Introduction Compared with traditional fundus examination techniques, ultra-widefield fundus (UWF) images provide 200° panoramic images of the retina, which allows better detection of peripheral retinal lesions. The advent of UWF provides effective solutions only for detection but still lacks efficient diagnostic capabilities. This study proposed a retinal lesion detection model to automatically locate and identify six relatively typical and high-incidence peripheral retinal lesions from UWF images which will enable early screening and rapid diagnosis. Methods A total of 24,602 augmented ultra-widefield fundus images with labels corresponding to 6 peripheral retinal lesions and normal manifestation labelled by 5 ophthalmologists were included in this study. An object detection model named You Only Look Once X (YOLOX) was modified and trained to locate and classify the six peripheral retinal lesions including rhegmatogenous retinal detachment (RRD), retinal breaks (RB), white without pressure (WWOP), cystic retinal tuft (CRT), lattice degeneration (LD), and paving-stone degeneration (PSD). We applied coordinate attention block and generalized intersection over union (GIOU) loss to YOLOX and evaluated it for accuracy, sensitivity, specificity, precision, F 1 score, and average precision (AP). This model was able to show the exact location and saliency map of the retinal lesions detected by the model thus contributing to efficient screening and diagnosis. Results The model reached an average accuracy of 96.64%, sensitivity of 87.97%, specificity of 98.04%, precision of 87.01%, F 1 score of 87.39%, and mAP of 86.03% on test dataset 1 including 248 UWF images and reached an average accuracy of 95.04%, sensitivity of 83.90%, specificity of 96.70%, precision of 78.73%, F 1 score of 81.96%, and mAP of 80.59% on external test dataset 2 including 586 UWF images, showing this system performs well in distinguishing the six peripheral retinal lesions. Conclusion Focusing on peripheral retinal lesions, this work proposed a deep learning model, which automatically recognized multiple peripheral retinal lesions from UWF images and localized exact positions of lesions. Therefore, it has certain potential for early screening and intelligent diagnosis of peripheral retinal lesions. Supplementary Information The online version contains supplementary material available at 10.1007/s40123-023-00651-x.
Purpose: To compare the efficacy and safety of the intravitreal dexamethasone (DEX) implant for the treatment of diabetic macular edema (DME) in vitrectomized and nonvitrectomized eyes.Methods: We performed a literature search in four electronic databases (PubMed, EMBASE, MEDLINE, and Cochrane Library) from inception to 22 May 2022. Studies comparing the efficacy of the DEX implant in vitrectomized and nonvitrectomized eyes with DME with at least 3 months of follow-up were included. The main outcomes included comparison of the mean change in the best-corrected visual acuity (BCVA) and central macular thickness (CMT) from baseline to different follow-up endpoints between the vitrectomized and nonvitrectomized groups. The secondary outcomes were the mean duration of action for the first DEX implantation and the number of required injections throughout the follow-up period. Safety data were collected and compared.Results: The final analysis included 7 studies involving 582 eyes, 208 vitrectomized eyes and 374 nonvitrectomized eyes. The mean between-group differences in BCVA improvement were not significant at any endpoint, with averages difference of −0.07 logarithm of the minimum angle of resolution (logMAR) (p = 0.088) at 1 month, −0.03 logMAR (p = 0.472) 3 months, −0.07 logMAR (p = 0.066) 6 months, and −0.04 logMAR (p = 0.486) 12 months. The mean between-group differences in CMT reduction were not statistically significant, with mean differences of 7.17 μm (p = 0.685) at 1 month, 20.03 μm (p = 0.632) 3 months, −1.80 μm (p = 0.935) 6 months, and −25.65 μm (p = 0.542) 12 months. However, the vitrectomized group had a significantly shorter duration of action during the first DEX implantation than the nonvitrectomized group, with a mean difference of 0.8 months (p = 0.005). No significant between-group differences were detected for the number of required injections or safety profile.Conclusion: This meta-analysis showed similar efficacy and safety of the sustained-release DEX intravitreal implant for vitrectomized and nonvitrectomized eyes with DME. The intravitreal DEX implant could be considered an effective choice for DME treatment in eyes with prior vitrectomy.
Purpose: To assess the functional and anatomical consequences of single-dose dexamethasone (DEX) implants for the treatment of refractory macular edema (ME) secondary to retinal vein occlusion (RVO) after anti-vascular endothelial growth factor agents.Methods: A literature search of studies on switching therapy to DEX implants from anti-VEGF agents in refractory RVO patients was performed with five electronic databases (PubMed, Embase, Web of Science, MEDLINE, and Cochrane Library) prior to January 2022. The main outcomes included best-corrected visual acuity (BCVA) and central macular thickness (CMT) changes at different follow-up endpoints from baseline. All analyses were performed using Stata version 15.0.Results: The final analysis included four eligible studies with a total of 99 patients. After single-dose DEX implant application, BCVA improved significantly at 2, 3, and 6 months with an average gain of −0.23 logarithm of the minimum angle of resolution (logMAR) (p = 0.004), −0.20 logMAR (p = 0.027), and -0.09 logMAR (p = 0.021), respectively. Mean CMT reduction was also significant from baseline to 2 months (-241.89 μm, p < 0.001), 3 months (−222.61 μm, p < 0.001), and 6 months (−90.49 μm, p < 0.001). No serious adverse events were observed in any of the included studies.Conclusion: This meta-analysis showed that RVO patients with refractory ME could benefit significantly from switching therapy to DEX implantation, with efficacy lasting 6 months after a single-dose application. Intravitreal DEX implantation is a safe and effective option for refractory cases.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.