopic imaging and medical detection. Specifically, the invention relates to a method for calculating cone cell density based on image recognition. Background technique [0002] There are three levels of neurons in the retina, including cones, rods, bipolar cells, and ganglion cells. Cone cells and rod cells belong to the first-level neurons. They sense external light and image information and transmit them to the visual center through bipolar cells and ganglion cells. Among them, the cone cells are mainly responsible for brightening vision, distinguishing fine shapes and color vision, and are mainly distributed in the macular area of ​​the retina (the center of the macula only has cone cells), which is the anatomical and physiological basis for the formation of visual acuity, that is, vision. And in some fundus diseases such as retinitis pigmentosa and cone-rod dystrophy, there will be changes in con...

AI Technical Summary

Problems solved by technology

At present, different research institutions at home and abroad have disclosed the use of adaptive optics technology to realize microscopic imaging of the human eye retina (JP2007-14569, 99115051.1, 201110293434.1). They have continuously improved the AOSLO imaging system to achieve a larger field of view. Clearer images of cones, but none of them proposed a method for automatic cone density counting

However, if the cone cell analysis is to be performed, it is necessary to understand the change of the number density. If only the calculation of the cone cell density is performed manually, it is time-consuming and labor-intensive, which will inevitably limit the clinical application in the future.

Images