Efecto de la acetazolamida en la vasculatura retiniana y coroidea de la mácula y el disco óptico mediante angiografía OCT / The effect of acetazolamide on the retinal and choroidal vasculature of the macula and the optic disc using OCT angiography

Introducción y objetivos Investigar el efecto de la acetazolamida (AZ) sobre la microvasculatura ocular retiniana y coroidea en la mácula y los capilares peripapilares radiales (CPR) del disco óptico con angiografía-OCT (OCTA). Materiales y métodos Estudio transversal observacional de 9meses de duración. Se reclutaron 45 ojos de 45 participantes sanos que se sometieron a cirugía de cataratas. Se comparó la densidad de vasos (DV) de la retina macular y la coriocapilar (CC) y la DV de la CPR en la zona del disco óptico antes y 60 min después de administrar 250mg de AZ por vía oral. También se midieron la presión intraocular (PIO) y la presión arterial (PA) sistémica antes de cada exploración. Resultado La edad media era de 73,1±6,9 años. La densidad de vasos (DV) en el plexo capilar superficial (PCS) y profundo (PCP) de la retina y la CC en el área macular no mostraron cambios significativos (p>0,5, para todos los parámetros). La DV en los CPR no mostró cambios significativos con la AZ (p>0,5, para todos los parámetros). El grosor foveal y parafoveal aumentó de 248,98 (± 23,89) a 250,33 (± 23,74) y de 311,62 (± 16,53) a 311,98 (± 16,38) (p<0,001 y p=0,046), respectivamente. La PIO disminuyó de 13,2 (± 3,0) mmHg a 11,8 (± 3,2) mmHg (p<0,001), mientras que la PA sistólica y diastólica disminuyó de 144,8 (± 21,8) a 137,7 (± 19,0) y de 80,0 (± 12,7) a 76,2 (± 11,7) (p=0,021 y p=0,030), respectivamente. Conclusiones Las imágenes de OCTA no revelaron cambios significativos en la VD del disco óptico ni en el VD de la retina y la coroides en la mácula con AZ oral una hora después de su administración en participantes por lo demás sanos que se sometieron a cirugía de cataratas (AU)

Introduction and objectives To investigate the effect of acetazolamide (AZ) on the retinal and choroidal ocular microvasculature in the macula and radial peripapillary capillaries (RPC) of the optic disc with OCT Angiography (OCTA). Materials and method Nine-month observational cross-sectional study. Forty-five eyes from 45 healthy participants who underwent cataract surgery were recruited. Macular retina and choriocapillaris vessel density (VD) and RPC VD in the optic disc area were compared before and 60minutes after 250mg acetazolamide per os. Intraocular pressure (IOP) and systemic blood pressure (BP) were also measured before each scan. Result Mean age was 73.1±6.9 years. VDs in the superficial (SCP) and deep (DCP) capillary plexus of the retina and the choriocapillaris (CC) in the macular area showed no significant change (p>0.5, for all parameters). VD in the RPC showed no significant change with AZ (p>0.5, for all parameters). Foveal and parafoveal thickness increased from 248.98 (±23.89) to 250.33 (±23.74) and from 311.62 (±16.53) to 311.98 (±16.38) (p<0.001 and p=0.046), respectively. IOP decreased from 13.2 (±3.0) mmHg to 11.8 (±3.2) mmHg (p<0.001), while systolic and diastolic BP decreased from 144.8 (±21.8) to 137.7 (±19.0) and from 80.0 (±12.7) to 76.2 (±11.7) (p=0.021 and p=0.030), respectively. Conclusion OCTA imaging did not reveal any significant changes in the VD of the optic disc or the retinal and choroidal VD in the macula with oral AZ one hour after its administration in otherwise healthy participants who underwent cataract surgery (AU)

Clinical identification of optic disk vascular alteration in glaucoma.

Background: Several characteristic vascular changes can be observed in the glaucomatous eyes, including changes in the vessel configuration and caliber, presence of collateral vessel on disk, and disk hemorrhage. Purpose: This video describes characteristic vascular changes in the optic nerve head, which can be observed on clinical examination in the glaucomatous eyes, and useful teaching points to identify the same. Synopsis: In glaucoma, as the optic cup enlarges, the normal pattern and course of retinal vessels on the optic disk are altered and show characteristic changes. Identification of these changes provides a clue to the presence of cupping. Highlights: In this video, the vascular changes and its identification in the glaucomatous disc are described, which would be useful to the residents. Video link: https://youtu.be/2eINumBx33E.

APSified OCT-angiography analysis: Macula vessel density in healthy eyes during office hours.

PURPOSE: Optical coherence tomography angiography (OCT-A) can visualize retinal capillary microcirculation non-invasively. In order to investigate potential factors influencing OCT-A diagnostics, the aim of the present study was to determine circadian changes in macular vessel density (VD) in healthy adults during office hours, considering axial length (AL) and subfoveal choroidal thickness (CT). METHODS: In the prospective study 30 eyes of 30 healthy subjects (mean age 28.7 ± 11.8, range 19-60 years) were recruited who underwent repeated measurements of AL, subfoveal CT and three-layer macula VD (superficial vascular plexus (SVP), intermediate capillary plexus (ICP) and deep capillary plexus (DCP)) on a single day at three predetermined timepoints (9 AM, 3 PM, and 9 PM). For better intra- and interindividual scan comparability, the new Anatomic Positioning System function (APS, part of Glaucoma Module Premium Edition [GMPE], Heidelberg Engineering, Germany) allowing analysis of identical retinal areas, was used for quantitative OCT-A analysis. RESULTS: Overall mean macula VD was unchanged during office hours in SVP, ICP and DCP, respectively (p>0.05). In addition, AL and CT showed no statistically significant changes over time (p>0.05). Rather, a large interindividual variance of VD with different peak time was observed. Contrary to the overall data, sectorial VD changed in dependency of office hours in all layers with an increase of VD in SVP between 9 AM and 9 PM (p = 0.003), in ICP between 3 PM and 9 PM (p = 0.000), in DCP between 9 AM and 9 PM (p = 0.048), and 3 PM and 9 PM (p = 0.000), respectively. CONCLUSION: Overall mean macula VD, subfoveal CT and AL tended not to show statistically significant changes over time in this cohort, whereas a regional analysis of VD did. Therefore, a circadian influence on capillary microcirculation should be kept in mind. Moreover, the results highlight the importance of a more detailed analysis of VD in different sectors and different vascular layers. In addition, the pattern of diurnal variation could vary inter-individually, thus a patient-specific fluctuation pattern would need to be considered when evaluating these parameters in clinical practice.

Correlation Between Retinal Vessel Diameters and Uveitis Activity.

Purpose: To assess retinal vein and artery diameters during active and inactive intraocular inflammation in eyes with uveitis. Methods: Color fundus photographs and clinical data of eyes with uveitis collected during two visits (active disease [i.e., T0] and inactive stage [i.e., T1]) were reviewed. The images were semi-automatically analyzed to obtain the central retina vein equivalent (CRVE) and central retina artery equivalent (CRAE). Changes of CRVE and CRAE from T0 to T1 were calculated, and their possible correlation with clinical data, including age, gender, ethnicity, uveitis etiology, and visual acuity, were investigated. Results: Eighty-nine eyes were enrolled in the study. Both CRVE and CRAE reduced from T0 to T1 (P < 0.0001 and P = 0.01, respectively), with active inflammation being able to influence the CRVE and CRAE (P < 0.0001 and P = 0.0004, respectively) after accounting for all other variables. The degree of venular (∆V) and arteriolar (∆A) dilation was influenced only by time (P = 0.03 and P = 0.04, respectively). Best-corrected visual acuity was influenced by time and ethnicity (P = 0.003 and P = 0.0006). Conclusions: CRVE and CRAE are increased in eyes with active intraocular inflammation regardless of the type of uveitis, and they decrease when the inflammation wears off.

Different scan areas affect the detection rates of diabetic retinopathy lesions by high-speed ultra-widefield swept-source optical coherence tomography angiography.

Introduction: The study aimed to determine the effect of the scanning area used for high-speed ultra-widefield swept-source optical coherence tomography angiography (SS-OCTA) on the detection rate of diabetic retinopathy (DR) lesions. Methods: This prospective, observational study involved diabetic patients between October 2021 and April 2022. The participants underwent a comprehensive ophthalmic examination and high-speed ultra-widefield SS-OCTA using a 24 mm × 20 mm scanning protocol. A central area denoted as "12 mm × 12 mm-central" was extracted from the 24 mm × 20 mm image, and the remaining area was denoted as "12 mm~24mm-annulus." The rates of detection of DR lesions using the two scanning areas were recorded and compared. Results: In total, 172 eyes (41 eyes with diabetes mellitus without DR, 40 eyes with mild to moderate non-proliferative diabetic retinopathy (NPDR), 51 eyes with severe NPDR, and 40 eyes with proliferative diabetic retinopathy (PDR) from 101 participants were included. The detection rates of microaneurysms (MAs), intraretinal microvascular abnormalities (IRMAs), and neovascularization (NV) for the 12 mm × 12 mm central and 24 mm × 20 mm images were comparable (p > 0.05). The detection rate of NPAs for the 24 mm × 20 mm image was 64.5%, which was significantly higher than that for the 12 mm × 12 mm central image (52.3%, p < 0.05). The average ischemic index (ISI) was 15.26% for the 12 mm~24mm-annulus, which was significantly higher than that for the 12 mm × 12 mm central image (5.62%). Six eyes had NV and 10 eyes had IRMAs that only existed in the 12 mm~24mm-annulus area. Conclusions: The newly developed high-speed ultra-widefield SS-OCTA can capture a 24 mm × 20 mm retinal vascular image during a single scan, which improves the accuracy of detecting the degree of retinal ischemia and detection rate of NV and IRMAs.

Evaluation of retinal microcirculation alterations using optical coherence tomography angiography in patients with hyperopia ametropic amblyopia: A case-control study.

Given that there are controversial findings regarding vessel density in amblyopia, we quantified retinal microcirculation using optical coherence tomography angiography and compared it between hyperopic ametropic amblyopia eyes and age-matched control eyes. This case-control study was conducted from March 2021 to March 2022 at the Affiliated Eye Hospital of Nanchang University, Nanchang, China. Both groups included 72 eyes. Foveal avascular zone area, circularity and perimeter, perfusion density and vessel density of macular superficial retinal capillary plexus, macular thickness, macular volume, peripapillary retinal nerve fiber layer thickness, and ganglion cell-inner plexiform layer thickness were compared between hyperopia ametropic amblyopia eyes and age-matched control eyes. Additionally, best-corrected visual acuity, maximum corneal curvature, minimum corneal curvature, and anterior chamber depth were measured. In the hyperopia ametropic amblyopia eyes and control eyes, vessel density was 7.51 ± 2.13 and 9.91 ± 2.71 mm-1 in the central, 17.20 ± 1.38 and 18.25 ± 1.37 mm-1 in the inner, and 17.90 ± 0.88 and 18.43 ± 0.97 mm-1 in the full regions, respectively. The perfusion densities were 0.17 ± 0.06 and 0.23 ± 0.07 in the central, 0.41 ± 0.05 and 0.44 ± 0.03 in the inner, and 0.44 ± 0.03 and 0.46 ± 0.02 in the full regions, respectively. The central macular thicknesses of hyperopia ametropic amblyopia and control eyes were 240.04 ± 20.11 and 235.08 ± 24.41 µm, respectively. Foveal avascular zone perimeter and circularity (P < .043 and P = .001) significantly differed between the 2 groups. Hyperopia ametropic amblyopia eyes showed lower appreciably in vessel and perfusion densities, which could be one of the major pathophysiological mechanisms of hyperopia ametropic amblyopia and provide a new direction for the diagnosis and treatment of amblyopia.

Neural Networks Application for Accurate Retina Vessel Segmentation from OCT Fundus Reconstruction.

The use of neural networks for retinal vessel segmentation has gained significant attention in recent years. Most of the research related to the segmentation of retinal blood vessels is based on fundus images. In this study, we examine five neural network architectures to accurately segment vessels in fundus images reconstructed from 3D OCT scan data. OCT-based fundus reconstructions are of much lower quality compared to color fundus photographs due to noise and lower and disproportionate resolutions. The fundus image reconstruction process was performed based on the segmentation of the retinal layers in B-scans. Three reconstruction variants were proposed, which were then used in the process of detecting blood vessels using neural networks. We evaluated performance using a custom dataset of 24 3D OCT scans (with manual annotations performed by an ophthalmologist) using 6-fold cross-validation and demonstrated segmentation accuracy up to 98%. Our results indicate that the use of neural networks is a promising approach to segmenting the retinal vessel from a properly reconstructed fundus.

Optical Coherence Tomography Angiography Analysis Toolbox: A Repeatable and Reproducible Software Tool for Quantitative Optical Coherence Tomography Angiography Analysis.

BACKGROUND AND OBJECTIVE: The purpose of this article is to demonstrate the optical coherence tomography angiography (OCTA) Analysis Toolkit (OAT), a custom-designed software package, as a repeatable and reproducible tool for computing OCTA metrics across different devices. MATERIALS AND METHODS: Fourteen participants were imaged using three devices. Foveal avascular zone, vessel index, vessel length index, and vessel diameter index were calculated using the OAT. Repeatability and reproducibility were assessed using the coefficient of variation and interclass correlation coefficient (ICC). RESULTS: Analysis of identical images demonstrated perfect levels of repeatability for all metrics (coefficient of variation 0%), which was a consequence of the software being deterministic (ie, producing the same outputs for the same inputs). Foveal avascular zone ICC values were in the excellent-to-good range (ICC > 0.6) for all devices. All values for vessel index (VI), vessel length index, and vessel diameter index fell in the good-to-fair (ICC > 0.4) or excellent-to-good range, except for vessel index analysis in the Cirrus device (ICC = 0.34). CONCLUSIONS: The OAT appears to be a reliable tool that may enable comparison between OCTA data sets acquired on different imaging instruments, thereby facilitating a more consistent approach to OCTA analysis. [Ophthalmic Surg Lasers Imaging Retina 2023;54:114-122.].

MINet: Multi-scale input network for fundus microvascular segmentation.

Vessel segmentation in fundus images is a key procedure in the diagnosis of ophthalmic diseases, which can play a role in assisting doctors in diagnosis. Although current deep learning-based methods can achieve high accuracy in segmenting fundus vessel images, the results are not satisfactory in segmenting microscopic vessels that are close to the background region. The reason for this problem is that thin blood vessels contain very little information, with the convolution operation of each layer in the deep network, this part of the information will be randomly lost. To improve the segmentation ability of the small blood vessel region, a multi-input network (MINet) was proposed to segment vascular regions more accurately. We designed a multi-input fusion module (MIF) in the encoder, which is proposed to acquire multi-scale features in the encoder stage while preserving the microvessel feature information. In addition, to further aggregate multi-scale information from adjacent regions, a multi-scale atrous spatial pyramid (MASP) module is proposed. This module can enhance the extraction of vascular information without reducing the resolution loss. In order to better recover segmentation results with details, we designed a refinement module, which acts on the last layer of the network output to refine the results of the last layer of the network to get more accurate segmentation results. We use the HRF, CHASE_DB1 public dataset to validate the fundus vessel segmentation performance of the MINet model. Also, we merged these two public datasets with our collected Ultra-widefield fundus image (UWF) data as one dataset to test the generalization ability of the model. Experimental results show that MINet achieves an F1 score of 0.8324 on the microvessel segmentation task, achieving a high accuracy compared to the current mainstream models.

Asymmetry of Peripapillary Retinal Blood Vessel and Retinal Nerve Fiber Layer Thickness Between Healthy Right and Left Eyes.

Purpose: The purpose of this study was to determine if there is asymmetry in retinal blood vessel (RBV) position and thickness between right and left eyes (R-L) and evaluate whether R-L asymmetry in RBV thickness is related to R-L asymmetry of retinal nerve fiber layer thickness (RNFLT). Methods: We analyzed peripapillary circle scan optical coherence tomography (OCT) examinations from healthy White subjects to measure RNFLT and RBV thickness and position relative to the fovea to Bruch's membrane opening axis, for all visible RBV. The R-L asymmetries of RNFLT and RBV thickness were computed for each A-scan. Four major vessels (superior temporal artery [STA] and superior temporal vein [STV], inferior temporal artery [ITA], and vein [ITV]) were identified using infrared images. Results: We included 219 individuals. The mean (standard deviation) number of RBV measured per eye was 15.0 (SD = 2.2). The position of the STV and STA was more superior in left eyes than in right eyes, by 2.4 degrees and 3.7 degrees, respectively (P < 0.01). There was no region with significant R-L asymmetry in RBV thickness. RNFLT was thicker in right eyes in the temporal superior region and thicker in left eyes in the superior and nasal superior regions, with the asymmetry profile resembling in a "W" shape. This shape was also present in post hoc analyses in two different populations. The R-L asymmetries of RBV and RNFLT at each A-scan were not significantly associated (P = 0.37). Conclusions: There is little R-L asymmetry in RBV, and it is not related to RNFLT asymmetry. This study suggests that R-L RNFLT asymmetry is due to factors other than RBV.

Analyses of Foveal Avascular Zone in Patients with General Blunt Ocular Trauma Using Optical Coherence Tomography Angiography.

PURPOSE: To investigate the effect of blunt ocular trauma (BOT) on foveal circulation, and in particular the foveal avascular zone (FAZ), using optical coherence tomography angiography (OCTA). METHODS: This retrospective study consisted of 96 eyes (48 traumatized eyes and 48 nontraumatized eyes) from 48 subjects with BOT. We analyzed the FAZ area of deep capillary plexus (DCP) and superficial capillary plexus (SCP) immediately after BOT and at 2 weeks after BOT. We also evaluated the FAZ area of DCP and SCP in patients with and without blowout fracture (BOF). RESULTS: There were no significant differences in FAZ area between traumatized and nontraumatized eyes at DCP and SCP in the initial test. In traumatized eyes, the FAZ area at SCP was significantly reduced on follow-up when compared to initial test (p = 0.01). In case of eyes with BOF, there was no significant differences in FAZ area between traumatized and nontraumatized eyes at DCP and SCP on initial test. No significant difference of FAZ area was found on follow-up relative to the initial test, whether in the DCP or SCP. In case of eyes without BOF, there was no significant differences of FAZ area between traumatized and nontraumatized eyes at DCP and SCP in initial test. Also, no significant difference of FAZ area at DCP was found on follow-up test compared to initial test. However, the FAZ area at SCP was significantly reduced in follow-up test compared with that in the initial test (p = 0.04). CONCLUSIONS: Temporary microvascular ischemia occurs in the SCP of patients after BOT. Patients should be warned of transient ischemic changes that may occur after trauma. OCTA can provide useful information regarding the subacute changes in the FAZ at SCP after BOT, even without evident findings of structural damage on fundus examination.

OCTA biomarkers in adults aged 50 and above: a prospective and cross-sectional community-based study.

BACKGROUND/AIMS: To assess the normative values and parameters of optical coherence tomography angiography (OCTA) influencing the best corrected visual acuity (BCVA) in adults aged 50 and above. METHODS: This was a prospective cross-sectional study from an eye screening programme in Hong Kong for 4188 citizens aged 50 and above. Images were analysed using a validated quantification software calculating vessel density and capillary perfusion density (CPD), along with other OCTA parameters, such as the foveal avascular zone area (FAZ) and circularity. OCTA data was collected from May 2019 to December 2020, including a total of 4188 healthy eyes from 4188 subjects. RESULTS: Mean superficial vessel density (MSVD) was 14.48 ± 3.60 mm- 1, while the mean capillary perfusion density (MCPD) was 0.41 ± 0.06. Multivariate analysis revealed ageing (ß = 0.321, p < 0.001), being male (ß=-0.089, p < 0.001), having a high body mass index (BMI) (ß = 0.039, p = 0.006), high FAZ area and low FAZ circularity (ß = 0.039 and - 0.034, p = 0.01 and 0.024 respectively), low MSVD in the outer ring (ß=-0.513, p < 0.001), specifically in the nasal and temporal outer quadrants (ß = -0.226 and - 0.259, p < 0.001 for both), and low MCPD in the outer superior quadrant (ß= -0.123, p = 0.016) being independently associated with BCVA. CONCLUSION: High FAZ area and low FAZ circularity, low MSVD in the outer ring, specifically the nasal and temporal outer quadrants, and low MCPD in the outer superior quadrant can be used as biomarkers in predicting a low visual acuity in adults aged 50 and above.

A novel vessel segmentation algorithm for pathological en-face images based on matched filter.

The vascular information in fundus images can provide important basis for detection and prediction of retina-related diseases. However, the presence of lesions such as Coroidal Neovascularization can seriously interfere with normal vascular areas in optical coherence tomography (OCT) fundus images. In this paper, a novel method is proposed for detecting blood vessels in pathological OCT fundus images. First of all, an automatic localization and filling method is used in preprocessing step to reduce pathological interference. Afterwards, in terms of vessel extraction, a pore ablation method based on capillary bundle model is applied. The ablation method processes the image after matched filter feature extraction, which can eliminate the interference caused by diseased blood vessels to a great extent. At the end of the proposed method, morphological operations are used to obtain the main vascular features. Experimental results on the dataset show that the proposed method achieves 0.88 ± 0.03, 0.79 ± 0.05, 0.66 ± 0.04, results in DICE, PRECISION and TPR, respectively. Effective extraction of vascular information from OCT fundus images is of great significance for the diagnosis and treatment of retinal related diseases.

Using Ultrawide Field-Directed Optical Coherence Tomography for Differentiating Nonproliferative and Proliferative Diabetic Retinopathy.

Purpose: To evaluate the ability of ultrawide field (UWF)-directed optical coherence tomography (OCT) to detect retinal neovascularization in eyes thought to have severe nonproliferative diabetic retinopathy (NPDR). Methods: Retrospective study of 20 consecutive patients diagnosed with severe NPDR by clinical examination. All patients underwent UWF color imaging (UWF-CI) and UWF-directed OCT following a prespecified imaging protocol to assess the mid periphery, 15/32 (46.9%) eyes underwent UWF-fluorescein angiography (FA). On OCT, new vessels elsewhere (NVE) were defined when vessels breached the internal limiting membrane. Results: A total of 32 eyes of 20 patients were evaluated. Of the 45 suspected areas of intraretinal microvascular abnormalities (IRMA) on UWF-CI, 38 (84.4%) were imaged by UWF-directed OCT, and 9/38 IRMA (23.7%) were NVE by OCT. Furthermore, UWF-directed OCT identified seven additional NVE in three eyes not seen on UWF-CI. This resulted in a change in diabetic retinopathy (DR) severity from severe NPDR to PDR in 8/32 eyes (25.0%). Among the 46.9% of eyes with UWF-FA, UWF-directed OCT agreed with the UWF-FA findings in 80% (12/15 eyes), missing only one peripheral NVE outside the UWF-OCT scanning area. Two eyes had subtle NVD that were not evident on UWF-directed OCT. Conclusions: This pilot study suggests that UWF-directed OCT may help differentiate IRMA from NVE and detect unrecognized NVE in eyes with advanced DR in a clinical practice setting. Future prospective studies in larger cohorts could determine whether this rapid and noninvasive method is clinically relevant in determining NVE presence or retinopathy progression and complication risk. Translational Relevance: UWF-directed OCT may offer a noninvasive alternative to detect NVE in eyes with DR.

Central retinal artery occlusion with cilioretinal artery sparing secondary to COVID-19: Additional ocular complication.

We describe a 68-year-old female patient with unilateral central retinal artery occlusion (CRAO) with cilioretinal artery sparing post-coronavirus disease 2019 (COVID-19) infection. The patient presented with acute vision loss in the left eye 11 days after discharge from a severe COVID-19 infection, with altered D-dimer, C-reactive protein, and fibrinogen levels. The best-corrected visual acuity (BCVA) in the left eye was 20/400; fundoscopic examination revealed diffuse pallor retina with a patent arterial branch from the optic disk to the fovea, confirmed by fluorescein angiography. CRAO with a cilioretinal artery sparing post-COVID-19 may be considered an additional ocular manifestation of the post-acute COVID-19 syndrome spectrum.

[Application of Novel Down-sampling Method in Retinal Vessel Segmentation].

Accurate segmentation of retinal blood vessels is of great significance for diagnosing, preventing and detecting eye diseases. In recent years, the U-Net network and its various variants have reached advanced level in the field of medical image segmentation. Most of these networks choose to use simple max pooling to down-sample the intermediate feature layer of the image, which is easy to lose part of the information, so this study proposes a simple and effective new down-sampling method Pixel Fusion-pooling (PF-pooling), which can well fuse the adjacent pixel information of the image. The down-sampling method proposed in this study is a lightweight general module that can be effectively integrated into various network architectures based on convolutional operations. The experimental results on the DRIVE and STARE datasets show that the F1-score index of the U-Net model using PF-pooling on the STARE dataset improved by 1.98%. The accuracy rate is increased by 0.2%, and the sensitivity is increased by 3.88%. And the generalization of the proposed module is verified by replacing different algorithm models. The results show that PF-pooling has achieved performance improvement in both Dense-UNet and Res-UNet models, and has good universality.

Optical coherence tomography-based assessment of macular vessel density, retinal layer metrics and sub-foveal choroidal thickness in COVID-19 recovered patients.

Purpose: The primary objective of the study was to assess the macular retinal vessel density, subfoveal choroidal thickness, and retinal layer metrics by optical coherence tomography angiography (OCTA), enhanced-depth imaging optical coherence tomography (EDI-OCT), and spectral domain optical coherence tomography (SD-OCT), respectively, in recovered COVID-19 patients and its comparison with the same in control subjects. The secondary objective was to evaluate differences in OCTA parameters in relation with the severity of COVID-19 disease and administration of corticosteroids. Methods: A case-control study was performed that included patients who had recovered from COVID-19 and age-matched healthy controls. Complete ocular examination including OCTA, SD-OCT, and EDI-OCT were performed three months following the diagnosis. Results: Three hundred sixty eyes of 180 subjects were enrolled between the two groups. A decreased mean foveal avascular zone area in both superficial capillary plexuses (P = 0.03) and deep capillary plexuses (P < 0.01), reduced average ganglion cell layer-inner plexiform layer thickness (P = 0.04), and increased subfoveal choroidal thickness (P < 0.001) were observed among cases in comparison to the control group. A significant correlation was found between sectoral macular vessel density in relation to disease severity and a decrease in vessel density with greater severity of the disease. Conclusion: OCTA detected retinal microvascular alterations following SARS-CoV-2 infection in subjects with the absence of any clinical ocular manifestation or systemic thrombotic events. These parameters could be used to help identify patients with a higher incidence of systemic thromboembolism on longer follow-ups and identify the impact of corticosteroids on retinal architecture.

Retinal perfusion density can predict cardiovascular disease risk in patients with retinal vein occlusion.

Purpose: To correlate microvascular changes and assess the relationship between microvascular changes and cardiovascular disease (CVD) risk in patients with retinal vein occlusion (RVO). Methods: Patients over 40 years of age with unilateral RVO were included in this prospective study. Those known to have cardiovascular disease were excluded. A detailed medical history was taken and physical exam was done to measure the height, weight, body mass index (BMI), and systolic blood pressure (SBP). A comprehensive eye check-up was followed by optical coherence tomography angiography (OCTA). Microvascular indices such as vessel density (VD) and perfusion density (PD) were noted. A statistical model was developed for prediction of CVD risk and was integrated with the World Health Organization (WHO)'s risk prediction charts. Results: This study included 42 patients with RVO and 22 controls with an age range of 42-82 years. There were 40 males (62.5%) and 24 females (37.5%). Along with age, SBP, and gender, perfusion density was found to have significant impact on CVD risk (P = 0.030). Reduction in PD was associated with increase in CVD risk. PD had a greater influence on CVD in <50 years age than in >70 years group. Using linear regression, a model with accuracy of 72.1% was developed for CVD risk prediction and was converted into color coded charts similar to WHO risk prediction charts. Conclusion: These findings suggest a significant correlation between microvascular parameters and CVD risk in RVO patients. Based on these parameters, an easy-to-use and color-coded risk prediction chart was developed.

Automatic vessel crossing and bifurcation detection based on multi-attention network vessel segmentation and directed graph search.

Analysis of the vascular tree is the basic premise to automatically diagnose retinal biomarkers associated with ophthalmic and systemic diseases, among which accurate identification of intersection and bifurcation points is quite challenging but important for disentangling complex vascular network and tracking vessel morphology. In this paper, we present a novel directed graph search-based multi-attentive neural network approach to automatically segment the vascular network and separate intersections and bifurcations from color fundus images. Our approach uses multi-dimensional attention to adaptively integrate local features and their global dependencies while learning to focus on target structures at different scales to generate binary vascular maps. A directed graphical representation of the vascular network is constructed to represent the topology and spatial connectivity of the vascular structures. Using local geometric information including color difference, diameter, and angle, the complex vascular tree is decomposed into multiple sub-trees to finally classify and label vascular feature points. The proposed method has been tested on the DRIVE dataset and the IOSTAR dataset containing 40 images and 30 images, respectively, with 0.863 and 0.764 F1-score of detection points and average accuracy of 0.914 and 0.854 for classification points. These results demonstrate the superiority of our proposed method outperforming state-of-the-art methods in feature point detection and classification.

Avascular Peripheral Retina in Infants.

Avascular peripheral retina in an infant is a common characteristic of numerous pediatric retinal vascular disorders and often presents a diagnostic challenge to the clinician. In this review, key features of each disease in the differential diagnosis, from retinopathy of prematurity, familial exudative vitreoretinopathy, Coats disease, incontinentia pigmenti, Norrie disease, and persistent fetal vasculature, to other rare hematologic conditions and telomere disorders, will be discussed by expert ophthalmologists in the field.