A floating ball inside the eye in smartphone slit-lamp imaging: A case report of a pediatric vitreous cyst and a literature review.

An 8-year-old male patient was presented with a chief complaint of visual perception of a spherical object located in the visual field of his right eye. According to the patient's prior medical records, they exhibited a sole incident of minor visual impairment in the right eye, characterized by blurred vision (best-corrected visual acuity: 8/10), which first manifested during preschool assessments at the age of 5 years. During the fundoscopic examination of the patient, a pigmented, lobulated, and mobile vitreous cyst was observed in the right eye, whereas the examination of the patient's left eye revealed no abnormalities. A video of a smartphone slit-lamp imaging was also captured to facilitate subsequent examinations and patient follow-up.

Quantitative analysis of the eyelid curvature in patients with blepharoptosis.

BACKGROUND: The aim of this study was to evaluate the ability of two novel eyelid curvature measurements to distinguish between normal eyes and different severities of blepharoptosis. METHODS: A comparative cross-sectional analysis of upper eyelid curvature was performed for different severities of patients with unilateral blepharoptosis (congenital and aponeurotic) and normal controls. Mean upper lid contour index (ULCI) and area circularity index (ACI) were calculated for each group by dividing the intercanthal distance by upper eyelid margin length (ULCI) and dividing the interpalpebral area by the area of a circle enclosing the eye (ACI). The ratio of each index for the study and fellow normal eye of each patient was also calculated and compared between groups. RESULTS: A total of 106 eyes including 30 eyes in the control group and 25, 27, and 24 eyes in the mild, moderate, and severe ptosis groups were enrolled in the study. ULCI and ACI showed a statistically significant difference between the groups (p < 0.001, p < 0.001). The inter-eye ratio (ULCI-ratio and ACI-ratio) of indices was also significantly different between groups (p = 0.002, p < 0.001). Pairwise comparisons revealed that ACI and ACI-ratio were significantly different between all pairs of study groups. CONCLUSION: The results of our study showed that ACI based on area measurements may distinguish blepharoptosis patients from normal controls and from each other. Including the data from the fellow normal eyes in the form of ratio indices may improve the differentiating power. These results can be useful in designing the optimal eyelid curvature measurements.

Uveal melanoma in the Iranian population: two decades of patient management in a tertiary eye center.

BACKGROUND: To assess the characteristics and outcomes of uveal melanoma management at a tertiary center in the Middle East. METHODS: A study on 164 patients with uveal melanoma was conducted by reviewing the available medical records, ultrasound, and pathology report results. Age at diagnosis, tumor location and size, treatment mode, visual outcome, metastasis, mortality, and survival were studied. RESULTS: The mean age of patients was 52.0 ± 15.0 years, and 52.5% were male. Choroidal melanoma was the most common uveal melanoma, followed by the ciliary body and iris melanoma. The mean thickness of tumors was 8.29 ± 3.29. The majority of patients (n = 111, 67.9%) were managed by brachytherapy with ruthenium-106 plaques. Enucleation was performed primarily in 46 (28%) patients and secondarily in nine (5.5%) patients. The sexual disparity was detected as the proximity of uveal melanoma to the fovea in males. For a 61-month mean follow-up period, mortality occurred in eight of our cases, six of which were due to metastasis. The most common site for distance metastasis was the liver (5/6), followed by the lung (1/6). The five-year and eight-year overall survival (OS) rate was 0.947%± 0.019. The 5-year survival rate reached zero in metastatic patients. OS was not statistically different depending on the age, tumor diameters, the primary treatment received, or the histopathologic findings (p > 0.50 for all). CONCLUSION: In this study, individuals diagnosed with UM exhibited an OS rate of around 94% at the five-year mark, which remained consistent up to eight years. Notably, the presence of distance metastasis emerged as the sole statistically significant factor influencing overall survival.

Evaluating the Efficacy and Safety of Aflibercept Biosimilar (P041) Compared with Originator Product in Patients with Neovascular Age-Related Macular Degeneration.

OBJECTIVE: To assess the noninferiority of biosimilar aflibercept (P041, CinnaGen) to the originator aflibercept (AFL, Regeneron) in terms of efficacy, safety, and immunogenicity. DESIGN: This was a phase Ш, 52-week, multicenter, randomized, double-masked, and active control trial involving eyes in a 1:1 ratio. SUBJECTS: Patients with active subfoveal choroidal neovascularization secondary to age-related macular degeneration randomized into the 2 groups of P041 and AFL. METHODS: Patients received an injection of aflibercept every 4 weeks for 3 doses, followed by administration every 8 weeks up to week 48. MAIN OUTCOME MEASURES: The primary outcome was the noninferiority analysis of eyes maintaining vision at week 52. Secondary outcomes included the changes in visual acuity and retinal thickness, safety evaluation, and immunogenicity during the study. RESULTS: In total, 168 eyes of 168 patients were included. At week 52, the proportion of patients maintaining vision was 94.44% in the P041 group compared with 94.52% in the AFL group. The 95% confidence interval (CI) for the difference of maintaining vision from baseline did not exceed the predefined noninferiority margin of 10% (difference, -0.0008; 95% CI, -0.074 to 0.074; P = 0.98). Secondary outcomes indicated similar results in both arms (all P > 0.05). Safety measured outcomes and immunogenicity were similar between the 2 study groups. CONCLUSIONS: Biosimilar aflibercept was noninferior to AFL in eyes with neovascular age-related macular degeneration. Other efficacy and safety findings also indicated the similarity of 2 products. FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Automated diagnosis of plus disease in retinopathy of prematurity using quantification of vessels characteristics.

The condition known as Plus disease is distinguished by atypical alterations in the retinal vasculature of neonates born prematurely. It has been demonstrated that the diagnosis of Plus disease is subjective and qualitative in nature. The utilization of quantitative methods and computer-based image analysis to enhance the objectivity of Plus disease diagnosis has been extensively established in the literature. This study presents the development of a computer-based image analysis method aimed at automatically distinguishing Plus images from non-Plus images. The proposed methodology conducts a quantitative analysis of the vascular characteristics linked to Plus disease, thereby aiding physicians in making informed judgments. A collection of 76 posterior retinal images from a diverse group of infants who underwent screening for Retinopathy of Prematurity (ROP) was obtained. A reference standard diagnosis was established as the majority of the labeling performed by three experts in ROP during two separate sessions. The process of segmenting retinal vessels was carried out using a semi-automatic methodology. Computer algorithms were developed to compute the tortuosity, dilation, and density of vessels in various retinal regions as potential discriminative characteristics. A classifier was provided with a set of selected features in order to distinguish between Plus images and non-Plus images. This study included 76 infants (49 [64.5%] boys) with mean birth weight of 1305 ± 427 g and mean gestational age of 29.3 ± 3 weeks. The average level of agreement among experts for the diagnosis of plus disease was found to be 79% with a standard deviation of 5.3%. In terms of intra-expert agreement, the average was 85% with a standard deviation of 3%. Furthermore, the average tortuosity of the five most tortuous vessels was significantly higher in Plus images compared to non-Plus images (p ≤ 0.0001). The curvature values based on points were found to be significantly higher in Plus images compared to non-Plus images (p ≤ 0.0001). The maximum diameter of vessels within a region extending 5-disc diameters away from the border of the optic disc (referred to as 5DD) exhibited a statistically significant increase in Plus images compared to non-Plus images (p ≤ 0.0001). The density of vessels in Plus images was found to be significantly higher compared to non-Plus images (p ≤ 0.0001). The classifier's accuracy in distinguishing between Plus and non-Plus images, as determined through tenfold cross-validation, was found to be 0.86 ± 0.01. This accuracy was observed to be higher than the diagnostic accuracy of one out of three experts when compared to the reference standard. The implemented algorithm in the current study demonstrated a commendable level of accuracy in detecting Plus disease in cases of retinopathy of prematurity, exhibiting comparable performance to that of expert diagnoses. By engaging in an objective analysis of the characteristics of vessels, there exists the possibility of conducting a quantitative assessment of the disease progression's features. The utilization of this automated system has the potential to enhance physicians' ability to diagnose Plus disease, thereby offering valuable contributions to the management of ROP through the integration of traditional ophthalmoscopy and image-based telemedicine methodologies.

Assessment of area and structural irregularity of retinal layers in diabetic retinopathy using machine learning and image processing techniques.

Diabetes retinopathy prevention necessitates early detection, monitoring, and treatment. Non-invasive optical coherence tomography (OCT) shows structural changes in the retinal layer. OCT image evaluation necessitates retinal layer segmentation. The ability of our automated retinal layer segmentation to distinguish between normal, non-proliferative (NPDR), and proliferative diabetic retinopathy (PDR) was investigated in this study using quantifiable biomarkers such as retina layer smoothness index (SI) and area (S) in horizontal and vertical OCT images for each zone (fovea, superior, inferior, nasal, and temporal). This research includes 84 eyes from 57 individuals. The study shows a significant difference in the Area (S) of inner nuclear layer (INL) and outer nuclear layer (ONL) in the horizontal foveal zone across the three groups (p < 0.001). In the horizontal scan, there is a significant difference in the smoothness index (SI) of the inner plexiform layer (IPL) and the upper border of the outer plexiform layer (OPL) among three groups (p < 0.05). There is also a significant difference in the area (S) of the OPL in the foveal zone among the three groups (p = 0.003). The area (S) of the INL in the foveal region of horizontal slabs performed best for distinguishing diabetic patients (NPDR and PDR) from normal individuals, with an accuracy of 87.6%. The smoothness index (SI) of IPL in the nasal zone of horizontal foveal slabs was the most accurate at 97.2% in distinguishing PDR from NPDR. The smoothness index of the top border of the OPL in the nasal zone of horizontal slabs was 84.1% accurate in distinguishing NPDR from PDR. Smoothness index of IPL in the temporal zone of horizontal slabs was 89.8% accurate in identifying NPDR from PDR patients. In conclusion, optical coherence tomography can assess the smoothness index and irregularity of the inner and outer plexiform layers, particularly in the nasal and temporal regions of horizontal foveal slabs, to distinguish non-proliferative from proliferative diabetic retinopathy. The evolution of diabetic retinopathy throughout severity levels and its effects on retinal layer irregularity need more study.

Hemicentral retinal vein occlusion in a patient with a history of coronavirus disease 2019 infection: a case report and review of the literature.

BACKGROUND: Considering the various manifestations of coronavirus disease 2019 and its imperative importance in terms of the right clinical approach and early management, we sought to present a hemicentral retinal vein occlusion case, with a history of heterozygosity of methylenetetrahydrofolate reductase (MTHFR) genes and potential for clotting complications as a late manifestation of coronavirus disease 2019, and provide a brief review of reported retinal vein occlusion cases in patients with coronavirus disease 2019. CASE PRESENTATION: A 35-year-old Iranian patient presented with a visual impairment in the left eye 4 months after recovering from coronavirus disease 2019. He reported a mild blurring of vision in the same eye a few days after admission due to coronavirus disease 2019. The ophthalmic evaluation was compatible with hemicentral retinal vein occlusion. Systemic and laboratory workups were negative except for borderline protein C activity, homocysteine levels, and heterozygosity of MTHFR genes. The patient was scheduled to receive three monthly intravitreal antivascular endothelial growth factor injections. CONCLUSION: We present a case of inferior hemicentral retinal vein occlusion case with an MTHFR mutation with sequential loss of vision 4 months after coronavirus disease 2019 to make clinicians aware of the possibility of late ocular coronavirus disease 2019 manifestations.

Pachychoroid neovasculopathy versus macular neovascularization in age-related macular degeneration with and without shallow irregular pigment epithelial detachment.

To compare the choroidal neovascular features of individuals with pachychoroid neovasculopathy (PNV) and neovascular age-related macular degeneration (nAMD) with and without shallow irregular pigment epithelial detachment (SIPED). Using optical coherence tomography angiography, the choroidal neovascular complexes of 27 patients with PNV, 34 patients with nAMD and SIPED, and 15 patients with nAMD without SIPED were analyzed with FIJI and AngioTool software. PNV compared to nAMD with SIPED had a greater vessel percentage area (P = 0.034), junction density (P = 0.045), average vessel length (P < 0.001), and fractal dimension (P < 0.001). PNV, compared to nAMD without SIPED, had a greater total vessel length (P = 0.002), total number of junctions (P < 0.001), junction density (P = 0.034), and fractal dimension (P = 0.005). nAMD with SIPED, compared to nAMD without SIPED, had greater vessel area, total number of junctions, total vessel length, and average vessel length (all P values < 0.001). Patients with nAMD plus SIPED and individuals with nAMD without SIPED have similar fractal dimension values (P = 0.703). Biomarkers of choroidal neovascular complexity, such as fractal dimension, can be used to differentiate PNV from nAMD with or without SIPED.

Sector area index: a novel supporting marker for blepharoptosis screening and grading.

PURPOSE: To introduce a new supporting marker for discriminating different grades of ptosis called Sector Area Index (SAI) and a semi-automated technique to calculate it. METHODS: In this cross-sectional comparative case series, a circle enclosing the intercanthal distance was automatically drawn after choosing two points as the medial and lateral canthus and manually selecting the palpebral fissure region. Finally, 15-degree apart sectors are applied to the enclosed circle. SAI was measured automatically by dividing the area of each 15-degree sector marked with the upper eyelid contour by the total area of the sector marked with the edge of the surrounding circle. SAI values and inter-eye SAI differences were compared between patients with different grades of ptosis as well as normal patients. RESULTS: In the current study, 106 eyes were recruited (30, 25, 27, and 24 in the control, mild, moderate, and severe ptosis groups, respectively). Mean values of SAI in all sectors showed a decreasing trend from normal individuals toward patients with severe ptosis. The mean difference values of SAI between study eyes and fellow eyes in all four groups of patients showed a statistically significant difference (p < 0.05). In a pairwise comparison between groups, mean values of SAI in all nasal sectors from 15° to 60° showed a statistically significant difference between all groups (p < 0.05). CONCLUSION: The mean difference of SAI between study eyes and fellow eyes, including eyelid curvature, especially in 15°-60° and 120°-165° sectors, can demonstrate differentiating performance for detecting and discriminating varying grades of ptosis.

Application of ImageJ in Optical Coherence Tomography Angiography (OCT-A): A Literature Review.

Background: This study aimed to review the literature on the application of ImageJ in optical coherence tomography angiography (OCT-A) images. Methods: A general search was performed in PubMed, Google Scholar, and Scopus databases. The authors evaluated each of the selected articles in order to assess the implementation of ImageJ in OCT-A images. Results: ImageJ can aid in reducing artifacts, enhancing image quality to increase the accuracy of the process and analysis, processing and analyzing images, generating comparable parameters such as the parameters that assess perfusion of the layers (vessel density (VD), skeletonized density (SD), and vessel length density (VLD)) and the parameters that evaluate the structure of the layers (fractal dimension (FD), vessel density index (VDI), and lacunarity (LAC)), and the foveal avascular zone (FAZ) that are used widely in the retinal and choroidal studies), and establishing diagnostic criteria. It can help to save time when the dataset is huge with numerous plugins and options for image processing and analysis with reliable results. Diverse studies implemented distinct binarization and thresholding techniques, resulting in disparate outcomes and incomparable parameters. Uniformity in methodology is required to acquire comparable data from studies employing diverse processing and analysis techniques that yield varied outcomes. Conclusion: Researchers and professionals might benefit from using ImageJ because of how quickly and correctly it processes and analyzes images. It is highly adaptable and potent software, allowing users to evaluate images in a variety of ways. There exists a diverse range of methodologies for analyzing OCTA images through the utilization of ImageJ. However, it is imperative to establish a standardized strategy to ensure the reliability and consistency of the method for research purposes.

Bilateral central serous retinal detachment in a patient with nephrotic syndrome: a case report.

BACKGROUND: The aim of this report is to highlight the importance of considering nephrotic syndrome as a potential underlying cause of bilateral central serous retinal detachment in a patient with systemic lupus erythematosus and to underscore the significance of a comprehensive systemic workup in these patients. CASE PRESENTATION: A 19-year-old Iranian female patient with history of systemic lupus erythematosus presented with progressive vision loss and bilateral macular elevation. Ophthalmic examination revealed periorbital edema, chemosis, and subretinal fluid at the macula of both eyes. Optical coherence tomography confirmed the existence of subretinal fluid and serous detachment located at the macula of both eyes. On fluorescein angiography, there were no signs of subretinal leakage such as smoke stack sign or expansile dot in late phases. Laboratory tests detected hypoalbuminemia and significant proteinuria, leading to the diagnosis of nephrotic syndrome. Treatment with prednisolone and albumin infusion resulted in improved visual acuity and resolution of subretinal fluid. CONCLUSION: Nephrotic syndrome can be a rare underlying cause of bilateral central serous retinal detachment, and its association with systemic lupus erythematosus should be considered. Hypoalbuminemia in nephrotic syndrome alters fluid dynamics in the retina, contributing to bilateral central serous retinal detachment. Early recognition and management of nephrotic syndrome are essential for vision recovery and preventing long-term complications.

Eccentric Fixation and Good Visual Acuity in a Child with Large Traumatic Macular Hole: A Case Report.

A girl of 8 years old was referred to our clinic with a history of penetrating injury to her left eye 6 years ago with light perception vision and a large traumatic macular hole in her right eye. Her right eye's vision was 4/10 when she first visited our clinic. Considering the patient's one-eye status, her parents' reluctance to undergo surgery, and the possibility of spontaneous closure of traumatic macular holes, it was determined to observe the patient and evaluate her visual acuity and macular hole condition. In 2 years, the final best corrected visual acuity was 8/10 in the right eye, with infratemporal eccentric fixation in visuoscopy. In addition to evaluating and reporting this case as a traumatic macular hole, we will discuss the role of nonsurgical treatment and the possibility of good visual acuity with eccentric fixation in a child with large traumatic macular hole.

Retinal astrocytic hamartoma complicated by branch retinal vein occlusion in a patient with tuberous sclerosis complex.

Purpose: To report a case with branch retinal vein occlusion secondary to a retinal astrocytic hamartoma in a patient with tuberous sclerosis complex. Observations: A fourteen-year-old boy, a known case of tuberous sclerosis complex, with multiple bilateral retinal astrocytic hamartomas was followed by 6 months intervals. In his last follow-up, 6 months after initial presentation, the patient developed angiographic signs of branch retinal vein occlusion (BRVO) in the superotemporal arcade of the right eye distal to one of the retinal astrocytic hamartomas. He underwent targeted retinal laser photocoagulation. No secondary complication related to BRVO was observed during the next six-month follow-up. Conclusion: And Importance: Although the co-occurrence of branch retinal vein occlusion and astrocytic hamartoma may represent an incidental finding, awareness of BRVO as a possible complication associated with retinal astrocytic hamartoma helps timely diagnosis and prompt treatment of this complication, improving the visual prognosis of these patients.

Evaluation of Choroidal Vascularity Index in Keratoconus Patients: Does Choroidal Vascularity Change in Keratoconus?

Purpose: To investigate the choroidal structure in keratoconic patients with different severity using the choroidal vascularity index (CVI) derived from image binarization on enhanced depth imaging optical coherence tomography scans (EDI-OCT). Methods: Sixty-eight eyes from 34 keratoconus (KCN) patients and 72 eyes from 36 healthy subjects were recruited in this prospective, noninterventional, comparative cross-sectional study. EDI-OCT was employed to measure choroidal parameters, including choroidal thickness (CT), total choroidal area (TCA), luminal area, stromal area, and CVI. Results: Subfoveal CT was 354.6 ± 66.8 µm in the control group and 371 ± 64.5 µm in the KCN group (P = 0.86). There was no significant difference between control and KCN groups in terms of TCA (0.66 ± 0.14 mm2 vs. 0.7 ± 0.12 mm2; P = 0.70), luminal area (0.49 ± 0.10 mm2 vs. 0.53 ± 0.08 mm2; P = 0.67), and stromal area (0.16 ± 0.05 mm2 vs. 0.17 ± 0.05 mm2; P = 0.84). CVI was also comparable in the control group (75.4% ±3.4%) and the KCN group (75.6% ±4.5%; P = 0.43). There was also no significant correlation between other choroidal parameters and KCN severity indices. Conclusion: It seems that CVI as well as other choroidal biomarkers were not significantly different between patients with KCN and healthy subjects.

Henle fiber layer hemorrhage associated with combined central retinal vein occlusion and cilioretinal artery occlusion: a case report.

BACKGROUND: The purpose of this study is to describe a patient who experienced simultaneous central retinal vein and cilioretinal artery occlusions, as well as perifoveal hemorrhage in the Henle fiber. CASE PRESENTATION: A 67-year-old Iranian woman presented with a 3-day history of reduced vision in her left eye. Venous tortuosity and retinal hemorrhage were observed in the retina, together with whitened regions around the fovea, consistent with the diagnosis of central retinal vein occlusion in conjunction with cilioretinal artery occlusion. In structural and en face optical coherence tomography, star-shaped hemorrhages were observed around the fovea, which looked hyperreflective in the Henle fiber layer. CONCLUSIONS: We present a case of central retinal vein occlusion exacerbated by cilioretinal occlusion and hemorrhage in the Henle fiber layer. The hemorrhage is most likely the result of increased intraluminal pressure in the deep capillary plexus.

Microvascular and structural analysis of the retina and choroid in heart failure patients with reduced ejection fraction.

This cross-sectional study was designed to assess alterations of choroidal and retinal microvasculature in patients with Heart Failure with Reduced Ejection Fraction (HFrEF) and compare them with a normal age and sex-matched population. Fifty-two eyes of 26 patients with HFrEF (left ventricular ejection fraction [LVEF] < 40%) and 64 eyes of 32 healthy individuals were considered as the patient and the control groups, respectively. We found no statistically significant differences in age-adjusted mean central macular thickness (CMT), superficial or deep retinal capillary plexus vascular densities, and choriocapillaris flow (CC flow) density between the HFrEF group and the normal controls, with the exception of the parafoveal mean superficial capillary plexus vascular density (P = 0.023), which remained statistically significant after adjusting for age (P = 0.034). The patients with HFrEF had a significantly lower subfoveal choroidal thickness (SFCT) than the normal subjects (264 ± 82 vs 313 ± 72; P = 0.009), and the difference was still statistically significant after age adjustment (P = 0.026). Although choroidal vascularity index (CVI) was lower in the HFrEF group than in the control group, the difference was not statistically significant before and after age adjustment (73.45 ± 6.67 vs 75.77 ± 5.92; P = 0.118 and P = 0.096, respectively). In conclusion, in patients with HFrEF, we observed a reduction in parafoveal retinal VD in the superficial capillary plexus, as well as SFCT, but no significant change in CVI, CMT, or CC flow density.

Cataract surgery in patients with retinitis pigmentosa: systematic review.

Retinitis pigmentosa (RP) is an inherited bilateral retinal degenerative disease with an incidence of 1 in 4000 people. RP affects more than 1 million individuals worldwide. Although night blindness and restricted visual field are the most typical symptoms of these individuals, generalized vision loss due to cataracts can be expected in the latter stages of the disease. It has been demonstrated that posterior subcapsular cataract is the most prevalent cataract in younger individuals with RP, as opposed to age-related cataracts. Although most ophthalmologists may have a negative view of cataract surgery in patients with RP, it appears that it can play an important role in the visual restoration of patients with RP. However, there are concerns about performing cataract surgery for patients with RP. Herein, a systematic review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses on databases of MEDLINE and Scopus.

Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm.

Quantifying the smoothness of different layers of the retina can potentially be an important and practical biomarker in various pathologic conditions like diabetic retinopathy. The purpose of this study is to develop an automated machine learning algorithm which uses support vector regression method with wavelet kernel and automatically segments two hyperreflective retinal layers (inner plexiform layer (IPL) and outer plexiform layer (OPL)) in 50 optical coherence tomography (OCT) slabs and calculates the smoothness index (SI). The Bland-Altman plots, mean absolute error, root mean square error and signed error calculations revealed a modest discrepancy between the manual approach, used as the ground truth, and the corresponding automated segmentation of IPL/ OPL, as well as SI measurements in OCT slabs. It was concluded that the constructed algorithm may be employed as a reliable, rapid and convenient approach for segmenting IPL/OPL and calculating SI in the appropriate layers.

Automated machine learning-based classification of proliferative and non-proliferative diabetic retinopathy using optical coherence tomography angiography vascular density maps.

PURPOSE: The study aims to classify the eyes with proliferative diabetic retinopathy (PDR) and non-proliferative diabetic retinopathy (NPDR) based on the optical coherence tomography angiography (OCTA) vascular density maps using a supervised machine learning algorithm. METHODS: OCTA vascular density maps (at superficial capillary plexus (SCP), deep capillary plexus (DCP), and total retina (R) levels) of 148 eyes from 78 patients with diabetic retinopathy (45 PDR and 103 NPDR) was used to classify the images to NPDR and PDR groups based on a supervised machine learning algorithm known as the support vector machine (SVM) classifier optimized by a genetic evolutionary algorithm. RESULTS: The implemented algorithm in three different models reached up to 85% accuracy in classifying PDR and NPDR in all three levels of vascular density maps. The deep retinal layer vascular density map demonstrated the best performance with a 90% accuracy in discriminating between PDR and NPDR. CONCLUSIONS: The current study on a limited number of patients with diabetic retinopathy demonstrated that a supervised machine learning-based method known as SVM can be used to differentiate PDR and NPDR patients using OCTA vascular density maps.

Evaluation of the additive effect of interferon α 2b with monthly intravitreal injection of bevacizumab in refractory diabetic macular edema.

BACKGROUND: To evaluate the additive effect of topical or sub-tenon injection of interferon (IFN)-α 2b in the treatment of refractory diabetic macular edema. METHODS: In this prospective study patients with center-involved DME who were unresponsive to 3 monthly consecutive IVB injections were recruited. Patients were divided into three groups: group1, received IFN- α 2b topical drop at a dose of 1mIU/ml four times a day for 3 months. Group 2, received a single sub-tenon injection of 1mIU/ml IFN- α 2b at the enrollment. Group 3 received artificial tears four times a day for 3 months (control group). All groups received three consecutive monthly IVB injections and were evaluated monthly up to 1 month following the last IVB injection. RESULTS: In this study, 59 eyes of 35 patients with refractory DME were assessed. The final follow-up showed that although CMT decreased in all groups, only patients in Group 2 had statistically significant lower CMT compared to their baseline values (change in CMT: - 117 ± 213 µm; p-value = 0.025). Comparison of CMT changes between three groups showed no statistically significant difference, although it was higher in group 2 (change in CMT: - 117 ± 213 µm (Group2) vs. - 49 ± 173 (Group 1) vs. - 36 ± 86 (Group 3); p-value = 0.085). Considering eyes with baseline CMT > 400 µm, sub-tenon injection of IFN α2b led to a significant reduction of CMT at the first month and final follow-up visit (CMT change: - 166 ± 210, - 145 ± 231 µm; p-value = 0.018 and 0.035, respectively). In this subgroup, eyes in Group 2 had lower CMT at the first month following treatment in comparison with the control group (CMT: 444 ± 123 µm vs. 544 ± 96 µm, p-value = 0.042). Alterations of CDVA were not statistically significant among groups, although patients in Group 1 had a significant improvement in vision at second and last follow up (CDVA change: - 0.23 ± 0.39, - 0.20 ± 0.43 logMAR; p-value = 0.030 and 0.010, respectively). CONCLUSIONS: In short term, Sub-tenon injection of IFN might have an additive anatomical effect in eyes with refractory DME. Validation of this observation requires further prospective controlled studies.