Purpose To investigate the correlation between choroidal thickness and myopia progression using a deep learning method. Methods Two data sets, data set A and data set B, comprising of 123 optical coherence tomography (OCT) volumes, were collected to establish the model and verify its clinical utility. The proposed mask region-based convolutional neural network (R-CNN) model, trained with the pretrained weights from the Common Objects in Context database as well as the manually labeled OCT images from data set A, was used to automatically segment the choroid. To verify its clinical utility, the mask R-CNN model was tested with data set B, and the choroidal thickness estimated by the model was also used to explore its relationship with myopia. Results Compared with the result of manual segmentation in data set B, the error of the automatic choroidal inner and outer boundary segmentation was 6.72 ± 2.12 and 13.75 ± 7.57 µm, respectively. The mean dice coefficient between the region segmented by automatic and manual methods was 93.87% ± 2.89%. The mean difference in choroidal thickness over the Early Treatment Diabetic Retinopathy Study zone between the two methods was 10.52 µm. Additionally, the choroidal thickness estimated using the proposed model was thinner in high-myopic eyes, and axial length was the most significant predictor. Conclusions The mask R-CNN model has excellent performance in choroidal segmentation and quantification. In addition, the choroid of high myopia is significantly thinner than that of nonhigh myopia. Translational Relevance This work lays the foundations for mask R-CNN models that could aid in the evaluation of more intricate changes occurring in chorioretinal diseases.

Background: Air tamponade’s effectiveness in treatment of rhegmatogenous retinal detachment (RRD) remains unclear. Objective: We aimed to review the surgical outcomes between air and gas tamponade after vitrectomy for RRD. Method: PubMed, Cochrane Library, EMBASE, and Web of Science were reviewed. The study protocol was registered in the International Prospective Register of Systematic Reviews (PROSPERO CRD42022342284). The primary outcome was the primary anatomical success after vitrectomy. The secondary outcome was the prevalence of postoperative ocular hypertension. Certainty of evidence was evaluated using the Grading of Recommendations Assessment, Development, and Evaluation system. Results: Ten studies involving 2677 eyes were included. One study was randomized, and the others were non-randomized. The primary anatomical success after vitrectomy was not significantly different between the air and gas groups (odds ratio [OR], 1.00; 95% confidence interval [CI], 0.68–1.48). The risk of ocular hypertension was significantly lower in the air group (OR, 0.14; 95% CI, 0.09–0.24). The certainty of evidence regarding air tamponade having an comparable anatomical outcome and lower frequency of postoperative ocular hypertension in treatment of RRD were low. Discussion: The current evidence base for tamponade selection in treatment of RRD has several major limitations. Further appropriately designed studies are needed to guide tamponade selection.

No abstract

No abstract

Background: Macular edema can be a cause of visual loss in eyes undergoing vitrectomy with epiretinal membrane(ERM) peeling. Objective: To evaluate the efficacy of combined vitrectomy with intravitreal corticosteroid injection for ERM. Methods: We conducted a systematic literature review by searching PubMed, Embase, and Medline up to December 2020 for studies that evaluated the effect of intravitreal corticosteroid injection during vitrectomy for ERM. Follow-up data on postoperative best-corrected visual acuity (BCVA) and central macular thickness (CMT) were collected and pooled using the standard mean deviation (SMD) with the corresponding 95% confidence interval (CI). Heterogeneity was statistically quantified using I2 statistics, and a meta-analysis was performed using a random-effects model. Results: Eight studies provided data on a total sample of 443 eyes. The meta-analysis revealed that concomitant intravitreal corticosteroid administration during vitrectomy contributed to a significant reduction in CMT than vitrectomy alone at 3 months after operation (pooled SMD = −0.353; 95% CI, −0.594 to −0.111; p = 0.004). However, between the two groups, no significant difference was found in CMT reduction at 1 and 6 months after operation and in postoperative BCVA improvement at 1, 3, and 6 months after operation. Conclusion: Combined treatment with vitrectomy and intravitreal corticosteroid injection may accelerate CMT reduction 3 months after ERM surgery. However, it did not result in a significant change in CMT and BCVA compared with vitrectomy alone at the end of follow-up.