SD-OCT image macular fovea centralis center positioning method

Abstract

The invention discloses an SD-OCT image macular fovea centralis center positioning method. The method comprises the following steps: segmenting an inner boundary film layer and a Bloom film layer of an SD-OCT image; extracting each column of pixels between the inner boundary film layer and the Bloom film layer as features; training a random forest classifier to segment a fovea centralis non-vascular region, and calculating the geometric center position of the fovea centralis non-vascular region as the rough center position P1 of the macular fovea centralis; a retina thickness image is generated within a certain range with P1 as the center; judging whether the retina in the area is sunken or not, and if yes, taking the position at the minimum thickness value as a new foveal fovea central position P2; if not, the P2 is still the position of the P1; and searching a central concave high-reflection region around the position P2, if the high-reflection region exists, taking the central position of the high-reflection region as a final central concave central position P3, and otherwise, taking the P3 as the position P2. Compared with the conventional method for positioning only accordingto the thickness change of the retina, the robustness and the precision of the method are greatly improved.

Description

technical field [0001] The invention belongs to the field of retinal image analysis, in particular to a method for locating the center of the macular fovea in a frequency-domain optical coherence tomography (SD-OCT) image. Background technique [0002] SD-OCT is a rapid, non-invasive frequency-domain optical coherence tomography technique that has become part of the standard of care in ophthalmology. The macular area of ​​the retina is the main imaging area of ​​SD-OCT, and the center of the macular fovea is the most important marker of the macular area of ​​the retina, and it is the most sensitive area on the retina. Generating a thickness grid map based on the center of the macular fovea is an important tool for early treatment of retinopathy. Therefore, the positioning of the center of the macular fovea is a fundamental work of great significance. [0003] Existing technologies are mainly based on the convergence of the retinal layer structure and the thinning of the re...

AI Technical Summary

Problems solved by technology

[0003] Existing technologies are mainly based on the convergence of the retinal layer structure and the thinning of the retinal thickness. These algorithms need to rely on multi-layer retinal layer segmentation algorithms, and these layer segmentation algorithms are less robust to retinal disease, especially in the In diseases such as retinal edema, the position of the center of the macular fovea will no longer be at the minimum value of retinal thickness, so these foveal algorithms will also fail

Images