1.
Clinical efficacy and acceptability of panretinal photocoagulation combined with conbercept for patients with proliferative diabetic retinopathy: A protocol for systematic review and meta-analysis.
Wang, L, Chen, Z, Wang, X
Medicine. 2021;(17):e25611
-
-
Free full text
-
Abstract
BACKGROUND Although conbercept has been used for other diseases associated with new vascular formation, the effect of single-dose conbercept in combination with proliferative diabetic retinopathy (PDR) have not been established. We thus conducted this protocol for systematic review and meta-analysis to compare the efficacy and acceptability of panretinal photocoagulation (PRP) associated with intravitreal conbercept injections versus PRP alone in the treatment of patients with PDR. METHODS The Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocols reporting guidelines and the recommendations of the Cochrane Collaboration were followed to conduct this study. Reviewers will search the PubMed, Cochrane Library, Web of Science, and EMBASE online databases using the key phrases "panretinal photocoagulation," "conbercept," and "proliferative diabetic retinopathy" for all cohort studies published up to May 2021. The studies on cohort study focusing on PRP + conbercept and PRP alone for PDR patients will be included in our meta-analysis. At least one of the following outcomes should have been measured: PRP completion rate, proportion of eyes with visual gain/loss, central macular thickness, and incidence of complication. Review Manager software (v 5.4; Cochrane Collaboration) is used for the meta-analysis. RESULTS It was hypothesized that intravitreal conbercept plus PRP was more effective than PRP alone. OSF REGISTRATION NUMBER 10.17605/OSF.IO/HCQ2S.
2.
A location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images.
Liu, Q, Zou, B, Chen, J, Ke, W, Yue, K, Chen, Z, Zhao, G
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society. 2017;:78-86
Abstract
The automatic exudate segmentation in colour retinal fundus images is an important task in computer aided diagnosis and screening systems for diabetic retinopathy. In this paper, we present a location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images, which includes three stages: anatomic structure removal, exudate location and exudate segmentation. In anatomic structure removal stage, matched filters based main vessels segmentation method and a saliency based optic disk segmentation method are proposed. The main vessel and optic disk are then removed to eliminate the adverse affects that they bring to the second stage. In the location stage, we learn a random forest classifier to classify patches into two classes: exudate patches and exudate-free patches, in which the histograms of completed local binary patterns are extracted to describe the texture structures of the patches. Finally, the local variance, the size prior about the exudate regions and the local contrast prior are used to segment the exudate regions out from patches which are classified as exudate patches in the location stage. We evaluate our method both at exudate-level and image-level. For exudate-level evaluation, we test our method on e-ophtha EX dataset, which provides pixel level annotation from the specialists. The experimental results show that our method achieves 76% in sensitivity and 75% in positive prediction value (PPV), which both outperform the state of the art methods significantly. For image-level evaluation, we test our method on DiaRetDB1, and achieve competitive performance compared to the state of the art methods.