Abstract

Retinal layer thickness, evaluated as a function of spatial position from optical coherence tomography (OCT) images is an important diagnostics marker for many retinal diseases. However, due to factors such as speckle noise, low image contrast, irregularly shaped morphological features such as retinal detachments, macular holes, and drusen, accurate segmentation of individual retinal layers is difficult. To address this issue, a computer method for retinal layer segmentation from OCT images is presented. An efficient two-step kernel-based optimization scheme is employed to first identify the approximate locations of the individual layers, which are then refined to obtain accurate segmentation results for the individual layers. The performance of the algorithm was tested on a set of retinal images acquired in-vivo from healthy and diseased rodent models with a high speed, high resolution OCT system. Experimental results show that the proposed approach provides accurate segmentation for OCT images affected by speckle noise, even in sub-optimal conditions of low image contrast and presence of irregularly shaped structural features in the OCT images.

Highlights

  • Optical coherence tomography (OCT) is a powerful imaging technique, capable of acquiring non-invasive, high resolution, 3D images of the structural composition of biological tissue [1,2]

  • One important biomedical application of OCT is in ophthalmology, where high resolution volumetric retinal imaging allows for clinical diagnosis and investigation of retinal diseases [3]

  • This paper proposes a segmentation algorithm for the segmentation of all intra-retinal layers in OCT images

Read more

Summary

Introduction

Optical coherence tomography (OCT) is a powerful imaging technique, capable of acquiring non-invasive, high resolution, 3D images of the structural composition of biological tissue [1,2]. Speckle noise in OCT images causes difficulty in the precise identification of the boundaries of layers or other structural features in the image either through direct observation or use of segmentation algorithms. Fernandez et al [6] proposed to first apply complex diffusion filtering to reduce speckle noise and determine the individual retinal layers based on intensity peaks. Ahlers et al [9] employed adaptive thresholding and intensity peak detection to determine individual retinal layers, with morphological filtering applied to the thresholded results These methods are sensitive to intensity inconstancy within the individual layers, which may not be the case in situations characterized by low image contrast and the presence of blood vessels or other morphological features within the retina. The proposed approach is highly efficient and allows for the segmentation of retinal layers

Theory
Experimental Verification
Results and Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call