The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation.

We compared the performance of deep learning (DL) in the classification of optical coherence tomography (OCT) images of macular diseases between automated classification alone and in combination with automated segmentation. OCT images were collected from patients with neovascular age-related macular degeneration, polypoidal choroidal vasculopathy, diabetic macular edema, retinal vein occlusion, cystoid macular edema in Irvine-Gass syndrome, and other macular diseases, along with the normal fellow eyes. A total of 14,327 OCT images were used to train DL models. Three experiments were conducted: classification alone (CA), use of automated segmentation of the OCT images by RelayNet, and the graph-cut technique before the classification (combination method 1 (CM1) and 2 (CM2), respectively). For validation of classification of the macular diseases, the sensitivity, specificity, and accuracy of CA were found at 62.55%, 95.16%, and 93.14%, respectively, whereas the sensitivity, specificity, and accuracy of CM1 were found at 72.90%, 96.20%, and 93.92%, respectively, and of CM2 at 71.36%, 96.42%, and 94.80%, respectively. The accuracy of CM2 was statistically higher than that of CA (p = 0.05878). All three methods achieved AUC at 97%. Applying DL for segmentation of OCT images prior to classification of the images by another DL model may improve the performance of the classification.

Capacity building in screening and treatment of diabetic retinopathy in Asia-Pacific region.

The focus of capacity building for screening and treatment of diabetic retinopathy (DR) is on health professionals who are nonophthalmologists. Both physicians and nonphysicians are recruited for screening DR. Although there is no standardization of the course syllabus for the capacity building, it is generally accepted to keep their sensitivity >80%, specificity >95%, and clinical failure rate <5% for the nonophthalmologists, if possible. A systematic literature search was performed using the PubMed database and the following search terms: diabetic retinopathy, diabetic retinopathy screening, Asia, diabetic retinopathy treatment, age-related macular degeneration, capacity building, deep learning, artificial intelligence (AI), nurse-led clinic, and intravitreal injection (IVI). AI may be a tool for improving their capacity. Capacity building on IVIs of antivascular endothelial growth factors for DR is focused on nurses. There is evidence that, after a supervision of an average of 100 initial injections, the trained nurses can do the injections effectively and safely, the rate of endophthalmitis ranges from 0.03 to 0.07%, comparable to ophthalmologists. However, laws and regulations, which are different among countries, are challenges and barriers for nonophthalmologists, particularly for nonphysicians, for both screening and treatment of DR. Even if nonphysicians or physicians who are nonophthalmologists are legally approved for these tasks, sustainability of the capacity is another important challenge, this may be achieved if the capacity building can be part of their career development. Patient acceptability is another important barrier for initiating care provided by nonophthalmologists, particularly in Asia. There are also collaborations between national eye institutes of high-income countries, nongovernment organizations, and local eye institutes to improve both the quality and quantity of ophthalmologists and retinal specialists in low-income countries in Asia. This approach may require more labor, cost, and time consuming than training nonophthalmologists.

Subclinical subretinal fluid detectable only by optical coherence tomography in choroidal naevi-the SON study.

BACKGROUND: Subretinal fluid is a risk factor for growth and malignant transformation of choroidal naevi, however it is unclear if this applies to subclinical fluid that is only detectable by optical coherence tomography (OCT). The objective of this study was to determine the prevalence and associations of subclinical but OCT-detectable subretinal fluid over choroidal naevi. METHODS: Cross-sectional study of 309 consecutive cases of choroidal naevi imaged by OCT between July 2017 to January 2019. Multicentre international study involving ten retinal specialist centres. All patients presenting to retinal specialists had routine clinical examination and OCT imaging. The prevalence of subclinical OCT-detectable subretinal fluid over choroidal naevi and its associations with other features known to predict growth and malignant transformation were noted and analysed. RESULTS: Of 309 identified consecutive cases, the mean patient age was 65 years, 89.3% of patients were Caucasian and 3.9% were Asian. The prevalence of subclinical but OCT-detectable subretinal fluid associated with choroidal naevi was 11.7% (36/309). Naevi with fluid were associated with larger basal diameters, greater thickness, presence of a halo, orange pigmentation, hyperautofluorescence, and hypodensity on B-scan ultrasonography. CONCLUSION AND RELEVANCE: Of choroidal naevi where subretinal fluid is not visible on clinical examination, 11.7% demonstrate subretinal fluid on OCT scans. These naevi more commonly exhibit features known to be associated with growth and transformation to melanoma. The presence of subclinical OCT-detectable fluid over choroidal naevi may assist in their risk stratification.

Spontaneous Resolution of Subretinal Fluid Secondary to Retinal Astrocytic Hamartoma in Tuberous Sclerosis:A Case Report.

Retinal astrocytic hamartoma is the most common ocular manifestation in tuberous sclerosis. Although astrocytic hamartomas are usually benign and stationary, there are occasionally circumstances when they are considered to be active. In this study, the authors report a case of self-limited visual impairment due to astrocytic hamartomas. [Ophthalmic Surg Lasers Imaging Retina. 2019;50:737-739.].

Real-world outcomes of non-responding diabetic macular edema treated with continued anti-VEGF therapy versus early switch to dexamethasone implant: 2-year results.

AIMS: To provide 2-year follow-up data on eyes with diabetic macular edema (DME) that were non-responsive after three initial anti-vascular endothelial growth factor (VEGF) injections, comparing functional and anatomical outcomes under continued anti-VEGF therapy versus dexamethasone (DEX) implant. METHODS: Multicenter, retrospective chart review comparing eyes with treatment-naïve DME and a suboptimal response to a loading phase of anti-VEGF therapy (3 injections given monthly) which were then treated with (a) further anti-VEGF (n = 72) or (b) initially switched to DEX implant (n = 38). Main outcome measures were change in visual acuity (VA) and central subfield thickness (CST) from the end of the loading phase to 24 months. RESULTS: In 79% of the 12-month study population (87/110 eyes), 24-month data were available. One quarter of eyes in each group switched treatments during the second year. Eyes that were switched early to DEX implant maintained the functional and anatomical improvements at 24 months which were seen in the first year (from month 3: + 8.9 letters, - 214 µm). Eyes that were switched from anti-VEGF therapy to steroids in the second year improved VA and reduced CST at 24 months (from month 12: + 6.8 letters, p = 0.023; - 226 µm, p = 0.004). In eyes continued on anti-VEGF therapy, VA and CST were stable at 24 months (from month 3: + 2.8 letters, p = 0.254; - 24 µm, p = 0.243). Eyes that were non-responsive to anti-VEGF therapy for 12 months had similar chances to experience a VA gain from further therapy as eyes that were non-responsive for 3 months only (23.8 vs. 31.0%, p = 0.344). CONCLUSIONS: The beneficial effect of an early switch to DEX implant in DME non-responders seen at month 12 was maintained during the second year. A later switch from anti-VEGF to steroids still provided significant improvement. Eyes continued on anti-VEGF over a period of 24 months maintained vision. A quarter of eyes, which had not improved vision at 12 months, exhibited a delayed response to treatment.

Causative Pathogens of Endophthalmitis after Intravitreal Anti-VEGF Injection: An International Multicenter Study.

PURPOSE: The main objective of this study was to investigate the microbiological spectrum of endophthalmitis after anti-VEGF injections and to compare streptococcal with non-streptococcus-associated cases with regard to baseline characteristics and injection procedure. METHODS: Retrospective, international multicenter study of patients with culture-positive endophthalmitis after intravitreal anti-VEGF injection at 17 different retina referral centers. RESULTS: Eighty-three cases with 87 identified pathogens were included. Coagulase-negative staphylococci (59%) and viridans streptococci (15%) were the most frequent pathogens found. The use of postoperative antibiotics and performance of injections in an operating room setting significantly reduced the rate of streptococcus-induced endophthalmitis cases (p = 0.01 for both). CONCLUSION: We found a statistically significant lower rate of postinjectional local antibiotic therapy and operating room-based procedures among the streptococcus-induced cases compared to cases caused by other organisms.

Shall we stay, or shall we switch? Continued anti-VEGF therapy versus early switch to dexamethasone implant in refractory diabetic macular edema.

AIMS: To compare functional and anatomical outcomes of continued anti-vascular endothelial growth factor (VEGF) therapy versus dexamethasone (DEX) implant in eyes with refractory diabetic macular edema (DME) after three initial anti-VEGF injections in a real-world setting. METHODS: To be included in this retrospective multicenter, case-control study, eyes were required: (1) to present with early refractory DME, as defined by visual acuity (VA) gain ≤ 5 letters or reduction in central subfield thickness (CST) ≤ 20%, after a loading phase of anti-VEGF therapy (three monthly injections) and (2) to treat further with (a) anti-VEGF therapy or (b) DEX implant. Main outcome measures were change in visual acuity (VA) and central subfield thickness (CST) at 12 months. Due to imbalanced baseline characteristics, a matched anti-VEGF group was formed by only keeping eyes with similar baseline characteristics as those in the DEX group. RESULTS: A total of 110 eyes from 105 patients were included (anti-VEGF group: 72 eyes, DEX group: 38 eyes). Mean change in VA at 12 months was - 0.4 ± 10.8 letters (anti-VEGF group), and + 6.1 ± 10.6 letters (DEX group) (P = 0.004). Over the same period, mean change in CST was + 18.3 ± 145.9 µm (anti-VEGF group) and - 92.8 ± 173.6 µm (DEX group) (P < 0.001). Eyes in the DEX group were more likely to gain ≥ 10 letters (OR 3.71, 95% CI 1.19-11.61, P = 0.024) at month 12. CONCLUSIONS: In a real-world setting, eyes with DME considered refractory to anti-VEGF therapy after three monthly injections which were switched to DEX implant and had better visual and anatomical outcomes at 12 months than those that continued treatment with anti-VEGF therapy.

Idiopathic polypoidal choroidal vasculopathy in Thai patients with clinical and angiographic choroidal neovascularization.

OBJECTIVE: This study aimed to study the prevalence and characteristics of idiopathic polypoidal choroidal vasculopathy (IPCV) in Thai patients with clinical and angiographic choroidal neovascularization (CNV). PATIENTS AND METHODS: A consecutive case study of 140 patients presenting with CNV was conducted in nine large referral eye centers throughout Thailand. The demographic data, fundus photographs, fundus fluorescein angiography and indocyanine green angiography of the patients were analyzed. RESULTS: Of 129 patients with clinical and angiographic CNV, IPCV was diagnosed in 100 patients (77.52%), idiopathic CNVs in 16 patients (12.40%) and age-related macular degeneration (AMD) in 12 patients (9.30%). Of the 107 eyes with IPCV, 90 eyes (84.11%) had both branching venous networks (BVNs) and polypoidal lesions. Most IPCV patients (93%) had unilateral involvement and were at a younger age than AMD patients. In all, 79 eyes (73.83%) had lesions found in the macular area, 14 eyes (13.08%) in the temporal to vascular arcades, ten eyes (9.35%) in the peripapillary area and four eyes (3.74%) in both macular and peripapillary areas. The clinical manifestations of IPCV at presentation were categorized into two patterns. There were 95 eyes (88.79%) of a hemorrhagic pattern and 12 eyes (11.21%) of an exudative pattern. CONCLUSION: IPCV is the most common macular disease in Thai patients with CNV. Most IPCVs have both BVNs and polypoidal lesions located in the macular area and present with a hemorrhagic pattern.