Retinal Vessel Segmentation of Non-Proliferative Diabetic Retinopathy

2019 ◽  
Vol 10 (1) ◽  
pp. 30-38
Author(s):  
Santosh S. Chowhan ◽  
Rakesh S. Deore ◽  
Sachin A. Naik
Keyword(s):  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Blood Vessels ◽  
Proliferative Diabetic Retinopathy ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Experimental Results ◽  
Diabetic Patients ◽  
Retinal Vessel Segmentation ◽  
Macular Ischemia

Diabetic retinopathy is a disease in diabetic patients that affects the eye. It happens due to damage in the blood vessels of the light-sensitive tissues at the retina. In non-proliferative diabetic retinopathy, tiny changes occur in the blood vessels of the eye. Non-proliferative diabetic retinopathy can trigger macular edema or macular ischemia. In this study proposes the retinal vessel segmentation and vessel quantization on the DRIVE database which is publicly available. The experimental results express the retinal vessel can be effectively detected and segmented.

scholarly journals Effects of Intra-vitreal Injection of Bevacizumab as an Adjunct during Phacoemulsification in Diabetic Maculopathy

2020 ◽  
Vol 37 (1) ◽  
Author(s):  
Ali Afzal Bodla ◽  
Syeda Minahil Kazmi ◽  
Noor Tariq ◽  
Ayema Moazzam ◽  
Muhammad Muneeb Aman
Keyword(s):  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Proliferative Diabetic Retinopathy ◽  
Macular Thickness ◽  
Control Group ◽  
Key Words Diabetes Mellitus ◽  
Diabetic Patients ◽  
Key Words Diabetes ◽  
Post Surgery ◽  
Significant Difference

Purpose:  To study the effects of Intra-vitreal injection of Bevacizumab as an adjunct during phacoemulsification in patients with diabetic retinopathy. Study Design:  Quasi experimental study. Methods:  Hundred diabetic patients who were scheduled to undergo phacoemulsification were included in the study. They were equally divided into two groups; Bevacizumab and control group. Complete ocular examination and macular thickness and volume were determined using an OPTOVUE-OCT machine. The patients in the Bevacizumab group were given intra-vitreal injection of 1.25 mg/0.05ml of Bevacizumab at the time of Phacoemulsification. A written ethical approval was obtained and the study was conducted according to principles of declaration of Helsinki. Results:  The bevacizumab group manifested low value of CMT one month post-surgery as compared to the control group (262.2 ± 32.2 and 288.5 ± 54.1, respectively) with P = 0.01. The Total Macular volume, and Best-corrected visual acuity in the two groups showed no significant difference one month after surgery. Amongst the patients who developed postsurgical macular edema, four patients did not possess a positive history for diabetic retinopathy and 3 of them had Non Proliferative Diabetic Retinopathy. We found no significant relationship between the post-surgical macula edema with the presence of mild Non Proliferative Diabetic Retinopathy. (Fisher's test, P = 0.321). Conclusion:  The ocular anti-VEGF therapy substantially reduces macular edema secondary to post-surgical inflammation in diabetic patients. It effectively reduces the central macular thickness although the results are not found to be statistically significant when compared with the control group. Key Words:  Diabetes mellitus; diabetic macular edema; diabetic retinopathy: Bevacizumab.

scholarly journals MSC-Net: Multitask Learning Network for Retinal Vessel Segmentation and Centerline Extraction

2021 ◽  
Vol 12 (1) ◽  
pp. 403
Author(s):  
Lin Pan ◽  
Zhen Zhang ◽  
Shaohua Zheng ◽  
Liqin Huang
Keyword(s):  
Blood Vessel ◽  
Blood Vessels ◽  
Automatic Segmentation ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Multitask Learning ◽  
Learning Network ◽  
Centerline Extraction ◽  
Retinal Vessel Segmentation ◽  
And Performance

Automatic segmentation and centerline extraction of blood vessels from retinal fundus images is an essential step to measure the state of retinal blood vessels and achieve the goal of auxiliary diagnosis. Combining the information of blood vessel segments and centerline can help improve the continuity of results and performance. However, previous studies have usually treated these two tasks as separate research topics. Therefore, we propose a novel multitask learning network (MSC-Net) for retinal vessel segmentation and centerline extraction. The network uses a multibranch design to combine information between two tasks. Channel and atrous spatial fusion block (CAS-FB) is designed to fuse and correct the features of different branches and different scales. The clDice loss function is also used to constrain the topological continuity of blood vessel segments and centerline. Experimental results on different fundus blood vessel datasets (DRIVE, STARE, and CHASE) show that our method can obtain better segmentation and centerline extraction results at different scales and has better topological continuity than state-of-the-art methods.

scholarly journals Impact of Novel Image Preprocessing Techniques on Retinal Vessel Segmentation

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2297
Author(s):  
Toufique A. Soomro ◽  
Ahmed Ali ◽  
Nisar Ahmed Jandan ◽  
Ahmed J. Afifi ◽  
Muhammad Irfan ◽  
...  
Keyword(s):  
Blood Vessels ◽  
Retinal Disease ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Low Contrast ◽  
The Public ◽  
Retinal Blood Vessels ◽  
Retinal Vessel Segmentation ◽  
Automated Screening ◽  
Traditional Image

Segmentation of retinal vessels plays a crucial role in detecting many eye diseases, and its reliable computerized implementation is becoming essential for automated retinal disease screening systems. A large number of retinal vessel segmentation algorithms are available, but these methods improve accuracy levels. Their sensitivity remains low due to the lack of proper segmentation of low contrast vessels, and this low contrast requires more attention in this segmentation process. In this paper, we have proposed new preprocessing steps for the precise extraction of retinal blood vessels. These proposed preprocessing steps are also tested on other existing algorithms to observe their impact. There are two steps to our suggested module for segmenting retinal blood vessels. The first step involves implementing and validating the preprocessing module. The second step applies these preprocessing stages to our proposed binarization steps to extract retinal blood vessels. The proposed preprocessing phase uses the traditional image-processing method to provide a much-improved segmented vessel image. Our binarization steps contained the image coherence technique for the retinal blood vessels. The proposed method gives good performance on a database accessible to the public named DRIVE and STARE. The novelty of this proposed method is that it is an unsupervised method and offers an accuracy of around 96% and sensitivity of 81% while outperforming existing approaches. Due to new tactics at each step of the proposed process, this blood vessel segmentation application is suitable for computer analysis of retinal images, such as automated screening for the early diagnosis of eye disease.

scholarly journals Evaluation of Proteoforms of the Transmembrane Chemokines CXCL16 and CX3CL1, Their Receptors, and Their Processing Metalloproteinases ADAM10 and ADAM17 in Proliferative Diabetic Retinopathy

2021 ◽  
Vol 11 ◽  
Author(s):  
Ahmed M. Abu El-Asrar ◽  
Mohd Imtiaz Nawaz ◽  
Ajmal Ahmad ◽  
Alexandra De Zutter ◽  
Mohammad Mairaj Siddiquei ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Blood Vessels ◽  
Proliferative Diabetic Retinopathy ◽  
Müller Cells ◽  
Intercellular Adhesion Molecule ◽  
Enzyme Linked Immunosorbent Assay ◽  
Diabetic Patients ◽  
Muller Cells ◽  
Epiretinal Membranes ◽  
Positive Correlations

The transmembrane chemokine pathways CXCL16/CXCR6 and CX3CL1/CX3CR1 are strongly implicated in inflammation and angiogenesis. We investigated the involvement of these chemokine pathways and their processing metalloproteinases ADAM10 and ADAM17 in the pathophysiology of proliferative diabetic retinopathy (PDR). Vitreous samples from 32 PDR and 24 non-diabetic patients, epiretinal membranes from 18 patients with PDR, rat retinas, human retinal Müller glial cells and human retinal microvascular endothelial cells (HRMECs) were studied by enzyme-linked immunosorbent assay, immunohistochemistry and Western blot analysis. In vitro angiogenesis assays were performed and the adherence of leukocytes to CXCL16-stimulated HRMECs was assessed. CXCL16, CX3CL1, ADAM10, ADAM17 and vascular endothelial growth factor (VEGF) levels were significantly increased in vitreous samples from PDR patients. The levels of CXCL16 were 417-fold higher than those of CX3CL1 in PDR vitreous samples. Significant positive correlations were found between the levels of VEGF and the levels of CXCL16, CX3CL1, ADAM10 and ADAM17. Significant positive correlations were detected between the numbers of blood vessels expressing CD31, reflecting the angiogenic activity of PDR epiretinal membranes, and the numbers of blood vessels and stromal cells expressing CXCL16, CXCR6, ADAM10 and ADAM17. CXCL16 induced upregulation of phospho-ERK1/2, p65 subunit of NF-κB and VEGF in cultured Müller cells and tumor necrosis factor-α induced upregulation of soluble CXCL16 and ADAM17 in Müller cells. Treatment of HRMECs with CXCL16 resulted in increased expression of intercellular adhesion molecule-1 (ICAM-1) and increased leukocyte adhesion to HRMECs. CXCL16 induced HRMEC proliferation, formation of sprouts from HRMEC spheroids and phosphorylation of ERK1/2. Intravitreal administration of CXCL16 in normal rats induced significant upregulation of the p65 subunit of NF-κB, VEGF and ICAM-1 in the retina. Our findings suggest that the chemokine axis CXCL16/CXCR6 and the processing metalloproteinases ADAM10 and ADAM17 might serve a role in the initiation and progression of PDR.

scholarly journals Hybrid UNet Architecture based on Residual Learning of Fundus Images for Retinal Vessel Segmentation

2021 ◽  
Vol 2070 (1) ◽  
pp. 012104
Author(s):  
Sushma Nagdeote ◽  
Sapna Prabhu
Keyword(s):  
Blood Vessels ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Intensity Difference ◽  
Fundus Images ◽  
The Past ◽  
Retinal Blood Vessels ◽  
Retinal Fundus Image ◽  
Retinal Vessel Segmentation ◽  
Retinal Fundus

Abstract This paper deals with the new segmentation techniques for retinal blood vessels on fundus images. This technique aims at extracting thin vessels to reduce the intensity difference between thick and thin vessels. This paper proposes the modified UNet model by incorporating ResNet blocks into it which includes structured prediction. In this work we generate the visualization of blood vessels from retinal fundus image for two loss functions namely cross entropy loss and Dice loss where the network classifies several pixels simultaneously. The results shows higher accuracy by considering a much more expressive UNet algorithm and outperforms the past algorithms for Retinal Vessel Segmentation. The benefits of this approach will be demonstrated empirically.

Empirical Evaluation of Retinal Vessel Segmentation Techniques

2020 ◽  
Vol 17 (9) ◽  
pp. 4671-4677
Author(s):  
M. Vijaya Maheswari ◽  
G. Murugeswari
Keyword(s):  
Blood Vessels ◽  
Active Contour ◽  
Active Contour Model ◽  
Empirical Evaluation ◽  
Region Growing ◽  
Retinal Vessel ◽  
Diabetic Patients ◽  
Neural Signals ◽  
Retinal Vessel Segmentation ◽  
The Brain

Human eye is made up of millions of blood vessels. Retina is a delicate layer that covers the back portion of the eye. The role of retina is to transmit the light signals into neural signals to the brain which is then interpreted. The interpretation from the brain is converted as visual perceptions. Blood vessels supply a large amount of blood to the retina. When the level of glucose is high in the blood, the blood vessels in the retina gets damaged. In the advanced stages of damaged blood vessels, it leads to blindness. Various retinal diseases are caused by the damage in the vessels. One of the most threatening disease in the recent days is Diabetic Retinopathy (DR) in diabetic patients. In this paper, few segmentation techniques like Active Contour model, Thresholding based method and Region Growing methods are implemented. The performance of these techniques are analyzed in measures of Accuracy, Sensitivity, and Specificity. DRIVE and CHASE_DB1 dataset is used for this purpose. The outcome of this comparative analysis on DRIVE dataset shows that thresholding technique produces an accuracy of 95.06% and sensitivity of 88.30%, region growing technique produces a specificity of 97.24%, on CHASE_DB1 dataset results show that thresholding technique produces an accuracy of 94.74%, region growing produces an sensitivity of 77.08% and active contour produces a specificity of 97.06% respectively.

scholarly journals Efficient BFCN for Automatic Retinal Vessel Segmentation

2020 ◽  
Vol 2020 ◽  
pp. 1-14 ◽  
Author(s):  
Yun Jiang ◽  
Falin Wang ◽  
Jing Gao ◽  
Wenhuan Liu
Keyword(s):  
Blood Vessels ◽  
Spatial Information ◽  
Contextual Information ◽  
Receptive Fields ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Deep Convolutional Neural Networks ◽  
Low Contrast ◽  
Retinal Vessel Segmentation ◽  
Segmentation Image

Retinal vessel segmentation has high value for the research on the diagnosis of diabetic retinopathy, hypertension, and cardiovascular and cerebrovascular diseases. Most methods based on deep convolutional neural networks (DCNN) do not have large receptive fields or rich spatial information and cannot capture global context information of the larger areas. Therefore, it is difficult to identify the lesion area, and the segmentation efficiency is poor. This paper presents a butterfly fully convolutional neural network (BFCN). First, in view of the low contrast between blood vessels and the background in retinal blood vessel images, this paper uses automatic color enhancement (ACE) technology to increase the contrast between blood vessels and the background. Second, using the multiscale information extraction (MSIE) module in the backbone network can capture the global contextual information in a larger area to reduce the loss of feature information. At the same time, using the transfer layer (T_Layer) can not only alleviate gradient vanishing problem and repair the information loss in the downsampling process but also obtain rich spatial information. Finally, for the first time in the paper, the segmentation image is postprocessed, and the Laplacian sharpening method is used to improve the accuracy of vessel segmentation. The method mentioned in this paper has been verified by the DRIVE, STARE, and CHASE datasets, with the accuracy of 0.9627, 0.9735, and 0.9688, respectively.

scholarly journals Automatic Retinal Vessel Segmentation Based on an Improved U-Net Approach

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Zihe Huang ◽  
Ying Fang ◽  
He Huang ◽  
Xiaomei Xu ◽  
Jiwei Wang ◽  
...  
Keyword(s):  
Blood Vessels ◽  
Structural Changes ◽  
Area Under The Curve ◽  
Image Data ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Circulation System ◽  
Retinal Blood Vessels ◽  
Image Patches ◽  
Retinal Vessel Segmentation

Retinal blood vessels are the only deep microvessels in the blood circulation system that can be observed directly and noninvasively, providing us with a means of observing vascular pathologies. Cardiovascular and cerebrovascular diseases, such as glaucoma and diabetes, can cause structural changes in the retinal microvascular network. Therefore, the study of effective retinal vessel segmentation methods is of great significance for the early diagnosis of cardiovascular diseases and the vascular network’s quantitative results. This paper proposes an automatic retinal vessel segmentation method based on an improved U-Net network. Firstly, the image patches are rotated to amplify the image data, and then, the RGB fundus image is preprocessed by normalization. Secondly, after the improved U-Net model is constructed with 23 convolutional layers, 4 pooling layers, 4 upsampling layers, 2 dropout layers, and Squeeze and Excitation (SE) block, the extracted image patches are utilized for training the model. Finally, the fundus images are segmented through the trained model to achieve precise extraction of retinal blood vessels. According to experimental results, the accuracy of 0.9701, 0.9683, and 0.9698, sensitivity of 0.8011, 0.6329, and 0.7478, specificity of 0.9849, 0.9967, and 0.9895, F1-Score of 0.8099, 0.8049, and 0.8013, and area under the curve (AUC) of 0.8895, 0.8845, and 0.8686 were achieved on DRIVE, STARE, and HRF databases, respectively, which is better than most classical algorithms.

Sign in / Sign up

Export Citation Format

Share Document