Central serous chorioretinopathy (CSC) is a common condition characterized by serous detachment of the neurosensory retina at the posterior pole. We built a deep learning system model to diagnose CSC, and distinguish chronic from acute CSC using spectral domain optical coherence tomography (SD-OCT) images. Data from SD-OCT images of patients with CSC and a control group were analyzed with a convolutional neural network. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC) were used to evaluate the model. For CSC diagnosis, our model showed an accuracy, sensitivity, and specificity of 93.8%, 90.0%, and 99.1%, respectively; AUROC was 98.9% (95% CI, 0.983–0.995); and its diagnostic performance was comparable with VGG-16, Resnet-50, and the diagnoses of five different ophthalmologists. For distinguishing chronic from acute cases, the accuracy, sensitivity, and specificity were 97.6%, 100.0%, and 92.6%, respectively; AUROC was 99.4% (95% CI, 0.985–1.000); performance was better than VGG-16 and Resnet-50, and was as good as the ophthalmologists. Our model performed well when diagnosing CSC and yielded highly accurate results when distinguishing between acute and chronic cases. Thus, automated deep learning system algorithms could play a role independent of human experts in the diagnosis of CSC.
SFCT in eyes with RVO was significantly greater than it was in normal contralateral eyes. After Ozurdex injection, SFCT decreased significantly. Improvement in visual acuity was correlated with the decrease in SFCT after Ozurdex injection.
No consistent changes in choroidal thickness were observed after systemic high-dose corticosteroid treatment, but one patient with PED and thick choroid showed an increase in choroidal thickening as well as features of CSC. Thus, steroid-induced CSC may be an idiosyncratic response in selected vulnerable individuals rather than a dose-dependent effect.
Tubulointerstitial nephritis and uveitis (TINU) syndrome is a rare disease entity usually occurring in children. In the present study a case of TINU syndrome in an elderly patient is described and relevant literature is reviewed. A 61-year-old man presented with bilateral flank pain, urinary frequency, and foamy urine. A kidney ultrasonography revealed an increase in kidney parenchyma echogenicity. Following a kidney biopsy, the patient was diagnosed with acute tubulointerstitial nephritis. An ophthalmology examination initially performed for floater symptoms, revealed anterior uveitis in both eyes. Acute tubulointerstitial nephritis and anterior uveitis in both eyes responded to treatment with oral prednisolone, furosemide, carvedilol, and a topical steroid. TINU syndrome can occur in the elderly and should be part of the differential diagnosis when seeing a patient who has uveitis in association with renal disease; any therapy should be managed by both an internist and an ophthalmologist.
Diagnostic monocular occlusion could be useful in patients with DE-type or CI-type exotropia and with hyperopia. In other cases, however, it has a limited role in determining the maximum angle of exodeviation compared with multiple examinations.
PurposeTo compare the accuracy of intraocular lens (IOL) power calculation using conventional regression formulae or the American Society of Cataract and Refractive Surgery (ASCRS) IOL power calculator for previous corneal refractive surgery.MethodsWe retrospectively reviewed 96 eyes from 68 patients that had undergone cataract surgery after keratorefractive surgeries. We calculated the formula with two approaches: IOL powers using the ASCRS IOL power calculator and IOL powers using conventional formulae with previous refractive data (Camellin, Jarade, Savini, and clinical history method) or without prior data (0, 2 and, 4 mm total mean power in topography, Wang-Koch-Maloney, Shammas, Seitz, and Maloney). Two conventional IOL formulae (the SRK/T and the Hoffer Q) were calculated with the single K and double K methods. Mean arithmetic refractive error and mean absolute error were calculated at the first postoperative month.ResultsIn conventional formulae, the Jarade method or the Seitz method, applied in the Hoffer Q formula with the single K or double K method, have the lowest prediction errors. The least prediction error was found in the Shammas-PL method in the ASCRS group. There was no statistically significant difference between the 10 lowest mean absolute error conventional methods, the Shammas-PL method and the Barrett True-K method calculated with using the ASCRS calculator, without using preoperative data.ConclusionsThe Shammas-PL formula and the Barrett True-K formula, calculated with the ASCRS calculator, without using history, were methods comparable to the 10 most accurate conventional formulae. Other methods using the ASCRS calculator show a myopic tendency.
This cross-sectional study aimed to build a deep learning model for detecting neovascular age-related macular degeneration (AMD) and to distinguish retinal angiomatous proliferation (RAP) from polypoidal choroidal vasculopathy (PCV) using a convolutional neural network (CNN). Patients from a single tertiary center were enrolled from January 2014 to January 2020. Spectral-domain optical coherence tomography (SD-OCT) images of patients with RAP or PCV and a control group were analyzed with a deep CNN. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC) were used to evaluate the model’s ability to distinguish RAP from PCV. The performances of the new model, the VGG-16, Resnet-50, Inception, and eight ophthalmologists were compared. A total of 3951 SD-OCT images from 314 participants (229 AMD, 85 normal controls) were analyzed. In distinguishing the PCV and RAP cases, the proposed model showed an accuracy, sensitivity, and specificity of 89.1%, 89.4%, and 88.8%, respectively, with an AUROC of 95.3% (95% CI 0.727–0.852). The proposed model showed better diagnostic performance than VGG-16, Resnet-50, and Inception-V3 and comparable performance with the eight ophthalmologists. The novel model performed well when distinguishing between PCV and RAP. Thus, automated deep learning systems may support ophthalmologists in distinguishing RAP from PCV.
Bilateral same-day intravitreal injections drawn from a single vial using separate syringes or needles are well tolerated by patients, and its safety profile may be equivalent to unilateral injections. The bacterial molecular surveillance system using eubacterial PCR demonstrated the safety of bilateral same-day intravitreal injections and may be used for safety surveillance and for timely intervention of possible drug-related endophthalmitis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.