Microangiopathy in Ocular Sarcoidosis Using Fluorescein Gonio and Fundus Angiography from Diagnostic and Therapeutic Aspects

In this retrospective study, we investigated vascular abnormalities in sarcoidosis using fluorescein gonioangiography (FGA) to detect angle neovascularization (ANV), fundus fluorescein angiography (FFA), and pathological specimens from the aspects of microangiopathy. In 57 sarcoidosis patients, clinical data was reviewed by dividing the cases into three groups (Group I: histologically diagnosed; Group II: positive bilateral hilar lymphadenopathy (BHL); Group III: negative BHL). The FFA, FGA, and pathological examination data in the autopsy eyes and trabeculectomy specimens were investigated. FGA and FFA detected ANV (91%) and nodule-associated abnormalities (87%), respectively. No intraocular pressure (IOP) elevation was observed after continuous topical betamethasone, except in the steroid responder group. Maximum IOP had significant correlation with nodules in the angle (p = 0.02696) and visual field defect (p = 0.0151). Granulomas adjacent to blood vessels, including the Schlemm’s canal, and thickening of the retinal blood vessel wall caused occlusion of those vessels. Photocoagulation was required for retinal tears (14%) and the retinal blood vessel occlusion (7%). Suppression of IOP elevation via continuous topical betamethasone may be important to avoid irreversible outflow-route changes and optic-nerve damage, and the concept of microangiopathy in ocular sarcoidosis may be important for understanding the proper treatment of serious complications.

Download Full-text

Retinal Blood Vessel Segmentation and Identification of Glaucoma Using Convolutional Neural Network

SSRN Electronic Journal ◽

10.2139/ssrn.3643870 ◽

2020 ◽

Author(s):

G Roopa Krishna Chandra ◽

NV Kranthi ◽

K Kavya

Keyword(s):

Neural Network ◽

Blood Vessel ◽

Convolutional Neural Network ◽

Vessel Segmentation ◽

Retinal Blood Vessel ◽

Blood Vessel Segmentation

Download Full-text

Retinal Vessel Segmentation by Deep Residual Learning with Wide Activation

Computational Intelligence and Neuroscience ◽

10.1155/2020/8822407 ◽

2020 ◽

Vol 2020 ◽

pp. 1-11

Author(s):

Yuliang Ma ◽

Xue Li ◽

Xiaopeng Duan ◽

Yun Peng ◽

Yingchun Zhang

Keyword(s):

Blood Vessel ◽

Blood Vessels ◽

Area Under The Curve ◽

Retinal Vessel ◽

Vessel Segmentation ◽

Superior Performance ◽

Retinal Blood Vessel ◽

Low Contrast ◽

Blood Vessel Segmentation ◽

Small Vessels

Purpose. Retinal blood vessel image segmentation is an important step in ophthalmological analysis. However, it is difficult to segment small vessels accurately because of low contrast and complex feature information of blood vessels. The objective of this study is to develop an improved retinal blood vessel segmentation structure (WA-Net) to overcome these challenges. Methods. This paper mainly focuses on the width of deep learning. The channels of the ResNet block were broadened to propagate more low-level features, and the identity mapping pathway was slimmed to maintain parameter complexity. A residual atrous spatial pyramid module was used to capture the retinal vessels at various scales. We applied weight normalization to eliminate the impacts of the mini-batch and improve segmentation accuracy. The experiments were performed on the DRIVE and STARE datasets. To show the generalizability of WA-Net, we performed cross-training between datasets. Results. The global accuracy and specificity within datasets were 95.66% and 96.45% and 98.13% and 98.71%, respectively. The accuracy and area under the curve of the interdataset diverged only by 1%∼2% compared with the performance of the corresponding intradataset. Conclusion. All the results show that WA-Net extracts more detailed blood vessels and shows superior performance on retinal blood vessel segmentation tasks.

Download Full-text