Detection Of Proliferative Diabetic Retinopathy Research Articles

Inter-Rater Reliability of Proliferative Diabetic Retinopathy Assessment on Wide-Field OCT-Angiography and Fluorescein Angiography.

To assess inter-rater reliability in the detection of proliferative diabetic retinopathy (PDR) changes using wide-field optical coherence tomography angiography (WF-OCTA) versus fluorescein angiography (FA). This retrospective, cross-sectional study included patients with severe nonproliferative and PDR. Images were acquired with 12 × 12 mm WF-OCTA and FA with a 55° lens. Images were cropped to represent the exact same field of view. Qualitative (detection of neovascularization at the disc [NVD] and elsewhere [NVE], enlarged foveal avascular zone [FAZ], vitreous hemorrhage [VH]) and quantitative analyses (FAZ area, horizontal, vertical, and maximum FAZ diameter) were performed by 2 masked graders using ImageJ. Inter-rater reliability was calculated using unweighted Cohen's kappa coefficient (κ) for qualitative analyses and intraclass correlation coefficients (ICC) for quantitative analyses. Twenty-three eyes of 17 patients were included. Inter-rater reliability was higher for FA than for WF-OCTA in qualitative analyses: κ values were 0.65 and 0.78 for detection of extended FAZ, 0.83 and 1.0 for NVD, 0.78 and 1.0 for NVE, and 0.19 and 1 for VH for WF-OCTA and FA, respectively. In contrast, inter-rater reliability was higher for WF-OCTA than for FA in the quantitative analyses: ICC values were 0.94 and 0.76 for FAZ size, 0.92 and 0.79 for horizontal FAZ diameter, 0.82 and 0.72 for vertical FAZ diameter, and 0.88 and 0.82 for maximum FAZ diameter on WF-OCTA and FA, respectively. Inter-rater reliability of FA is superior to WF-OCTA for qualitative analyses whereas inter-rater reliability of WF-OCTA is superior to FA for quantitative analyses. The study highlights the specific merits of both imaging modalities in terms of reliability. FA should be preferred for qualitative parameters, whereas WF-OCTA should be preferred for quantitative parameters.

IDENTIFICATION OF RISK FACTORS FOR THE DEVELOPMENT OF DIABETIC RETINOPATHY IN PATIENTS WITH DIABETES MELLITUS

The article provides information about the research conducted in connection with the detection of risk factors that play a role in the development of diabetic retinopathy (DR) in patients with diabetes mellitus (DM). The study included 2567 DM type one and type two patients aged 18-75 years who were treated at the Central Hospital of Sheki Region 2015-2020. The frequency of detection of proliferative diabetic retinopathy (PDR) and vision-threatening diabetic retinopathy (DRVT) in relation to the types, course and duration of diabetes, as well as comorbid conditions, was studied. The study showed that there was a direct correlation between long-term hyperglycemia and the detection of DR, and DR was observed in DM1 patients (48.1%) and DM2 patients (31.2%). Due to the increase in the duration of diabetes, the frequency of PDR and DRVT in patients with diabetes mellitus type one (18.9%) was higher than that of patients with diabetes mellitus type two (8.3%). Except for nephropathy and neuropathy, high AT, obesity, dyslipidemia, and other risk factors were noted to be more common in DM2 patients than DM1 patients were.

Proliferative diabetic retinopathy detection: Comparison of clinical examination, optomap photographs and fluorescein angiography.

This study aimed to analyse the clinical retinal examination findings and undilated Optomap ultrawide field retinal imaging for the detection of proliferative diabetic retinopathy (DR) as compared to the fluorescein angiography (FA). In this retrospective cross-sectional study, five hundred and twenty-three patients diagnosed with diabetic retinopathy on dilated retinal examination underwent fluorescein angiography and undilated Optomap imaging. Fluorescein angiography and undilated Optomap images were graded by masked graders and the diagnosis was labelled either as proliferative diabetic retinopathy or non-proliferative diabetic retinopathy. Sensitivity and specificity was calculated comparing the diagnosis obtained from the dilated retinal examination and the undilated Optomap images against the fluorescein angiography image findings. Gradable quality fluorescein angiography and undilated Optomap images with a clinical diagnosis mentioned in the medical record for that particular visit were available in 980 (right eye - 656; 67%; left eye - 324; 33%) eyes of 496 patients. There were 332 (67%) males and 164 (33%) females with a mean age of 60.3 ± 9.51 years (range: 32 - 81 years). Sensitivity of clinical examination and undilated Optomap images in accurately identifying proliferative diabetic retinopathy was 63.5% and 43.5% respectively. Specificity of clinical examination and undilated Optomap images in accurately identifying proliferative diabetic retinopathy was 88.5% and 76.2% respectively. On comparison of the undilated Optomap imaging findings against the clinical examination findings, the sensitivity and specificity were 47.7% and 75.1% respectively. Both clinical fundus evaluation and undilated Optomap imaging were relatively inferior to fluorescein angiography in the detection of proliferative diabetic retinopathy, which hence remains the choice of imaging modality giving scope for wider application.

Categorization of Diabetic Retinopathy using Deep Learning Techniques

Diabetic retinopathy is a disease that infects the vision of human eyes suffering from diabetes. It affects the blood vessels of soft tissues at retina, which is located at the backside of the eyes. This disease is evaluated by the physicians based on the retinal images of patients. Detection of the disease initiates human-intensive work for medical practitioners with monetary expenses also. Recent research works have identified that the use of deep learning methods for automatic detection of diabetic retinopathy helps the experts to make quick decision about the patient’s health conditions. In this paper, automated detection of diabetic retinopathy using deep belief networks has been presented which process the retinal images of patients and provides accurate diagnosis of categories of diabetic retinopathy. The proposed method has been trained and tested with Convolutional Neural Networks and Deep Belief Networks. The confidence level of diagnosis is computed and 94.69% with 96.01% are achieved in the detection of Proliferative diabetic retinopathy using CNN and DBN based on the features of data.

Wide-field optical coherence tomography angiography for the detection of proliferative diabetic retinopathy.

To compare the ability of wide-field optical coherence tomography angiography (WF-OCTA) to that of ultra-wide field fluorescein angiography (UWF-FA) and ultra-wide-field color fundus photography (UWF-CP) to detect retinal neovascularization (NV) in eyes with proliferative diabetic retinopathy (PDR). In this cross-sectional study, naïve patients with active PDR underwent UWF-FA and UWF-CP using the Optos 200Tx and WF-OCTA with 12 × 12mm fields of five visual fixations using the PLEX Elite 9000. NV was defined on OCTA when the co-registered B-scan with flow overlay of the vitreoretinal interface (VRI) segmentation showed extraretinal proliferation. Three masked readers examined the UWF-FA, UWF-CP, and WF-OCTA independently for the presence of NV. Statistical analysis was performed to compare the diagnostic accuracy of the 3 wide-field imaging modalities using OCT B-scan as the reference standard. In 82 eyes with PDR, neovascularization of the disc (NVD) was detected in 13 eyes by UWF-CP, 35 eyes with UWF-FA, and 37 eyes with OCTA using the VRI slab. Upon review of the 2500 OCT B-scans with superimposed flow overlay of each eye, NVD was confirmed in 37 eyes. The sensitivity and specificity of NVD detection were 35.1% and 97.8%, respectively for UWF-CP; 94.6% and 100%, respectively, for UWF-FA; and 100% and 100% for WF-OCTA. One hundred ninety-six foci of neovascularization elsewhere (NVE) were identified with the OCT B-scan with superimposed flow overlay. UWF-CP analysis was able to detect 62 foci of NVE of the 196 confirmed by B-scan (31.6% detection rate). An additional 11 foci of NVE seen on UWF-CP were not confirmed by B-Scan (15% false positive rate). There were 182 foci of NVE identified by UWF-FA (detection rate 91.3%), while WF-OCTA detected 196 retinal NVEs (detection rate 100%). The rate of false positives for both UWF-FA and WF-OCTA was low (< 2%). WF-OCTA can identify NV that is not evident in UWF-CP and represents a faster and safer alternative to UWF-FA for surveillance of PDR with comparable diagnostic accuracy.

Detection of Proliferative Diabetic Retinopathy in Fundus Images Using Convolution Neural Network

Convolution Neural Network (CNN) is one of the techniques under Artificial Neural Network (ANN) used to develop a Deep Learning Neural Network (DLNN) algorithm for detection of Proliferative Diabetic Retinopathy (PDR) on the fundus images. About 116 PDR and 150 Non-Proliferative Diabetic Retinopathy (NPDR) of fundus images retrieved from the publicly available MESSIDOR database applied in this research. This study consisted three objectives that included the execution of two pre-processing techniques on the data-set which were resizing and normalizing the fundus images, developed deep learning operational Artificial Intelligence (AI) network of feature extraction algorithm for detection of PDR on the fundus images and determined the output classification of the network encompassing the accuracy, sensitivity and specificity. There were five different parameters carried out along this research. Here, Parameter 5 showed the best performance among the five parameters based on the value of accuracy, sensitivity, and specificity that was 73.81%, 76%, and 69% respectively.

The automated detection of proliferative diabetic retinopathy using dual ensemble classification

Objective: Diabetic retinopathy (DR) is a retinal vascular disease that is caused by complications of diabetes. Proliferative diabetic retinopathy (PDR) is the advanced stage of the disease which carries a high risk of severe visual impairment. This stage is characterized by the growth of abnormal new vessels. We aim to develop a method for the automated detection of new vessels from retinal images. Methods: This method is based on a dual classification approach. Two vessel segmentation approaches are applied to create two separate binary vessel maps which each hold vital information. Local morphology, gradient and intensity features are measured using each binary vessel map to produce two separate 21-D feature vectors. Independent classification is performed for each feature vector using an ensemble system of bagged decision trees. These two independent outcomes are then combined to a produce a final decision. Results: Sensitivity and specificity results using a dataset of 60 images are 1.0000 and 0.9500 on a per image basis. Conclusions: The described automated system is capable of detecting the presence of new vessels.

Genetic algorithm based feature selection combined with dual classification for the automated detection of proliferative diabetic retinopathy

Proliferative diabetic retinopathy (PDR) is a condition that carries a high risk of severe visual impairment. The hallmark of PDR is the growth of abnormal new vessels. In this paper, an automated method for the detection of new vessels from retinal images is presented. This method is based on a dual classification approach. Two vessel segmentation approaches are applied to create two separate binary vessel map which each hold vital information. Local morphology features are measured from each binary vessel map to produce two separate 4-D feature vectors. Independent classification is performed for each feature vector using a support vector machine (SVM) classifier. The system then combines these individual outcomes to produce a final decision. This is followed by the creation of additional features to generate 21-D feature vectors, which feed into a genetic algorithm based feature selection approach with the objective of finding feature subsets that improve the performance of the classification. Sensitivity and specificity results using a dataset of 60 images are 0.9138 and 0.9600, respectively, on a per patch basis and 1.000 and 0.975, respectively, on a per image basis.

Automated Detection of Proliferative Diabetic Retinopathy Using Brownian Motion Features

Automated Detection of Proliferative Diabetic Retinopathy Using Brownian Motion Features

Automated detection of proliferative diabetic retinopathy using a modified line operator and dual classification

Proliferative diabetic retinopathy (PDR) is a condition that carries a high risk of severe visual impairment. The hallmark of PDR is neovascularisation, the growth of abnormal new vessels. This paper describes an automated method for the detection of new vessels in retinal images. Two vessel segmentation approaches are applied, using the standard line operator and a novel modified line operator. The latter is designed to reduce false responses to non-vessel edges. Both generated binary vessel maps hold vital information which must be processed separately. This is achieved with a dual classification system. Local morphology features are measured from each binary vessel map to produce two separate feature sets. Independent classification is performed for each feature set using a support vector machine (SVM) classifier. The system then combines these individual classification outcomes to produce a final decision. Sensitivity and specificity results using a dataset of 60 images are 0.862 and 0.944 respectively on a per patch basis and 1.00 and 0.90 respectively on a per image basis.

Detection of neovascularization in retinal images using multivariate m-Mediods based classifier

Diabetic retinopathy is a progressive eye disease and one of the leading causes of blindness all over the world. New blood vessels (neovascularization) start growing at advance stage of diabetic retinopathy known as proliferative diabetic retinopathy. Early and accurate detection of proliferative diabetic retinopathy is very important and crucial for protection of patient's vision. Automated systems for detection of proliferative diabetic retinopathy should identify between normal and abnormal vessels present in digital retinal image. In this paper, we proposed a new method for detection of abnormal blood vessels and grading of proliferative diabetic retinopathy using multivariate m-Mediods based classifier. The system extracts the vascular pattern and optic disc using a multilayered thresholding technique and Hough transform respectively. It grades the fundus image in different categories of proliferative diabetic retinopathy using classification and optic disc coordinates. The proposed method is evaluated using publicly available retinal image databases and results show that the proposed system detects and grades proliferative diabetic retinopathy with high accuracy.

TNF-Alpha Levels in Tears: A Novel Biomarker to Assess the Degree of Diabetic Retinopathy

We assess the level of tumour necrosis factor alpha (TNF-alpha) in tear fluids and other serum parameters associated with diabetes in different degrees of diabetic retinopathy. We have performed a prospective, nonrandomized, observational study. Study population consisted of 16 healthy subjects (controls) and 32 type 2 diabetic patients: 16 affected by proliferative diabetic retinopathy (PDR) and 16 with nonproliferative retinopathy (NDPR, background/preproliferative). Body mass index, urinary albumin, blood glucose, HbA1c, and tear levels of TNF-alpha were measured in all subjects. The value of glycaemia, microalbuminurea, and Body mass index in diabetic retinopathy groups were higher than those in control group (P < 0.05). Glycemia in NPDR: 6.6 mmol/L (range: 5.8–6.3); in PDR: 6.7 mmol/L (range: 6.1–7.2); in control: 5.7 mmol/L (range: 4.9–6.1); microalbuminurea in NPDR: 10.6 mg/L (range: 5.6–20); in PDR: 25.2 mg/L (range: 17–40); in control: 5.3 mg/L (range: 2.6–10); Body mass index in NPDR: 26 Kg/m2 (range: 20.3–40); in PDR: 28 Kg/m2 (range 20.3–52); in control: 21 Kg/m2 (range 19–26). The TNF-alpha concentrations in tears increase with the severity of pathology and were lower in control group than in diabetic subjects. In the end, the level of TNF-alpha is highly correlated with severity of diabetic retinopathy and with nephropathy. Tear fluid collection may be a useful noninvasive method for the detection of proliferative diabetic retinopathy.

A Comparison and Evaluation of Computerized Methods for OD Localization and Detection in Retinal Images

Automated localization and detection of optic disc (OD) is essential step in the analysis of digital diabetic retinopathy systems. Retinal images give unique diagnostic about eye diseases. The detection of OD helps in early detection of proliferative diabetic retinopathy. In this paper two computerized optic disc localization and detection techniques are compared. First technique is uses edge detection method to localize the OD and Hough transform method to detect the OD. Second technique uses brightest region method for OD localization and LOG filtering method for OD detection. These techniques can be used to develop automated diagnostic system for OD localization and detection. We have used publicly available DRIVE and STARE databases for the testing of the two techniques. Experimental results showed that Hough transform technique gives better results.

Non-stereo photographic screening in long-term follow-up for detection of proliferative diabetic retinopathy.

The efficiency of two non-stereo photographs of the posterior pole as a screening device in long-term follow-up for the detection of proliferative diabetic retinopathy was evaluated in a clinical setting among 1341 diabetic hospital patients. False positive findings occurred in 0.4% (6/1341). Severe irreversible sight-threatening complications from undetected proliferative diabetic retinopathy, such as retinal traction detachment or secondary glaucoma, never occurred. Vitreous haemorrhages due to missed new vessels in the photographic area occurred in only 2 out of 3020 photographic reading sessions over a 5.5 year period. Evaluation of the nature, localization and magnitude of new vessels showed that optic disc new vessels were generally over-diagnosed in younger patients and missed in patients aged 45 years or older. New vessels elsewhere were more frequently misdiagnosed in patients older than 50 years. New vessels were most commonly found on the temporal arcades (48%) of the eyes and nasal to the optic disc (42%) but were significantly rare beyond the posterior pole (13%) (P less than 0.001). Patients younger than 60 years had significantly more lesions (P less than 0.001) and these lesions tended to be bilateral. Two non-stereo photographs of the posterior pole is a safe and efficient alternative method to conventional survey for proliferative diabetic retinopathy. New vessels are significantly most common in the posterior pole and complications from new vessels occurring exclusively outside the posterior pole can be disregarded. Bilateral neovascularization should be anticipated in patients under 60 years.

Characterisation of the neovascularisation process in diabetic retinopathy by means of fractal geometry: diagnostic implications

The neovascularisation formation and regression process of the peripheral retina in diabetic retinopathy was studied by means of fractal analysis. The fractal dimension of the local retinal vessel pattern was calculated to be significantly lower before formation of relevant neovascularisations than 2.5 years later, after formation of strong preretinal neovascularisations. Another year later the new vessels had regressed partially and the fractal dimension was again significantly reduced. This behaviour is almost independent of the representation of the vessel thickness during calculation. Since the retinal vasculature is a fractal, the fractal dimension appears as the "natural" measure of proliferative retinal vessel changes. It is demonstrated that the fractal dimension can be applied to characterise proliferative diabetic retinopathy. These features offer the possibility for computer-driven ("automated") quantitative characterisation of the treatment effect in proliferative diabetic retinopathy and possibly automated detection of proliferative diabetic retinopathy in the future. The limitations of the method are discussed.