Retinal segmentation is a prerequisite for quantifying retinal structural features and diagnosing related ophthalmic diseases. Canny operator is recognized as the best boundary detection operator so far, and is often used to obtain the initial boundary of the retina in retinal segmentation. However, the traditional Canny operator is susceptible to vascular shadows, vitreous artifacts, or noise interference in retinal segmentation, causing serious misdetection or missed detection. This paper proposed an improved Canny operator for automatic segmentation of retinal boundaries. The improved algorithm solves the problems of the traditional Canny operator by adding a multi-point boundary search step on the basis of the original method, and adjusts the convolution kernel. The algorithm was used to segment the retinal images of healthy subjects and age-related macular degeneration (AMD) patients; eleven retinal boundaries were identified and compared with the results of manual segmentation by the ophthalmologists. The average difference between the automatic and manual methods is: 2–6 microns (1–2 pixels) for healthy subjects and 3–10 microns (1–3 pixels) for AMD patients. Qualitative method is also used to verify the accuracy and stability of the algorithm. The percentage of “perfect segmentation” and “good segmentation” is 98% in healthy subjects and 94% in AMD patients. This algorithm can be used alone or in combination with other methods as an initial boundary detection algorithm. It is easy to understand and improve, and may become a useful tool for analyzing and diagnosing eye diseases.
The virtual lens model has important value in ophthalmic research, clinical diagnosis, and treatment. However, the establishment of personalized lens models and the verification of accommodation accuracy have not been paid much attention. We proposed a personalized lens model establishment and the accommodation accuracy evaluation method based on sweep-source optical coherence tomography (SS-OCT). Firstly, SS-OCT is used to obtain a single lens image in the maximum accommodation state. After refraction correction, boundary detection, and curve fitting, the central curvature radius, thickness, and lens nucleus contour of the anterior and posterior surfaces of the lens were obtained. Secondly, a personalized finite element model improved from Burd’s model was established using these individual parameters, and the adaptation process of the lens model was simulated by pulling the suspensory ligament. Finally, the shape and refractive power changes of the real human lens under different accommodation stimuli were collected and compared with the accommodation process of the finite element model. The results show that the accommodation process of the finite element model is highly consistent with that of the real lens. From the un-accommodation state to the maximum-accommodation state, the difference rate of all geometric and refractive parameters between the two is less than 5%. Thus, the personalized lens finite element model obtained by the calibration and correction of the existing model can accurately simulate the regulation process of a specific human lens. This work helps to provide a valuable theoretical basis and research ideas for the study of clinical diagnosis and treatment of related diseases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.