Dataset Information

Macular Ischemia Quantification Using Deep-Learning Denoised Optical Coherence Tomography Angiography in Branch Retinal Vein Occlusion.

ABSTRACT:

Purpose

To examine whether deep-learning denoised optical coherence tomography angiography (OCTA) images could enhance automated macular ischemia quantification in branch retinal vein occlusion (BRVO).

Methods

This retrospective, single-center, cross-sectional study enrolled 74 patients with BRVO and 46 age-matched healthy subjects. The severity of macular ischemia was graded as mild, moderate, or severe. Denoised OCTA images were produced using a neural network model. Quantitative parameters derived from denoised images, including vessel density and nonperfusion area, were compared with those derived from the OCTA machine. The main outcome measures were correlations between quantitative parameters, and areas under receiver operating characteristic curves (AUCs) in classifying the severity of the macular ischemia.

Results

The vessel density and nonperfusion area from denoised images were correlated strongly with the corresponding parameters from machine-derived images in control eyes and BRVO eyes with mild or moderate macular ischemia (all P < 0.001). However, no such correlation was found in eyes with severe macular ischemia. The vessel density and nonperfusion area from denoised images had significantly larger area under receiver operating characteristic curve than those derived from the original images in classifying moderate versus severe macular ischemia (0.927 vs 0.802 [P = 0.042] and 0.946 vs 0.797, [P = 0.022], respectively). There were no significant differences in the areas under receiver operating characteristic curve between the denoised images and the machine-derived parameters in classifying control versus BRVO, and mild versus moderate macular ischemia.

Conclusions

A neural network model is useful for removing speckle noise on OCTA images and facilitating the automated grading of macular ischemia in eyes with BRVO.

Translational relevance

Deep-learning denoised optical coherence tomography angiography images could enhance automated macular ischemia quantification.

SUBMITTER: Yeung L

PROVIDER: S-EPMC8212432 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundRetinal vein occlusion (RVO) is the second most common vision-threatening retinal vascular disease. Intravitreal dexamethasone implant has been applied to treat macular edema secondary to RVO (RVO-ME). However, the alteration of morphologic features detected with optical coherence tomography angiography (OCTA) has not been fully studied in RVO-ME patients before and after the treatment.ObjectiveThis study is aimed at identifying potential therapeutic targets in RVO with integrative bioinformatic analysis and compares the OCTA characteristics alterations in patients with RVO-ME receiving injection of dexamethasone intravitreal implant.MethodsBioinformatic analysis was analyzed in GSE101398 dataset from the Gene Expression Omnibus database. Multiple functional enrichment analyses were performed, and protein-protein interaction network was constructed to visualize the key node genes. Eleven eyes with RVO-ME were examined with OCTA before and after intravitreal dexamethasone implant. The OCTA parameters, including macular thickness, vessel density, foveal avascular zone parameters, the number of hyperreflective foci (HRF), area of cystoid edema, and subretinal fluid (SRF), were compared. The correlation was analyzed between best-corrected visual acuity (BCVA) and OCTA parameters.ResultsA total of 79 differentially expressed genes were identified. Functional enrichment analyses revealed the enriched inflammatory events in RVO. In RVO-ME, Pearson correlation revealed that baseline BCVA was positively correlated with the area of SRF and central macular thickness, while no correlation was detected between baseline BCVA and HRF number or the area of cystoid edema. The visual acuity improved, and the central macular thickness was decreased after intravitreal dexamethasone implant injection. Besides, the number of HRF, the area of cystoid edema, and SRF were significantly alleviated after dexamethasone intravitreal injection.ConclusionRetinal inflammation plays a crucial role in RVO pathogenesis. The imaging biomarkers of RVO including Müller glial intracellular edema, and retinal pigment epithelium dysfunction, could be assessed in OCTA and attenuated by intravitreal dexamethasone implant effectively.

Project description:IntroductionIt is reported that eyes with a branch retinal artery occlusion (BRAO) had normal full-field electroretinography (ERG) but the response of the multifocal electroretinography (mfERG) was reduced in the area of the arterial occlusion. Optical coherence tomography angiography (OCTA) is a recently appeared modality that can evaluate microvascularizations in different retinal layers and in different regions of the retina. The purpose of this study was to determine the density of the microcirculation and the function of the macular area of eyes with BRAO, and to determine whether they are significantly correlated.MethodsThe OCTA and mfERG findings of 7 eyes of 6 patients (3 men, 3 women) were studied. The mean age of the patients was 71.7±10.6 years. The OCTA examinations were made with volume scans of 3 × 3 and 6 × 6 mm squares centered on the fovea. The macular vessel densities (mVD) in the superficial retinal layer (SRL) and deep retinal layer (DRL) were measured for the superior and inferior halves of 3 × 3 and 6 × 6 mm diameter concentric circles. The mfERGs were recorded with targets set to stimulate the focal areas of the retina corresponding to the areas examined by OCTA.ResultsThe OCTA examinations showed that the mVD of the 3 mm concentric circle in the SRL was significantly lower on the affected side than on the unaffected side (P = 0.022). No such difference was observed in the DRL. The N1 amplitude of the 20.2° concentric circle and the N1-P1 amplitude of the 10.1° concentric circle of the mfERGs were significantly smaller on the affected side than on the unaffected side (P = 0.047 and 0.031). A significant positive correlation was found between the mVD of the 6 mm concentric circle in the DRL and the P1-N2 amplitude of the 20.2° concentric circle (ρ = -0.929 and p = 0.003).DiscussionThese findings indicate that OCTA images may be able to show changes in the density of the retinal macular microcirculation, and the mfERGs may be able to show alterations in the function of the macular area of the eyes with BRAO. A layer-by-layer analysis of the local retinal microcirculation and function should help in determining the pathogenesis of BRAO.

Project description:PurposeTo determine the repeatability of superficial vessel density measurements using Spectral domain Ocular coherence tomography angiography(SD-OCTA) in patients diagnosed with retinal vein occlusion(RVO).DesignProspective observational study.SubjectsPatients who visited our retinal clinic from August 2017 to August 2018, diagnosed with RVO were recruited for the study.MethodsTwo consecutive 3×3 mm pattern scans were performed using the Cirrus HD-OCT 5000 along with AngioPlex software (Carl Zeiss Meditec) in each eye by single skilled examiner. All scans were analyzed using en face OCTA images to measure vessel density (VD) automatically. For further analysis of the effect of central macular thickness(CMT), eyes were divided into two groups according to CMT of 400μm (Group 1: CMT > 400μm, Group 2: CMT < 400μm). To identify factors affecting the repeatability of VD measurements, linear regression analyses were conducted for the coefficient of variation (CV) of VD by investigating demographics and ocular variables.Main outcome measuresThe intraclass correlation coefficient (ICC), coefficient of variation (CV) of VD measurements.ResultsA total of 57 eyes from 57 patients were examined: 35 eyes with BRVO and 22 eyes with CRVO. In all 57 eyes with RVO, the ICC and CV of the full VD(VD of 3mm diameter circle) were 0.800 and 10.61%, respectively. Univariate analyses showed that the mean CMT (B, 0.001; p<0.001) and mean ganglion cell-Inner plexiform layer (GC-IPL) thickness (B, -0.002; p = 0.020) were significant factors that affected the repeatability. Multivariate analyses of these two factors showed that only mean CMT was a significant factor. The ICC and CV of the full VD in group 1 (CMT > 400μm) were 0.348 and 22.55% respectively. In group 2 (CMT < 400μm), the ICC and CV of the full VD were 0.910 and 7.76%, respectively.ConclusionsThe repeatability of VD measurement in eyes with RVO was reasonably comparable to previous studies. Repeatability of VD measurement was significantly affected by central macular thickness.