Classifying neovascular age-related macular degeneration with a deep convolutional neural network based on optical coherence tomography images.

Neovascular age-related macular degeneration (nAMD) is among the main causes of visual impairment worldwide. We built a deep learning model to distinguish the subtypes of nAMD using spectral domain optical coherence tomography (SD-OCT) images. Data from SD-OCT images of nAMD (polypoidal choroidal vasculopathy, retinal angiomatous proliferation, and typical nAMD) and normal healthy patients were analyzed using a convolutional neural network (CNN). The model was trained and validated based on 4749 SD-OCT images from 347 patients and 50 healthy controls. To adopt an accurate and robust image classification architecture, we evaluated three well-known CNN structures (VGG-16, VGG-19, and ResNet) and two customized classification layers (fully connected layer with dropout vs. global average pooling). Following the test set performance, the model with the highest classification accuracy was used. Transfer learning and data augmentation were applied to improve the robustness and accuracy of the model. Our proposed model showed an accuracy of 87.4% on the test data (920 images), scoring higher than ten ophthalmologists, for the same data. Additionally, the part that our model judged to be important in classification was confirmed through Grad-CAM images, and consequently, it has a similar judgment criteria to that of ophthalmologists. Thus, we believe that our model can be used as an auxiliary tool in clinical practice.

Non-ICGA treatment criteria for Suboptimal Anti-VEGF Response for Polypoidal Choroidal Vasculopathy: APOIS PCV Workgroup Report 2.

PURPOSE: To develop and validate OCT and color fundus photography (CFP) criteria in differentiating polypoidal choroidal vasculopathy (PCV) from typical neovascular age-related macular degeneration (nAMD) in eyes with suboptimal response to anti-vascular endothelial growth factor (VEGF) monotherapy and to determine whether OCT alone can be used to guide photodynamic therapy (PDT) treatment. DESIGN: Clinical study evaluating diagnostic accuracy. PARTICIPANTS: Patients with nAMD who received 3-month anti-VEGF monotherapy but had persistent activity defined as subretinal fluid or intraretinal fluid at month 3 assessments. METHODS: In phase 1, international retina experts evaluated OCT and CFP of eyes with nAMD to identify the presence or absence of features due to PCV. The performance of individual and combinations of these features were compared with ICGA. In phase 2, these criteria were applied to an independent image set to assess generalizability. In a separate exercise, retinal experts drew proposed PDT treatment spots using only OCT and near-infrared (NIR) images in eyes with PCV and persistent activity. The location and size of proposed spot were compared with ICGA to determine the extent of coverage of polypoidal lesions (PLs) and branching neovascular network (BNN). MAIN OUTCOME MEASURES: Sensitivity and specificity of CFP and OCT criteria to differentiate PCV from nAMD and accuracy of coverage of OCT-guided PDT compared with ICGA. RESULTS: In eyes with persistent activity, the combination of 3 non-ICGA-based criteria (sharp-peaked pigment epithelial detachment [PED], subretinal pigment epithelium [RPE] ring-like lesion, and orange nodule) to detect PCV showed good agreement compared with ICGA, with an area under the receiver operating characteristic curve of 0.85. Validation using both an independent image set and assessors achieved an accuracy of 0.77. Compared with ICGA, the OCT-guided PDT treatment spot covered 100% of PL and 90% of the BNN. CONCLUSIONS: In nAMD eyes with persistent activity, OCT and CFP can differentiate PCV from typical nAMD, which may allow the option of adjunct PDT treatment. Furthermore, OCT alone can be used to plan adjunct PDT treatment without the need for ICGA, with consistent and complete coverage of PL.

A Validation Study of the Revised Diagnostic Criteria from the International Workshop on Ocular Sarcoidosis at a Single Institute in Japan.

Purpose: To validate the revised criteria of the International Workshop on Ocular Sarcoidosis (IWOS) for the diagnosis of ocular sarcoidosis (OS).Methods: A retrospective chart review study was performed on 323 patients including 51 patients with biopsy-proven sarcoidosis and 272 patients with other uveitis entities. Data on intraocular signs and systemic investigations were collected, and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the Youden index were calculated.Results: All intraocular signs and most systemic investigations showed high diagnostic parameters. Sensitivity, specificity, PPV, and NPV of the revised IWOS criteria were 1.000, 0.930, 0.728, and 1.000, respectively. Presumed or probable OS showed lower sensitivity and higher specificity when compared with the best Youden index.Conclusion: The revised IWOS criteria are useful in Japanese patients, but could possibly be improved by modifying the criterion of presumed or probable OS.

Comparison of ice pack test and single-fiber EMG diagnostic accuracy in patients referred for myasthenic ptosis.

OBJECTIVE: To compare the diagnostic accuracy of ice pack test (IPT) and single-fiber EMG (SF-EMG) in patients with suspected ocular myasthenia (OM) presenting with ptosis. METHODS: We studied consecutive patients referred for the clinical suspicion of OM. Patients underwent IPT and stimulated SF-EMG on the orbicularis oculi muscle. Receiver operating characteristic curve analysis was performed to determine the accuracy of IPT, SF-EMG, and their combination. RESULTS: We included 155 patients, 102 with OM and 53 with other diagnosis (OD). The IPT had a sensitivity of 86% (95% confidence interval [CI] 79-93) and a specificity of 79% (95% CI 68-90). SF-EMG showed a sensitivity of 94% (95% CI 89-98) and a specificity of 79% (95% CI 68-90). Overall, IPT and SF-EMG showed discordant results in 30 cases, 16 OM and 14 OD. The combination of IPT and SF-EMG, using the positivity of at least one test for OM diagnosis, increased the sensitivity to 98% (95% CI 95-100), reducing the specificity to 66% (95% CI 53-78), whereas using the positivity of both tests, we obtained a sensitivity of 82% (95% CI 75-90) and a specificity of 92% (95% CI 85-99). The negativity of both tests had a 94% (95% CI 87-100) negative predictive value. Comparison of the areas under the curve showed no differences in the diagnostic accuracy of IPT, SF-EMG, and their combinations. CONCLUSIONS: IPT and SF-EMG have similar diagnostic accuracy in patients with OM presenting with ptosis. The negativity of both tests strongly suggests another diagnosis. CLASSIFICATION OF EVIDENCE: This study provides Class I evidence that both the IPT and SF-EMG accurately identify patients with OM.

Virtual Visits in Ophthalmology: Timely Advice for Implementation During the COVID-19 Public Health Crisis.

Virtual visits (VVs) are necessitated due to the public health crisis and social distancing mandates due to COVID-19. However, these have been rare in ophthalmology. Over 3.5 years of conducting >350 ophthalmological VVs, our group has gained numerous insights into best practices. This communication shares these experiences with the medical community to support patient care during this difficult time and beyond. We highlight that mastering the technological platform of choice, optimizing lighting, camera positioning, and "eye contact," being thoughtful and creative with the virtual eye examination, and ensuring good documenting and billing will make a successful and efficient VV. Moreover, we think these ideas will stimulate further VV creativity and expertise to be developed in ophthalmology and across medicine. This approach, holds promise for increasing its adoption after the crisis has passed.

Care of ophthalmological patients during the COVID-19 pandemic: A rapid scoping review. / Atención de pacientes oftalmológicos durante la pandemia COVID-19: revisión panorámica rápida.

INTRODUCTION: A new type of coronavirus (SARS-CoV-2) causes a respiratory distress syndrome that has been called COVID-19 and has generated an unprecedented pandemic. Serious complications include pneumonia, and mortality ranges from 2 to 5%. Until March 26, the World Health Organization reports 462 684 confirmed cases and 20 834 deaths worldwide. Dissemination occurs from aerosols or respiratory droplets. Different scientific societies have published clinical practice guidelines regarding ophthalmic care in the COVID-19 pandemic, but the information is presented inconsistently, which makes decision-making difficult. METHODS: We conducted a sensitive bibliographic search in EMBASE and ophthalmic society webpages, of the clinical practice guidelines of ophthalmic care in pandemic COVID-19. We extracted the recommendations, organizing them into three categories: "Which patients to attend", "How should the clinic work", and "What interventions should be avoided". For each guideline, we assessed whether the search was systematic and whether the Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology was followed. RESULTS: Fourteen relevant articles were found. Fifty-one recommendations were extracted and are shown in a summary table. None are based on a systematic search for evidence, nor do any use GRADE to develop the recommendations. CONCLUSIONS: The clinical practice guidelines that we reviewed all recommend rescheduling all non-urgent consultations and surgeries, reinforcing contact precautions, the use of personal protection elements, and the disinfection of surfaces and instruments. The guidelines should be improved by incorporating systematic searches for evidence, using GRADE for recommendations, and Appraisal of Guidelines for Research and Evaluation (AGREE II) for reporting.

INTRODUCCIÓN: Un nuevo tipo de coronavirus, denominado SARS­CoV-2, puede provocar patología respiratoria, denominada COVID-19, y ha generado una pandemia sin precedentes. Las complicaciones graves incluyen neumonía y la mortalidad oscila entre un 2 a un 5%. Hasta el 26 de marzo de 2020 la OMS informó 462 684 casos confirmados, y 20 834 muertes en todo el mundo. Se transmite por aerosoles o gotitas respiratorias. Distintas sociedades científicas han publicado guías de práctica clínica respecto a la atención oftalmológica en pandemia COVID-19. Cada una expone la información de manera diferente, lo que dificulta la toma de decisiones. MÉTODOS: Realizamos una búsqueda bibliográfica sensible en EMBASE y dirigida en sociedades oftalmológicas de guías de práctica clínica de atención oftalmológica en pandemia COVID-19. Extrajimos las recomendaciones, organizándolas en tres categorías: "qué pacientes tratar", "funcionamiento del policlínico y consulta" y "qué intervenciones evitar". En cada una se evaluó la búsqueda sistemática de evidencia y el uso en las recomendaciones de metodología Appraisal of Guidelines for Research and Evaluation, GRADE. RESULTADOS: Se encontraron 14 artículos relevantes. Se extrajeron 51 recomendaciones, elaborando una tabla resumen. Ninguna efectuó búsqueda sistemática de evidencia, ni incorporó GRADE en las recomendaciones. CONCLUSIONES: Las guías de práctica clínica revisadas comparten los principios generales de reprogramar toda consulta y cirugía no urgente, reforzando las precauciones de contacto, el uso de elementos de protección personal y desinfección de superficies e instrumentos. Se deben mejorar las guías de práctica clínica incorporando búsquedas sistemáticas de evidencia, usando metodología GRADE para las recomendaciones y Appraisal of Guidelines for Research and Evaluation (AGREE II) para el reporte.

Examination Practices and Referral of Patients With Diabetic Retinopathy by Optometrists in Routine Clinical Care.

BACKGROUND AND OBJECTIVE: To analyze the examination practices and referral of patients with diabetic retinopathy (DR) by optometrists in routine clinical care. PATIENTS AND METHODS: Diabetic patient records from 2012 to 2018 were retrospectively reviewed for documentation of dilated fundus exam (DFE), imaging, follow-up appointments, and referrals. Concordance between clinical exam and coding was also analyzed. RESULTS: For 97.8% of encounters, DFE was performed, the patient was referred for DFE, or DFE was scheduled for follow-up. When DFE was performed at the initial visit, this resulted in referral of 19.8% of patients to an ophthalmologist. Imaging was obtained occasionally, with fundus photos in 2.6% and optical coherence tomography in 14.5% of encounters. Concordance of DR grading between exam and coding was 78.8%. Recommended follow-up times were incorrect based on DR severity level in 13.8% of encounters. CONCLUSION: Although DFE was performed reliably by optometrists, utilization of imaging, DR grading and coding, and appropriate follow-up periods could be improved. [Ophthalmic Surg Lasers Imaging Retina. 2019;50:608-612.].

Screening for Myopia-Related Retinal Changes Among Teenagers.

BACKGROUND AND OBJECTIVE: To evaluate the relationship between spherical equivalent (SE) refractive error and myopia-related peripheral retinal changes (MPRCs) and to find the optimal cutoff for screening myopic teenagers. PATIENTS AND METHODS: The study included 2,286 myopic subjects who had a dilated fundus examination between 1998 and 2011 and SE of -4.0 diopters (D) or higher in both eyes. RESULTS: Ninety-five subjects (4.16%) had MPRCs. Two subjects (0.09%) had moderate-to-severe MPRCs. A significant correlation (P < .0001) between SE and MPRC was found. The highest sum of sensitivity (72.63%) and specificity (73.44%) was achieved when a SE of -6.25 D in the more myopic eye was utilized as the cutoff. CONCLUSIONS: SE and MPRCs are highly associated. The optimal cutoff to detect MPRC in teenagers is -6.25 D. However, using a SE of -4.0 D as the cutoff may be the practical choice for screening due to the noninvasiveness nature and low cost of the examination. [Ophthalmic Surg Lasers Imaging Retina. 2019;50:e311-e319.].

Approche diagnostique et thérapeutique de la vasculopathie polypoïdale choroïdienne. Recommandations de la Fédération France Macula.

PURPOSE: To update the medical literature on the diagnostic and therapeutic approach to polypoidal choroidal vasculopathy (PCV) and to propose a treatment algorithm in agreement with French market approval, supported by the France Macula Federation (FFM). METHODS: Literature review and expert opinion. RESULTS: The diagnosis of PCV is based on multimodal imaging, including indocyanine green angiography (ICGA), which is considered the gold standard for the diagnosis of PCV. Regarding the therapeutic management of PCV, the FFM recommends treating PCV first-line either by monotherapy with intra-vitreal anti-vascular endothelial growth factor (anti-VEGF) injections, or by a combined treatment of photodynamic therapy (PDT) with Verteporfin and intra-vitreal anti-VEGF injections, depending on the location of the PCV.

Screening Criteria for Detecting Severe Ocular Injuries in the Setting of Orbital Fractures.

PURPOSE: Define incidence of severe ocular trauma in orbital fracture patients and determine if ocular signs and symptoms are useful predictors of severe ocular injuries. METHODS: Retrospective chart review was performed on all patients with orbital fractures between April 1, 2013, and December 31, 2014. Patients were included if they had radiographic evidence of acute fracture of at least one orbital wall and were evaluated by the Ophthalmology service. Demographics, concurrent injury data, and symptoms and signs of ocular trauma were collected. Concurrent ocular injuries were grouped by severity. Predictive signs or symptoms for severe ocular trauma were identified by stepwise logistic regression analysis. The threshold point for predictive signs and symptoms was detected by a receiver operating characteristic (ROC). RESULTS: Five-hundred-twelve patients were included. The most common mechanisms of injury were assault (39%), fall (25%), and motor vehicle accident (21%). The incidence of any concurrent ocular trauma was 75% (383/512), with 14% (70/512) being severe. Four signs and symptoms were predictors of severity: blurred vision (P < 0.0001), pain with eye movements (P < 0.0001), visual acuity worse than 20/40 in the ipsilateral eye (P < 0.001), and restricted motility (P < 0.001). The presence of 2 or more of these signs or symptoms was predictive of severe ocular trauma with high sensitivity (91%) and specificity (86%). CONCLUSIONS: In cooperative patients with acute orbital wall fractures, the presence of 2 or more signs or symptoms is predictive of severe ocular trauma and necessitates the need for urgent ophthalmic consultation.Severe ocular injury associated with orbital wall fracture is more likely in patients with 2 or more ophthalmic signs or symptoms.

Revised criteria of International Workshop on Ocular Sarcoidosis (IWOS) for the diagnosis of ocular sarcoidosis.

AIMS: International criteria for the diagnosis of ocular sarcoidosis (OS) was established by the first International Workshop on Ocular Sarcoidosis (IWOS) and validations studies revealed certain limitations of the criteria. To overcome the limitations, revised IWOS criteria was established in an international meeting. This manuscript was aimed at reporting the revised IWOS criteria. METHODS: A consensus workshop was carried out to discuss and revise the IWOS criteria. The workshop was held on 27 April 2017, in Nusa Dua, Bali, Indonesia. Prior to the workshop, a questionnaire proposing revised criteria and consisting of one item for differential diagnosis, seven items for ocular clinical signs, 10 items for systemic investigations and three categories of diagnostic criteria was circulated to 30 uveitis specialists. Questionnaire items with over 75% support were taken as consensus agreement; items with below 50% support were taken as consensus disagreement and items with 50%-75% support were discussed at the workshop. Of the latter items, those supported by two-thirds majority in the workshop were taken as consensus agreement. RESULTS: The survey and subsequent workshop reached consensus agreements of the revised criteria for the diagnosis of OS as follows: (1) other causes of granulomatous uveitis must be ruled out; (2) seven intraocular clinical signs suggestive of OS; (3) eight results of systemic investigations in suspected OS and (4) three categories of diagnostic criteria depending on biopsy results and combination of intraocular signs and results of systemic investigations. CONCLUSIONS: Revised IWOS criteria were proposed by a consensus workshop.

[Update from France Macula Federation: Diagnosis of wet AMD]. / Actualisations de la Fédération France Macula : diagnostic de la DMLA exsudative.

PURPOSE: To update the recommendations of the France Macula Federation for the diagnosis of wet age-related macular degeneration (AMD). METHODS: Analysis of literature and expert opinion. RESULTS: The FMF recommends diagnosing wet AMD by combining the results of fundus examination (or color or monochromatic fundus photographs), optical coherence tomography (OCT) showing exudative signs, and morphological visualization of the neovascular membrane, which may be obtained non-invasively (OCT-angiography) or invasively (fluorescein and/or indocyanine green angiography). Under optimal conditions in which all these tools are available, the FMF recommends using non-invasive methods as first-line tools and resorting to dye angiography if diagnostic doubt remains. CONCLUSION: As observed in other fields of medical imaging, non-invasive methods are preferred to invasive methods for the diagnosis of wet AMD, while the latter are reserved for more difficult cases.

[Evaluation of the nurse triage at the ophtalmology emergency department of Pierre-Paul-Riquet Hospital]. / Évaluation du questionnaire de tri infirmier aux urgences ophtalmologiques de l'hôpital Pierre-Paul-Riquet au CHU de Toulouse.

INTRODUCTION: The steady increase in the number of visits to the various emergency services combined with the decrease in medical demographics, make it necessary to optimize triage of patients to improve their care. The purpose of this study was to evaluate the pertinence of our triage questionnaire in the classification of ophthalmologic emergencies by severity. METHODS: We used a monocentric cross-sectional study. From September 5 through September 25 2017, 858 patients who had all been seen in the ophthalmology emergency department of Pierre Paul Riquet Hospital of Toulouse university medical center and had responded to the triage nurse questionnaire were included. According to the symptoms presented or not by the patient, a color code was attributed (GREEN, ORANGE or RED) in order of increasing level of emergency. For each patient, we compared the severity of the final diagnosis by Base Score with the level of emergency established by our questionnaire. RESULTS: There were 118 "GREEN" patients, 606 "ORANGE" patients and 134 "RED." We were able to analyze 822 patients. 21.65% of patients were correctly classified, 73.36% were overestimated (of which 87.06% by one level and 12.94% by two levels of severity), and 4.99% were underestimated (of which 90.24% by one level and 9.76% by two levels). CONCLUSION: Our current triage questionnaire is not sufficiently discriminating for effective triage of ophthalmologic emergencies. It often overestimates minor emergencies, causing a delay in treating other emergencies. We propose a new questionnaire modified according to the results obtained during our study.

Utility of the optical quality analysis system for decision-making in cataract surgery.

BACKGROUND: A cataract is a common cause of vision impairment that requires surgery in older subjects. The Optical Quality Analysis System (OQAS, Visiometrics SL, Terrassa, Spain) assesses the optical quality of the eye in cataract patients. This study shows the role of the optical quality evaluation system for decision-making in cataract surgery. We investigated the clinical utility of the OQAS for decision-making in cataract surgery. METHODS: Sixty-seven eyes from 67 patients undergoing cataract surgery and 109 eyes from 109 control subjects were compared. The best corrected visual acuity (BCVA) was measured. The objective scatter index (OSI), modulation transfer function (MTF), Strehl ratio, predicted visual acuity (PVA) 100%, PVA 20%, and PVA 10% were measured using the OQAS. The sensitivity and specificity of the different parameters were analyzed using the receiver operating characteristic (ROC) curve. The main parameters measured were sensitivity and specificity. RESULTS: The BCVA, OSI, PVA 100%, PVA 20%, and PVA 10% were higher in the cataract group compared to those in the control group, while the MTF and Strehl ratios were lower (p <  0.001 for all). ROC analysis showed that the OSI had the largest area under the curve and that the sensitivity and specificity of the OSI were 83.9 and 84.6%, respectively, at the optimal cut-off point of 2.35. CONCLUSION: The MTF, OSI, Strehl ratio, PVA 100%, PVA 20% and PVA 10% may be useful parameters for preoperative decision-making in cataract surgery. The OSI appears to be the most effective parameter for this purpose.

Analysis of cases and accuracy of 3 risk scoring systems in predicting ectasia after laser in situ keratomileusis.

PURPOSE: To identify risk factors for ectasia after laser in situ keratomileusis (LASIK) by comparing the accuracy of the Ectasia Risk Score System (ERSS), Screening Corneal Objective Risk of Ectasia (SCORE) Analyzer, and percentage of tissue altered (PTA) in predicting the occurrence of ectasia. SETTING: Multiple centers in 8 countries. DESIGN: Retrospective case series. METHODS: Previously unpublished post-LASIK ectasia cases were analyzed. Consecutive patients who had LASIK performed at least 5 years previously with no resultant ectasia were used as controls. Axial maps from preoperative Orbscan IIz topographies were analyzed in a masked fashion, and examination files tested with the SCORE Analyzer. The PTA values and ERSS scores were generated using available preoperative and perioperative data. Only eyes with subjectively identified normal preoperative topography were tested with the PTA. Threshold values for the SCORE, ERSS, and PTA were more than or equal to 0, 4, and 40, respectively. RESULTS: Ectasia occurred in 31 eyes (22 patients); 79 eyes (44 patients) were used as controls. In all eyes, the sensitivity and specificity for predicting ectasia, respectively, were 67.7% and 79.7% for the ERSS and 64.5% and 100% for the SCORE. In eyes with normal topography (ectasia group, 12 eyes; controls, 64 eyes), the PTA yielded sensitivity of 33.3% and specificity of 85.9%. The area under the receiver operating characteristic curve was highest for SCORE (0.911) followed by the ERSS (0.844) and PTA (0.557). CONCLUSIONS: The SCORE was most predictive of ectasia, achieving the best specificity; the ERSS had the best sensitivity. Further studies are required to validate the PTA as a screening metric for ectasia.