Fully-automated atrophy segmentation in dry age-related macular degeneration in optical coherence tomography
Ontology highlight
ABSTRACT:
SUBMITTER: Derradji Y
PROVIDER: S-EPMC8575929 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background:Optical coherence tomography (OCT) is an innovative imaging technique that generates high-resolution intracoronary images. In the last few years, the need for more precise analysis regarding coronary artery disease to achieve optimal treatment has made intravascular imaging an area of primary importance in interventional cardiology. One of the main challenges in OCT image analysis is the accurate detection of lumen which is significant for the further prognosis. Method:In this research, we present a new approach to the segmentation of lumen in OCT images. The proposed work is focused on designing an efficient automatic algorithm containing the following steps: preprocessing (artifacts removal: speckle noise, circular rings, and guide wire), conversion between polar and Cartesian coordinates, and segmentation algorithm. Results:The implemented method was tasted on 667 OCT frames. The lumen border was extracted with a high correlation compared to the ground truth: 0.97 ICC (0.97-0.98). Conclusions:Proposed algorithm allows for fully automated lumen segmentation on optical coherence tomography images. This tool may be applied to automated quantitative lumen analysis.
| S-EPMC6327279 | biostudies-literature
Project description:PurposeTo compare the characteristics of eyes that had manual vs. automated segmentation of choroidal neovascular membrane (CNVM) using optical coherence tomography angiography (OCTA).MethodsAll patients with CNVM underwent OCTA using the Zeiss Angioplex Cirrus 5000. Slabs of the avascular outer retina, outer retina to choriocapillaris (ORCC) region and choriocapillaris were generated. Manual segmentation was done when there were significant segmentation artifacts. Presence of activity of CNVM was adjudged by the presence of subretinal fluid (SRF) on structural OCT and was compared to activity detected on en face OCTA slabs based on well-defined criteria.ResultsEighty-one eyes of 81 patients were recruited of which manual segmentation was required in 46 (57%). Eyes with automated segmentation had significantly more CNVM in the ORCC (75%) whereas those with manual segmentation had deeper CNVM (sub-RPE = 22%, intra-PED = 22%) (p<0.001). Twenty eyes (25%) were found to have active CNVM on both the structural OCT and OCTA while an additional 19 eyes were presumed to have active CNVM on OCTA alone. There was only modest concordance between disease activity detected using structural OCT and OCTA (Kappa = 0.47, 95% CI = 0.30 to 0.64).ConclusionsManual segmentation of OCTA is required in more than 50% eyes with CNVM and this progressively increases with increasing depth of CNVM location from the ORCC to below the RPE. There is moderate concordance between OCTA and structural OCT in determining CNVM activity.
| S-EPMC7775057 | biostudies-literature
Project description:PurposeStructural and compositional heterogeneity within drusen comprising lipids, carbohydrates, and proteins have been previously described. We sought to detect and define phenotypic patterns of drusen heterogeneity in the form of optical coherence tomography-reflective drusen substructures (ODS) and examine their associations with age-related macular degeneration (AMD)-related features and AMD progression.DesignRetrospective analysis in a prospective study.ParticipantsPatients with intermediate AMD (n = 349) enrolled in the multicenter Age-Related Eye Disease Study 2 (AREDS2) ancillary spectral-domain optical coherence tomography (SD OCT) study.MethodsBaseline SD OCT scans of 1 eye per patient were analyzed for the presence of ODS. Cross-sectional and longitudinal associations of ODS presence with AMD-related features visible on SD OCT and color photographs, including drusen volume, geographic atrophy (GA), and preatrophic features, were evaluated for the entire macular region. Similar associations were also made locally within a 0.5-mm-diameter region around individual ODS and corresponding control region without ODS in the same eye.Main outcome measuresPreatrophy SD OCT changes and GA, central GA, and choroidal neovascularization (CNV) from color photographs.ResultsFour phenotypic subtypes of ODS were defined: low reflective cores, high reflective cores, conical debris, and split drusen. Among the 349 participants, there were 307 eligible eyes and 74 (24%) had at least 1 ODS. The ODS at baseline were associated with (1) greater macular drusen volume at baseline (P < 0.001), (2) development of preatrophic changes at year 2 (P = 0.001-0.01), and (3) development of macular GA (P = 0.005) and preatrophic changes at year 3 (P = 0.002-0.008), but not development of CNV. The ODS at baseline in a local region were associated with (1) presence of preatrophy changes at baseline (P = 0.02-0.03) and (2) development of preatrophy changes at years 2 and 3 within the region (P = 0.008-0.05).ConclusionsOptical coherence tomography-reflective drusen substructures are optical coherence tomography-based biomarkers of progression to GA, but not to CNV, in eyes with intermediate AMD. Optical coherence tomography-reflective drusen substructures may be a clinical entity helpful in monitoring AMD progression and informing mechanisms in GA pathogenesis.
| S-EPMC5125946 | biostudies-literature
Project description:PurposeTo benchmark the human and machine performance of spectral-domain (SD) and swept-source (SS) optical coherence tomography (OCT) image segmentation, i.e., pixel-wise classification, for the compartments vitreous, retina, choroid, sclera.MethodsA convolutional neural network (CNN) was trained on OCT B-scan images annotated by a senior ground truth expert retina specialist to segment the posterior eye compartments. Independent benchmark data sets (30 SDOCT and 30 SSOCT) were manually segmented by three classes of graders with varying levels of ophthalmic proficiencies. Nine graders contributed to benchmark an additional 60 images in three consecutive runs. Inter-human and intra-human class agreement was measured and compared to the CNN results.ResultsThe CNN training data consisted of a total of 6210 manually segmented images derived from 2070 B-scans (1046 SDOCT and 1024 SSOCT; 630 C-Scans). The CNN segmentation revealed a high agreement with all grader groups. For all compartments and groups, the mean Intersection over Union (IOU) score of CNN compartmentalization versus group graders' compartmentalization was higher than the mean score for intra-grader group comparison.ConclusionThe proposed deep learning segmentation algorithm (CNN) for automated eye compartment segmentation in OCT B-scans (SDOCT and SSOCT) is on par with manual segmentations by human graders.
| S-EPMC6697318 | biostudies-literature
Project description:PurposeTo identify precursors of macular atrophy (MA) and of fibrotic scar (FS) in eyes treated with anti-vascular endothelial growth factor through pixel-mapping analysis of baseline optical coherence tomography (OCT).MethodsDesign: Cross-sectional analysis.SettingMulticenter clinical trial.Patient population68 eyes from the Comparison of Age-Related Macular Degeneration Treatments Trials.InterventionTreatment with anti-vascular endothelial growth factor agents.Main outcome measureThe percentage of MA or FS pixels with each OCT feature at baseline, and the odds ratio for baseline pixels with an OCT feature to develop MA or FS.ResultsRetinal pigment epithelium atrophy and photoreceptor loss on OCT were highly predictive of MA at that location at years 2 and 5 (P < .0001), but accounted for only 22.5% of the ensuing atrophy at year 2 and less at year 5. Among pixels of MA at year 2, 78% were preceded by thick drusen, 54% by subretinal macular neovascularization (MNV), and 22.5% by no detectable OCT features. MNV, subretinal hyperreflective material, pigment epithelial detachment, intraretinal fluid, and sub-retinal pigment epithelium fluid were predictive of FS at that location (P values <.05). More than 75% of the pixels of FS at years 2 and 5 were preceded by pixels of baseline MNV.ConclusionsMost pixels of FS were preceded by components of neovascularization. Although one-quarter of MA was accounted for by pre-existing evidence of atrophy on OCT alone, the development of MA in areas of thick drusen, areas with and without subretinal MNV lesion, and areas without detectable OCT precursors argues that the development of MA is multifactorial and may follow, in part, a non-neovascular pathway.
| S-EPMC7979472 | biostudies-literature
Project description:PurposeTo assess the quality of optical coherence tomography (OCT) grading algorithms for retinal biomarkers of age-related macular degeneration (AMD).MethodsFollowing a systematic review of the literature data on detection and quantification of AMD retinal biomarkers by available algorithms were extracted and descriptively synthesized. Algorithm quality was assessed using a modified version of the Quality Assessment of Diagnostic Accuracy Studies 2 checklist with a focus on accuracy against established reference standards and risk of bias.ResultsThirty five studies reporting computer-aided diagnosis (CAD) tools for qualitative analysis or algorithms for quantitative analysis were identified. Compared with manual assessment in reference standards correlation coefficients ranged from 0.54 to 0.97 for drusen, 0.80 to 0.98 for geographic atrophy (GA), and 0.30 to 0.98 for intra- or subretinal fluid and pigment epithelial detachment (PED) detection by automated algorithms. CAD tools achieved area under the curve (AUC) values of 0.94 to 0.99, sensitivity of 0.90 to 1.00, and specificity of 0.89 to 0.92.ConclusionsAutomated analysis of AMD biomarkers on OCT is promising. However, most of the algorithm validation was performed in preselected patients, exhibiting the targeted biomarker only. In addition, type and quality of reported algorithm validation varied substantially.Translational relevanceThe development of algorithms for combined, simultaneous analysis of multiple AMD biomarkers including AMD staging and the agreement on standardized validation procedures would be of considerable translational value for the clinician and the clinical researcher.
| S-EPMC5516568 | biostudies-literature
Project description:Spectral domain optical coherence tomography can be used to measure both choroidal thickness and drusen load. The authors conducted an exploratory study using spectral domain optical coherence tomography to determine if a correlation between choroidal thickness and drusen load exists in patients with dry age-related macular degeneration.Forty-four patients with dry age-related macular degeneration were recruited. The drusen area and volume were determined using the automated software algorithm of the spectral domain optical coherence tomography device, and choroidal thickness was measured using enhanced depth imaging. Correlations were determined using multivariable and univariable analyses.The authors found an inverse correlation between choroidal thickness and drusen load (r = -0.35, P = 0.04). Drusen load was also correlated with visual acuity (r = 0.32, P = 0.04). A correlation between choroidal thickness and visual acuity was suggested (r = -0.22, P = 0.21).Spectral domain optical coherence tomography can be used to assess the correlation between drusen load and choroidal thickness, both of which show a relationship with visual acuity. The measurement of these outcomes may serve as important outcome parameters in routine clinical care and in clinical trials for patients with dry age-related macular degeneration.
| S-EPMC3947382 | biostudies-other
Project description:PurposeTo investigate the thickness of retinal layers and association with final visual acuity using spectral-domain optical coherence tomography (SD-OCT) in macular area of macula-off rhegmatogenous retinal detachment (RRD) patients after a successful macular re-attachment.MethodsIn retrospective study, a total 24 eyes with macula-off RRD were enrolled. All patients underwent vitrectomy to repair RRD. Outer plexiform layer (OPL), outer nuclear layer (ONL), photoreceptor layer (PR), retinal pigment epithelium (RPE) thicknesses were measured by the Spectralis (Heidelberg Engineering, Heidelberg, Germany) SD-OCT with automated segmentation software. The relationship between the thicknesses of each retinal layer and postoperative logarithm of the minimum angle of resolution scale (LogMAR) visual acuity was analyzed.ResultsOPL and RPE thicknesses were not significantly different between the retinal detachment eyes and fellow eyes (P = 0.839, 0.999, respectively). The ONL and photoreceptor thickness were significantly thinner in the retinal detachment eyes (P <0.001 and 0.001, respectively). In the univariate regression analysis, preoperative best corrected visual acuity (BCVA), ONL thickness and photoreceptor thickness showed association with the postoperative BCVA (P = 0.003, <0.001 and 0.024, respectively). In final multiple linear regression model, ONL thickness was the only variable significantly associated with postoperative BCVA (P = 0.044).ConclusionsSegmented ONL and photoreceptor thickness of retinal detachment eyes were significantly thinner than fellow eyes. Segmental analysis of the retinal layer in macular region may provide valuable information for evaluation RRD. And ONL thickness can be used as a potential biomarker to predict visual outcome after RRD repair.
| S-EPMC5937759 | biostudies-literature
Project description:Over the past two decades a significant number of OCT segmentation approaches have been proposed in the literature. Each methodology has been conceived for and/or evaluated using specific datasets that do not reflect the complexities of the majority of widely available retinal features observed in clinical settings. In addition, there does not exist an appropriate OCT dataset with ground truth that reflects the realities of everyday retinal features observed in clinical settings. While the need for unbiased performance evaluation of automated segmentation algorithms is obvious, the validation process of segmentation algorithms have been usually performed by comparing with manual labelings from each study and there has been a lack of common ground truth. Therefore, a performance comparison of different algorithms using the same ground truth has never been performed. This paper reviews research-oriented tools for automated segmentation of the retinal tissue on OCT images. It also evaluates and compares the performance of these software tools with a common ground truth.
| S-EPMC5025289 | biostudies-literature
Project description:PurposeDescribe qualitative spectral-domain optical coherence tomography (SD-OCT) characteristics of eyes classified as intermediate age-related macular degeneration (nonadvanced AMD) from Age-Related Eye Disease Study 2 (AREDS2) color fundus photography (CFP) grading.DesignProspective cross-sectional study.ParticipantsWe included 345 AREDS2 participants from 4 study centers and 122 control participants who lack CFP features of intermediate AMD.MethodsBoth eyes were imaged with SD-OCT and CFP. The SD-OCT macular volume scans were graded for the presence of 5 retinal, 5 subretinal, and 4 drusen characteristics. In all, 314 AREDS2 participants with ?1 category-3 AMD eye and all controls each had 1 eye entered into SD-OCT analysis, with 63 eyes regraded to test reproducibility.Main outcome measuresWe assessed SD-OCT characteristics at baseline.ResultsIn 98% of AMD eyes, SD-OCT grading of all characteristics was successful, detecting drusen in 99.7%, retinal pigment epithelium (RPE) atrophy/absence in 22.9%, subfoveal geographic atrophy in 2.5%, and fluid in or under the retina in 25.5%. Twenty-eight percent of AMD eyes had characteristics of possible advanced AMD on SD-OCT. Two percent of control eyes had drusen on SD-OCT. Vision loss was not correlated with foveal drusen alone, but with foveal drusen that were associated with other foveal pathology and with overlying focal hyperreflectivity. Focal hyperreflectivity over drusen, drusen cores, and hyper- or hyporeflectivity of drusen were also associated with RPE atrophy.ConclusionsMacular pathologies in AMD can be qualitatively and reproducibly evaluated with SD-OCT, identifying pathologic features that are associated with vision loss, RPE atrophy, and even possibly the presence of advanced AMD not apparent on CFP. Qualitative and detailed SD-OCT analysis can contribute to the anatomic characterization of AMD in clinical studies of vision loss and disease progression.Financial disclosure(s)Proprietary or commercial disclosure may be found after the references.
| S-EPMC3536919 | biostudies-literature