Fast Retinal Segmentation Based on the Wave Algorithm

The retinal layer segmentation technique of optical coherence tomography (OCT) data is essential for the diagnosis of ophthalmic and systemic diseases. To achieve fast and accurate retinal layer segmentation, a new medical image segmentation method (wave algorithm) is proposed based on the mathematical model of the fluid potential energy equation in fluid mechanics. A change in the gray value in the image is converted into a change in the potential energy in the ideal fluid (wave), thereby transforming the image segmentation problem into a problem that solves the potential energy based on the fluid potential energy equation. In the process of solving the fluid energy, it is necessary to constrain the potential energy according to the prior knowledge of the medical image. The method consists of two parts: the wave potential energy equation and the potential energy correction equation. When the method is applied to the retinal layer segmentation of an OCT image, the method first detects the boundary area of the retinal layer according to the wave potential energy equation and then uses the potential energy correction equation to accurately extract the boundary line from the boundary area. The proposed method is tested on publicly available datasets. The results show that compared with other advanced segmentation methods, the method achieved slightly superior segmentation accuracy and speed. When the mean unsigned positioning error of the retinal layer segmentation is less than 1.5 pixels, the method can quickly segment the retinal layer at a speed of 1.19 per B-scan/seconds.

Abstract licence: CC BY-NC-ND

25 more references, whose wording the paper’s licence keeps private.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.