DeepLensNet: Deep Learning Automated Diagnosis and Quantitative Classification of Cataract Type and Severity.

PURPOSE: To develop deep learning models to perform automated diagnosis and quantitative classification of age-related cataract from anterior segment photographs. DESIGN: DeepLensNet was trained by applying deep learning models to the Age-Related Eye Disease Study (AREDS) dataset. PARTICIPANTS: A total of 18 999 photographs (6333 triplets) from longitudinal follow-up of 1137 eyes (576 AREDS participants). METHODS: Deep learning models were trained to detect and quantify nuclear sclerosis (NS; scale 0.9-7.1) from 45-degree slit-lamp photographs and cortical lens opacity (CLO; scale 0%-100%) and posterior subcapsular cataract (PSC; scale 0%-100%) from retroillumination photographs. DeepLensNet performance was compared with that of 14 ophthalmologists and 24 medical students. MAIN OUTCOME MEASURES: Mean squared error (MSE). RESULTS: On the full test set, mean MSE for DeepLensNet was 0.23 (standard deviation [SD], 0.01) for NS, 13.1 (SD, 1.6) for CLO, and 16.6 (SD, 2.4) for PSC. On a subset of the test set (substantially enriched for positive cases of CLO and PSC), for NS, mean MSE for DeepLensNet was 0.23 (SD, 0.02), compared with 0.98 (SD, 0.24; P = 0.000001) for the ophthalmologists and 1.24 (SD, 0.34; P = 0.000005) for the medical students. For CLO, mean MSE was 53.5 (SD, 14.8), compared with 134.9 (SD, 89.9; P = 0.003) for the ophthalmologists and 433.6 (SD, 962.1; P = 0.0007) for the medical students. For PSC, mean MSE was 171.9 (SD, 38.9), compared with 176.8 (SD, 98.0; P = 0.67) for the ophthalmologists and 398.2 (SD, 645.4; P = 0.18) for the medical students. In external validation on the Singapore Malay Eye Study (sampled to reflect the cataract severity distribution in AREDS), the MSE for DeepSeeNet was 1.27 for NS and 25.5 for PSC. CONCLUSIONS: DeepLensNet performed automated and quantitative classification of cataract severity for all 3 types of age-related cataract. For the 2 most common types (NS and CLO), the accuracy was significantly superior to that of ophthalmologists; for the least common type (PSC), it was similar. DeepLensNet may have wide potential applications in both clinical and research domains. In the future, such approaches may increase the accessibility of cataract assessment globally. The code and models are available at https://github.com/ncbi/deeplensnet.

Selective laser trabeculoplasty vs micropulse laser trabeculoplasty in open-angle glaucoma.

AIM: The aim of this study was to prospectively compare the efficacy, safety, and tolerability of selective laser trabeculoplasty (SLT) vs micropulse laser trabeculoplasty (MLT) in reducing intraocular pressure (IOP) in open-angle glaucoma patients. PATIENTS AND METHODS: In all, 38 patients were randomized to 360° MLT and 31 patients were randomized to 360° SLT. IOP was measured at intervals of 1 hour and 1, 1-6, 6-12, 6-24, 24-36, and 36-52 weeks. Patients completed a survey 1 week after the procedure. Patients with end-stage, neovascular, uveitic, or angle-closure glaucoma were excluded. Treatment response was defined as an IOP reduction of ≥20.0% or ≥3 mmHg from baseline. RESULTS: IOP was lowered to ≥3 mmHg from baseline among 37.0% of the micropulse patients and 36.0% of patients in the selective laser group at 24-52 weeks. Similarly, 29.6% of the micropulse patients and 36.0% of the selective laser patients experienced a 20.0% IOP decrease from baseline during the 24-52-week interval (P=0.77). Both groups revealed similar reductions in IOP as absolute values and percentage decreases from baseline at all intervals up to 52 weeks post treatment. There were more treatment failures in the micropulse group up to 52 weeks post laser treatment; however, this was not statistically significant. The micropulse group reported less pain both during and after the procedure (P=0.005). CONCLUSION: Micropulse trabeculoplasty has demonstrated similar efficacy to SLT over a 52-week follow-up period with less discomfort experienced both during and after the procedure.

Corneal edema and keratitis following selective laser trabeculoplasty.

PURPOSE: To describe three cases of keratitis following Selective Laser Trabeculoplasty (SLT). OBSERVATIONS: Three females with a history of glaucoma presented with corneal edema, keratitis (endothelial, epithelial) and decreased visual acuity shortly after SLT. There was variable resolution of symptoms after starting treatment with oral antiherpetics and topical steroids. CONCLUSIONS AND IMPORTANCE: With the increase in usage of SLT as a treatment for glaucoma and subsequent reports of keratitis, it is imperative for ophthalmic surgeons to be aware of herpes simplex as a possible risk factor. Prompt treatment with antivirals and steroids can potentially prevent scarring and permanent damage to the cornea.

Marijuana Use Among Patients With Glaucoma in a City With Legalized Medical Marijuana Use.

IMPORTANCE: Previous research has shown several limitations associated with the use of marijuana as a treatment for glaucoma. However, little is known regarding patients' perceptions toward using marijuana for glaucoma and their intentions to use this therapeutic alternative. OBJECTIVE: To identify factors among patients with glaucoma that could lead to intentions to use marijuana for treatment. DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional survey study of 204 patients with glaucoma or suspected to have glaucoma was conducted at an academic-based glaucoma clinic in Washington, DC, between February 1 and July 31, 2013. Patients completed a self-administered survey assessing demographics, perceived severity of glaucoma, prior knowledge about marijuana use in glaucoma, past marijuana use, perceptions toward marijuana use (legality, systemic adverse effects, safety and effectiveness, and false beliefs), satisfaction with current glaucoma management, relevance of treatment costs, and intentions to use marijuana for glaucoma. Medical records were reviewed for disease severity. Data analysis was conducted from September 1, 2013, to September 30, 2015. MAIN OUTCOMES AND MEASURES: The main outcome was patients' intentions to use marijuana for glaucoma. Multiple linear regression analysis was conducted to identify factors associated with patients' intentions to use marijuana for glaucoma. RESULTS: Of the 334 patients who were invited to participate in the study, 204 (61.1%) completed the survey. About half the participants were women (104 [51.0]%), and 82 (40.2%) were white. Regression analysis of 204 respondents indicated that perceptions of legality of marijuana use (ß, 0.378; 95% CI, 0.205 to 0.444; P < .001), false beliefs regarding marijuana (ß, 0.323; 95% CI, 0.236 to 0.504; P < .001), satisfaction with current glaucoma care (ß, -0.222; 95% CI, -0.362 to -0.128; P < .001), and relevance of marijuana and glaucoma treatment costs (ß, 0.127; 95% CI, 0.008 to 0.210; P = .04) were significantly associated with intentions to use marijuana for glaucoma treatment after controlling for demographic variables, disease severity, and previous marijuana use. CONCLUSIONS AND RELEVANCE: This study's findings suggest a need for more education on this topic for ophthalmologists to be able to protect patients with glaucoma against the increased acceptability among the public of using marijuana based on false perceptions of its therapeutic value in glaucoma therapy. Considering the strong influence of perceptions of the legality of marijuana use on intentions to use this substance as a treatment for glaucoma, patient education might be particularly relevant in states in which marijuana use for glaucoma is legal, as in the case of the current study's setting.

Indirect cyclopexy for treatment of a chronic traumatic cyclodialysis cleft with hypotony.

Cyclodialysis cleft is a rare clinical finding and therefore, reports on surgical repair techniques in the literature are limited. Additionally, hypotony can make repair technically challenging. We share a novel, simple surgical approach to management of a case of chronic traumatic cyclodialysis cleft with a successful outcome.

Peripheral laser iridoplasty opens angle in plateau iris by thinning the cross-sectional tissues.

Plateau iris syndrome has been described as persistent angle narrowing or occlusion with intraocular pressure elevation after peripheral iridotomy due to the abnormal plateau iris configuration. Argon laser peripheral iridoplasty (ALPI) is an effective adjunct procedure to treat plateau iris syndrome. Classic theory suggests that the laser causes the contraction of the far peripheral iris stroma, "pulls" the iris away from the angle, and relieves the iris-angle apposition. We report a case of plateau iris syndrome that was successfully treated with ALPI. Spectral domain optical coherence tomography confirmed the angle was open at areas with laser treatment but remained appositionally closed at untreated areas. Further analysis suggested significant cross-sectional thinning of the iris at laser-treated areas in comparison with untreated areas. The findings indicate that APLI opens the angle, not only by contracting the iris stroma, but also by thinning the iris tissue at the crowded angle. This is consistent with the ALPI technique to aim at the iris as far peripheral as possible. This case also suggests that spectral domain optical coherence tomography is a useful adjunct imaging tool to gonioscopy in assessing the angle condition.