With the introduction of spectral-domain optical coherence tomography (OCT), much larger image datasets are routinely acquired compared to what was possible using previous generation time-domain OCT. Thus, need for 3-D segmentation methods processing such data is becoming increasingly important. We report a graph-theoretic method simultaneous multiple surfaces that guaranteed be optimal with respect cost function and directly applicable spectral OCT data. present two extensions general...

Current techniques for segmenting macular optical coherence tomography (OCT) images have been 2-D in nature. Furthermore, commercially available OCT systems only focused on a single layer of the retina, even though each intraretinal may be affected differently by disease. We report an automated approach (anisotropic) 3-D scans into five layers. Each dataset consisted six linear radial centered at fovea. The surfaces defining layers were identified composite image transforming segmentation...

purpose. To determine whether type 1 diabetes preferentially affects the inner retinal layers by comparing thickness of six in diabetic patients who have no or minimal retinopathy (DR) with those age- and sex-matched healthy controls. methods. Fifty-seven (n = 32) 25) DR underwent full ophthalmic examination, stereoscopic fundus photography, optical coherence tomography (OCT). After automated segmentation intraretinal OCT images, mean was calculated for retina fovea, pericentral area,...

Purpose.: To determine which retinal layers are most affected by diabetes and contribute to thinning of the inner retina investigate relationship between layer thickness (LT) duration, diabetic retinopathy (DR) status, age, glycosylated hemoglobin (HbA1c), sex individual, in patients with type 1 who have no or minimal DR. Methods.: Mean LT was calculated for individual after automated segmentation spectral domain-optical coherence tomography scans compared that control subjects. Multiple...

Purpose.: The purpose of this study was to determine whether diabetes type 2 causes thinning retinal layers as a sign neurodegeneration and investigate the possible relationship between duration mellitus, diabetic retinopathy (DR) status, age, sex, glycemic control (HbA1c). Methods.: Mean layer thickness calculated for following automated segmentation spectral domain optical coherence tomography images patients with no or minimal DR compared controls. To duration, HbA1c, multiple linear...

Optical coherence tomography (OCT) is becoming one of the most important modalities for noninvasive assessment retinal eye diseases. As number acquired OCT volumes increases, automating image analysis increasingly relevant. In this paper, a method automated characterization normal macular appearance in spectral domain (SD-OCT) reported together with general approach local abnormality detection. Ten intraretinal layers are first automatically segmented and 3-D dataset flattened to remove...

To determine the effect of age on thickness individual retinal layers, measured with spectral-domain optical coherence tomography (SD-OCT), in a population healthy Caucasians.One hundred and twenty subjects an ranging between 18 81 years were examined SD-OCT. Mean layer was calculated for seven fovea (region 1 9 Early Treatment Diabetic Retinopathy Study [ETDRS] regions); pericentral ring (ETDRS regions 2 to 5); peripheral 6 9) following automated segmentation using Iowa Reference Algorithm....

A novel splat feature classification method is presented with application to retinal hemorrhage detection in fundus images. Reliable of hemorrhages important the development automated screening systems which can be translated into practice. Under our supervised approach, color images are partitioned nonoverlapping segments covering entire image. Each segment, i.e., splat, contains pixels similar and spatial location. set features extracted from each describe its characteristics relative...

Glaucoma is the second leading ocular disease causing blindness due to gradual damage optic nerve and resultant visual field loss. Segmentations of disc cup neuroretinal rim can provide important parameters for detecting tracking this disease. The purpose study describe evaluate a method that automatically segment in spectral-domain 3-D OCT (SD-OCT) volumes. Four intraretinal surfaces were segmented using fast multiscale graph search algorithm. After surface segmentation, retina each scan...

Background: Spectral domain optical coherence tomography (SD-OCT) reveals retinal ganglion cell layer plus inner plexiform (GCL+IPL) and peripapillary nerve fiber (pRNFL) thinning in chronic optic injury. At presentation, swelling of the pRNFL confounds evaluation early axon loss. Objective: We studied whether GCL+IPL thins before pRNFL, trajectory loss relationship to vision. Methods: prospectively evaluated 33 eyes (study) with new neuritis, using perimetry SD-OCT investigative...

Purpose.: To determine the etiology and prognosis of visual acuity loss in idiopathic intracranial hypertension (IIH) at presentation to provide objective measures predict outcome. Methods.: A retrospective review 660 patients with IIH (2009–2013) identified 31 (4.7%) 48 eyes having best-corrected (BCVA) 20/25 or worse on initial presentation. Fundus photography, optical coherence tomography (OCT) optic disc macula, perimetry were used causes vision loss. Segmentation macula OCT was...

This paper proposes an algorithm to measure the width of retinal vessels in fundus photographs using graph-based segment both vessel edges simultaneously. First, simultaneous two-boundary segmentation problem is modeled as a two-slice, 3-D surface problem, which further converted into computing minimum closed set node-weighted graph. An initial generated from probability image. We use REVIEW database evaluate diameter measurement performance. The robust and estimates with subpixel accuracy....

Segmentation of multiple surfaces in medical images is a challenging problem, further complicated by the frequent presence weak boundary evidence, large object deformations, and mutual influence between adjacent objects. This paper reports novel approach to multi-object segmentation that incorporates both shape context prior knowledge 3-D graph-theoretic framework help overcome stated challenges. We employ an arc-based graph representation incorporate wide spectrum information through...

Purpose.: To evaluate the performance of an automated algorithm for determination cup and rim from close-to-isotropic spectral domain (SD) OCT images optic nerve head (ONH) compare to as determined by glaucoma experts stereo color photographs same eye. Methods.: Thirty-four consecutive patients with were included in study, ONH left eye was imaged SD-OCT photography on day. The segmented all volumes a novel voxel column classification algorithm, linear cup-to-disc (c/d) ratio determined....

To develop an automated approach for segmenting the neural canal opening (NCO) and cup at level of retinal pigment epithelium (RPE)/Bruch's membrane (BM) complex in spectral-domain optical coherence tomography (SD-OCT) volumes. investigate correspondence discrepancy between NCO-based metrics clinical disc margin on fundus photographs glaucoma subjects.SD-OCT scans corresponding stereo optic nerve head were obtained from 68 eyes 34 patients with or suspicion. Manual planimetry was performed...

To develop an automated method for the quantification of volumetric optic disc swelling in papilledema subjects using spectral-domain optical coherence tomography (SD-OCT) and to determine extent that such measurements correlate with Frisén scale grades (from fundus photographs) two-dimensional (2-D) peripapillary retinal nerve fiber layer (RNFL) total (TR) thickness from SD-OCT.A custom image-analysis algorithm was developed obtain circular RNFL thickness, TR volume SD-OCT volumes...

Purpose: To determine the frequency, patterns, associations, and biomechanical implications of retinal choroidal folds in papilledema due to idiopathic intracranial hypertension (IIH). Methods: Retinal were studied patients enrolled IIH Treatment Trial using fundus photography (n = 165 study eyes) spectral-domain optical coherence tomography (SD-OCT; n 125). We examined association between peripapillary shape, nerve fiber layer (RNFL) thickness, disc volume, Frisén grade, acuity, perimetric...

The separation of the retinal vessel network into distinct arterial and venous trees is high interest. We propose an automated method for identification in a color image by converting segmentation segment map identifying individual graph search. Orientation, width, intensity each are utilized to find optimal segments. separated labeled as primary or branches. utilize arterial-venous (AV) classification, based on properties vessels tree graph. applied our approach dataset 50 fundus images...

In this work, a multimodal approach is proposed to use the complementary information from fundus photographs and spectral domain optical coherence tomography (SD-OCT) volumes in order segment optic disc cup boundaries. The problem formulated as an optimization where optimal solution obtained using machine-learning theoretical graph-based method. particular, first photograph registered 2D projection of SD-OCT volume. Three in-region cost functions are designed random forest classifier...

The 3-D spectral-domain optical coherence tomography (SD-OCT) images of the retina often do not reflect true shape and are distorted differently along x y axes. In this paper, we propose a novel technique that uses thin-plate splines in two stages to estimate correct distinct axial artifacts SD-OCT images. method was quantitatively validated using nine pairs OCT scans obtained with orthogonal fast-scanning axes, where segmented surface compared after both datasets had been corrected. mean...

Purpose.: To determine relationships between spectral-domain optical coherence tomography (SD-OCT) derived regional damage to the retinal ganglion cell–axonal complex (RGC-AC) and visual thresholds for each location of Humphrey 24-2 field, in all stages open-angle glaucoma. Methods.: Patients with early, moderate, advanced glaucoma were recruited from a tertiary clinic. 9-field Spectralis SD-OCT acquired subject. Individual OCT volumes aligned, nerve fiber layer (NFL), cell inner plexiform...