Geodesic Graph Cut Based Retinal Fluid Segmentation in Optical Coherence Tomography

Abstract

Abstract. Age-related macular degeneration (AMD) is a leading cause of blindness in developed countries. Its most damaging form is characterized by accumulation of fluid inside the retina, whose quantification is of utmost importance for evaluating the disease progression. In this paper we propose an automated method for retinal fluid segmentation from 3D images acquired with optical coherence tomography (OCT). It combines a machine learning approach with an effective segmentation framework based on geodesic graph cut. After an image preprocessing step, an artificial neural network is trained based on textural features to assign to each voxel a probability of belonging to a fluid. The obtained probability maps are used to compute minimal geodesic distances from a set of identified seed points to the remaining unassigned voxels. Finally, the segmentation is solved optimally and efficiently using graph cut optimization. The method is evaluated on a clinical longitudinal dataset consisting of 30 OCT scans from 10 patients taken at 3 different stages of treatment. Manual annotations from two retinal specialists were taken as the gold standard. The segmentation method achieved mean precision of 0.88 and recall of 0.83, with the combined F1 score of 0.85. The segmented fluid volumes were within the measured inter-observer variability. The results demonstrate that the proposed method is a promising step towards accurate quantification of retinal fluid.

Fully-Automated Segmentation of Fluid/Cyst Regions in Optical Coherence Tomography Images with Diabetic Macular Edema using Neutrosophic Sets and Graph Algorithms

“…The accuracy of this method in retinal fluid segmentation was evaluated on 10 DME subjects. In [27], an automated method based on artificial neural network combined with a segmentation framework based on geodesic graph cut for retinal fluid segmentation from OCT images of AMD subjects was presented. This method was evaluated on 30 OCT volumes from 10 AMD subjects at 3 different treatment stages.…”

“…[36], [37] also present DME methods which have been applied to 3D OCT volumes but in a supervised manner. Apart from the proposed methods for DME subjects, methods in [24], [25], [27], [39] have been proposed for AMD subjects using a supervised 3D procedure. Correlation between initial vision and vision improvement with automatically calculated retinal cyst volume in treated DME subjects was analysed in [40].…”

Automated Deep Learning-based Multi-class Fluid Segmentation in Swept-Source Optical Coherence Tomography Images

“…This segmentation information was then encoded into a separate channel that was later entered into the supervised learning process. Existing literature has used, separately, layer information as features in support of the classification of fluid pockets, 15 in their words leveraging the fact that retinal fluid is known to exhibit layer dependent properties and thus is used by the model to help determine the type of fluid; IRF typically being higher up in the volume, SRF close to and above the RPE, PEDs below the RPE, but not below the retina itself. In Figure 2, the column of images on the left represent single B-scans within the volume, that on the right are the layer segmentation result encoded as image data for each of those Bscans.…”

Automated segmentation of intraretinal cystoid macular edema based on Gaussian mixture model

“…Gopinath et al 34 proposed a method based on FCNN by selective enhancement to segment retinal cysts. Bogunović et al 35 used a machine learning approach combined with an effective segmentation framework based on geodesic graph cut to segment retinal°uid regions. Although the methods described in Refs.…”