Radiology services encountering the coronavirus disease-19 pandemic will need to modify their daily operational practices. • Leadership, patient risk stratification, adequate manpower, operational workflow clarity, and workplace/social responsibility will help Radiology services safely and sustainably deal with the current disease outbreak.OBJECTIVES To develop and evaluate the performance of a deep learning-based system for automatic patellar height measurements using knee radiographs. METHODS The deep learning-based algorithm was developed with a data set consisting of 1018 left knee radiographs for the prediction of patellar height parameters, specifically the Insall-Salvati index (ISI), Caton-Deschamps index (CDI), modified Caton-Deschamps index (MCDI), and Keerati index (KI). The performance and generalizability of the algorithm were tested with 200 left knee and 200 right knee radiographs, respectively. The intra-class correlation coefficient (ICC), Pearson correlation coefficient, mean absolute difference (MAD), root mean square (RMS), and Bland-Altman plots for predictions by the system were evaluated in comparison with manual measurements as the reference standard. RESULTS Compared with the reference standard, the deep learning-based algorithm showed high accuracy in predicting the ISI, CDI, and KI (left knee ICC = 0.91-0.95, r = 0.84-mance to radiologists in measuring ISI, CDI, and KI.PURPOSE To evaluate the ablation zone diameter (AZD) using six modes of corneal topography after small-incision lenticule extraction (SMILE) and femtosecond laser-assisted in situ keratomileusis (FS-LASIK) for myopia and to compare the programmed and postoperative AZDs METHODS This retrospective comparative study included 86 right eyes in 86 patients who underwent SMILE or FS-LASIK at the Shandong Eye Institute between June 2016 and August 2017. Data were collected preoperatively and at 1, 3, and 6 months postoperatively using the Pentacam system. The AZD was determined using six modes of corneal topography postoperative axial curvature topography (PACT), postoperative tangential curvature topography (PTCT), difference-axial curvature topography (DACT), difference-tangential curvature topography (DTCT), postoperative front elevation topography (PFET), and difference-corneal thickness topography (DCTT). The difference between the programmed and postoperative AZDs was compared between the groups of two surgical procedures. RESULTS At 3 months, the AZDs measured by PTCT, DTCT, and PFET after SMILE showed a significant decrease, while the AZD by DACT revealed an increase (P  0.75). CONCLUSIONS In the treatment of myopia, the achieved topographic ablation zones after FS-LASIK were smaller than the theoretically designed ones. The AZDs after SMILE were larger than those after FS-LASIK, with an equivalent programmed value. The DACT may be more suitable for measuring postoperative ablation zones in clinic with clearer borders and favorable repeatability. This method may be potential for the measurement of ablation zones and further research on the visual quality after refractive surgery.PURPOSE There is an urgent need to address how to best provide ophthalmic care for patients with retinal disease receiving intravitreal injections with anti-vascular endothelial growth factor agents during the ongoing global COVID-19 pandemic. This article provides guidance for ophthalmologists on how to deliver the best possible care for patients while minimizing the risk of infection. METHODS The Vision Academy’s Steering Committee of international retinal disease experts convened to discuss key considerations for managing patients with retinal disease during the COVID-19 pandemic. After reviewing the existing literature on the issue, members put forward recommendations that were systematically refined and voted on to develop this guidance. RESULTS The considerations focus on the implementation of steps to minimize the exposure of patients and healthcare staff to COVID-19. These include the use of personal protective equipment, adherence to scrupulous hygiene and disinfection protocols, pre-screening to identify symptomatic patients, and reducing the number of people in waiting rooms. Other important measures include triaging of patients to identify those at the greatest risk of irreversible vision loss and prioritization of treatment visits over monitoring visits where possible. this website In order to limit patient exposure, ophthalmologists should refrain from using treatment regimens that require frequent monitoring. CONCLUSION Management of patients with retinal disease receiving intravitreal injections during the COVID-19 pandemic will require adjustment to regular clinical practice to minimize the risk of exposure of patients and healthcare staff, and to prioritize those with the greatest medical need. The safety of patients and healthcare staff should be of paramount importance in all decision-making.OBJECTIVE To evaluate the impact of selected clinical parameters on the mid-/long-term visual outcome of patients with acute retinal necrosis (ARN) DESIGN A retrospective cohort study METHODS SETTING Two University Hospitals (Parma, Italy; Lausanne, Switzerland). PARTICIPANTS Thirty-nine non-HIV patients (39 eyes) with ARN, as confirmed by polymerase chain reaction on intraocular samples. The following potential predictors were tested using linear regression models age, sex, etiology, best-corrected visual acuity (BCVA) on admission, delay between ARN symptom onset and treatment initiation, and surgery (performed or not). MAIN OUTCOME BCVA at the final follow up RESULTS Thirty-nine of 39 non-HIV patients (22 men and 17 women; mean age, 50 years) diagnosed with ARN were enrolled in the study. Etiologies were varicella-zoster virus in 25 eyes (64%), herpes simplex viruses in the remaining 14 eyes. The average follow-up duration was 19 ± 13 months. All patients had undergone systemic antivirals; surgery was performed in 16 eyes. The mean delay between onset of visual symptoms and antiviral treatment initiation was 15 ± 31 days (range, 1-180 days). The mean BCVA at baseline was 0.83 ± 0.75 logMAR, while the mean final BCVA was 0.75 ± 0.81 logMAR. Both initial BCVA and treatment delay (TD) were significantly correlated with the final BCVA (p  less then  0.05). CONCLUSIONS Initial BCVA and TD seem to be significant predictors of mid-/long-term visual outcome in non-HIV patients affected by ARN.