Segmentation of Retinal Vessels Based on DenseNet-Attention-Unet Model Network

2020 ◽  
Author(s):  
ZhenHao Liang ◽  
HuaZhu Liu ◽  
XiaoFang Zhao ◽  
Li Yu
Keyword(s):  
Retinal Vessels ◽  
Model Network

What's in a model? Network models as tools instead of representations of what psychiatric disorders really are

2019 ◽  
Vol 42 ◽  
Author(s):  
Hanna M. van Loo ◽  
Jan-Willem Romeijn
Keyword(s):  
Psychiatric Disorders ◽  
Network Models ◽  
Model Network

AbstractNetwork models block reductionism about psychiatric disorders only if models are interpreted in a realist manner – that is, taken to represent “what psychiatric disorders really are.” A flexible and more instrumentalist view of models is needed to improve our understanding of the heterogeneity and multifactorial character of psychiatric disorders.

A New Concept of the Pathogenesis of Retinopathy of Prematurity

2020 ◽  
pp. 5-12
Author(s):  
E.I. Sidorenko ◽  
Keyword(s):  
Growth Factors ◽  
Retinopathy Of Prematurity ◽  
Vascular Endothelium ◽  
Retinal Vessels ◽  
Protective Mechanisms ◽  
Preclinical Stage ◽  
Circulatory Hypoxia ◽  
Preclinical Phase ◽  
Vasculogenesis And Angiogenesis ◽  
Vascular Autoregulation

The lecture provides a detailed description of the development of retinal vessels, vasculogenesis and angiogenesis. The cascade of protective mechanisms of the organism of the system of combating hyperoxia, the system of combating circulatory hypoxia and the key growth factors of the vascular endothelium during angiogenesis are shown. The pathogenesis of retinopathy of prematurity is described and the first phase of ROP development is analyzed in detail, the reasons for the delay in the maturation of vascular autoregulation are explained. The author proposed to distinguish the first preclinical phase in the ROP classification. In contrast to the modern concentration of attention of ophthalmologists on the active and cicatricial stages, the author proposes to pay special attention to the study of the preclinical stage of ROP, where its pathogenesis is formed.

scholarly journals Retinal Vessels Thrombosis as Onset Manifestation of Systemic Sclerosis: 3 Clinical Cases

2014 ◽  
Vol 41 (12) ◽  
pp. 2495-2496 ◽  
Author(s):  
CINZIA ROTONDO ◽  
GIUSEPPE LOPALCO ◽  
GIOVANNI LAPADULA ◽  
FLORENZO IANNONE
Keyword(s):  
Systemic Sclerosis ◽  
Retinal Vessels ◽  
Clinical Cases

scholarly journals Retinal vessel segmentation with constrained-based nonnegative matrix factorization and 3D modified attention U-Net

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Yang Yu ◽  
Hongqing Zhu
Keyword(s):  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Computational Cost ◽  
Three Dimensional ◽  
Nonnegative Matrix ◽  
Retinal Vessel ◽  
Classification Problem ◽  
Image Resolution ◽  
Retinal Vessels ◽  
Segmentation Task

AbstractDue to the complex morphology and characteristic of retinal vessels, it remains challenging for most of the existing algorithms to accurately detect them. This paper proposes a supervised retinal vessels extraction scheme using constrained-based nonnegative matrix factorization (NMF) and three dimensional (3D) modified attention U-Net architecture. The proposed method detects the retinal vessels by three major steps. First, we perform Gaussian filter and gamma correction on the green channel of retinal images to suppress background noise and adjust the contrast of images. Then, the study develops a new within-class and between-class constrained NMF algorithm to extract neighborhood feature information of every pixel and reduce feature data dimension. By using these constraints, the method can effectively gather similar features within-class and discriminate features between-class to improve feature description ability for each pixel. Next, this study formulates segmentation task as a classification problem and solves it with a more contributing 3D modified attention U-Net as a two-label classifier for reducing computational cost. This proposed network contains an upsampling to raise image resolution before encoding and revert image to its original size with a downsampling after three max-pooling layers. Besides, the attention gate (AG) set in these layers contributes to more accurate segmentation by maintaining details while suppressing noises. Finally, the experimental results on three publicly available datasets DRIVE, STARE, and HRF demonstrate better performance than most existing methods.

Rubeosis iridis and macular hemorrhages from multiple Corkscrew retinal vessels in a patient with NF1

2021 ◽  
pp. 112067212199663
Author(s):  
Marilyn A Márquez ◽  
Claudio P Juárez ◽  
Maria C Sánchez ◽  
Jose D Luna
Keyword(s):  
Intravitreal Bevacizumab ◽  
Visual Outcome ◽  
Neovascular Glaucoma ◽  
Retinal Vessels ◽  
Retinal Hemorrhages ◽  
Fluorescein Angiogram ◽  
Rubeosis Iridis ◽  
Good Visual Outcome ◽  
Av Malformation ◽  
Sudden Decrease

Purpose: To report a case of a patient with NF1 presenting with ocular findings of AV malformation, multiple retinal hemorrhages, and neovascular glaucoma in the absence of retinal ischemia. Methods: Review of the medical record was conducted in accordance with the local IRBt. Results: A 60-year-old female patient with diagnosis of Neurofibromatosis type1 (NF1) and sudden decrease of vision in her left eye was found to have rubeosis iridis and high intraocular pressure (IOP). On fundus exam multiple corkscrew retinal vessels and retinal hemorrhages were present in her left eye. On Optical Coherence Tomography (OCT) the foveal hemorrhages appeared as outer layer hyperreflective retinal infiltrates whereas in the parafoveal area the hyperreflectivity was present between the RPE and neurosensory retina. Fluorescein Angiogram (FA) showed normal perfusion and no areas of leakage or ischemia. Treatment with anti-angiogenics in a timely manner correlated with a good visual outcome. Conclusions: We present a unique patient with NF1, rubeosis iridis, high IOP, and macular hemorrhages from multiple corkscrew retinal vessels in a well perfused retina, who underwent treatment with a single dose of intravitreal Bevacizumab and had an excellent response

scholarly journals Association of changes of retinal vessels diameter with ocular blood flow in eyes with diabetic retinopathy

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yoshitaka Ueno ◽  
Takeshi Iwase ◽  
Kensuke Goto ◽  
Ryo Tomita ◽  
Eimei Ra ◽  
...  
Keyword(s):  
Blood Flow ◽  
Diabetic Retinopathy ◽  
Adaptive Optics ◽  
Laser Speckle ◽  
The Other ◽  
Systemic Hypertension ◽  
Laser Speckle Flowgraphy ◽  
Retinal Vessels ◽  
External Diameter ◽  
The Mean

AbstractWe investigated morphological changes of retinal arteries to determine their association with the blood flow and systemic variables in type 2 diabetes patients. The patients included 47 non-diabetic retinopathy eyes, 36 mild or moderate nonproliferative diabetic retinopathy (M-NPDR) eyes, 22 severe NPDR (S-NPDR) eyes, 32 PDR eyes, and 24 normal eyes as controls. The mean wall to lumen ratio (WLR) measured by adaptive optics camera was significantly higher in the PDR groups than in all of the other groups (all P < 0.001). However, the external diameter of the retinal vessels was not significantly different among the groups. The mean blur rate (MBR)-vessel determined by laser speckle flowgraphy was significantly lower in the PDR group than in the other groups (P < 0.001). The WLR was correlated with MBR-vessel (r = − 0.337, P < 0.001), duration of disease (r = 0.191, P = 0.042), stage of DM (r = 0.643, P < 0.001), systolic blood pressure (r = 0.166, P < 0.037), and presence of systemic hypertension (r = 0.443, P < 0.001). Multiple regression analysis demonstrated that MBR-vessel (β = − 0.389, P < 0.001), presence of systemic hypertension (β = 0.334, P = 0.001), and LDL (β = 0.199, P = 0.045) were independent factors significantly associated with the WLR. The increased retinal vessel wall thickness led to a narrowing of lumen diameter and a decrease in the blood flow in the PDR group.

Sign in / Sign up

Export Citation Format

Share Document