scholarly journals ResNet Based Deep Features and Random Forest Classifier for Diabetic Retinopathy Detection

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3883
Author(s):  
Muhammad Kashif Yaqoob ◽  
Syed Farooq Ali ◽  
Muhammad Bilal ◽  
Muhammad Shehzad Hanif ◽  
Ubaid M. Al-Saggaf
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Random Forest ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
State Of The Art ◽  
Random Forest Classifier ◽  
Eye Disease ◽  
Diabetic Patients ◽  
The Right

Diabetic retinopathy, an eye disease commonly afflicting diabetic patients, can result in loss of vision if prompt detection and treatment are not done in the early stages. Once the symptoms are identified, the severity level of the disease needs to be classified for prescribing the right medicine. This study proposes a deep learning-based approach, for the classification and grading of diabetic retinopathy images. The proposed approach uses the feature map of ResNet-50 and passes it to Random Forest for classification. The proposed approach is compared with five state-of-the-art approaches using two category Messidor-2 and five category EyePACS datasets. These two categories on the Messidor-2 dataset include ’No Referable Diabetic Macular Edema Grade (DME)’ and ’Referable DME’ while five categories consist of ‘Proliferative diabetic retinopathy’, ‘Severe’, ‘Moderate’, ‘Mild’, and ‘No diabetic retinopathy’. The results show that the proposed approach outperforms compared approaches and achieves an accuracy of 96% and 75.09% for these datasets, respectively. The proposed approach outperforms six existing state-of-the-art architectures, namely ResNet-50, VGG-19, Inception-v3, MobileNet, Xception, and VGG16.

scholarly journals Fundus Fluorescein Angiography and Optical Coherence Tomography Angiography Findings in Diabetic Retinopathy and Diabetic Macular Edema

2018 ◽  
pp. 130-137
Keyword(s):  
Optical Coherence Tomography ◽  
Diabetic Retinopathy ◽  
Fluorescein Angiography ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Optical Coherence Tomography Angiography ◽  
Imaging Technique ◽  
Diabetic Patients ◽  
Type I ◽  
Optical Coherence

Diabetic retinopathy is an important public health issue as its prevalence has been increasing every year. It is one of the major causes of visual loss which can be preventable with early diagnosis and appropriate treatment. The fundus examination must be done in detail using mydriatics, and digital images must be recorded in all diabetic patients with special emphasis on the disease type (type I and type II), duration, and prognosis. Fluorescein angiography (FA) is a gold standard invasive retinal imaging technique for the diagnosis, monitoring, and evaluating the response of the treatment in diabetic patients, but FA has limitations due to possible side effects. Optical coherence tomography angiography (OCTA) is a recent, non-invasive, dye-free imaging technique that can be used in every visit. It has the capability to image all retinal and choroidal vascular layers (segmentation) and quantify macular ischemia in a short period of time which is beneficial for the patient, and the ophthalmologist. The aim of this review is to address the findings, advantages, and disadvantages of FA and OCTA in patients with diabetic retinopathy and diabetic macular edema.

scholarly journals Differentiating features of OCT angiography in diabetic macular edema

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Reza Mirshahi ◽  
Hamid Riazi-Esfahani ◽  
Elias Khalili Pour ◽  
Kaveh Fadakar ◽  
Parsa Yarmohamadi ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Optical Coherence Tomography Angiography ◽  
Vascular Density ◽  
Diabetic Patients ◽  
Foveal Thickness ◽  
Central Foveal Thickness ◽  
Capillary Plexus ◽  
Superficial Capillary Plexus

AbstractThe purpose of current study was to evaluate different optical coherence tomography angiography (OCTA) metrics in eyes with diabetic retinopathy with and without diabetic macular edema (DME). In this retrospective study, macular OCTA images of eyes with non-proliferative or proliferative diabetic retinopathy were evaluated. Vascular density, vascular complexity and non-perfusion densities were compared between eyes with and without DME. One-hundred-thirty-eight eyes of 92 diabetic patients including 49 eyes with DME were included. In multivariate analysis, the presence of DME was positively associated with geometric perfusion deficit (GPD) in superficial capillary plexus (SCP), capillary non-perfusion (CNP) of SCP, and GPD in deep capillary plexus (DCP) (all P < 0.05). In eyes with DME, central foveal thickness was associated with VD ratio (SCP/DCP) (P = 0.001) and FAZ area (P = 0.001). In conclusion, in eyes with diabetic retinopathy, the presence of DME was associated with more extensive capillary non-perfusion compared to those with no macular edema.

Photocoagulation for Diabetic Macular Edema

2020 ◽  
pp. 169-176
Author(s):  
Alan D. Penman ◽  
Kimberly W. Crowder ◽  
William M. Watkins
Keyword(s):  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Laser Photocoagulation ◽  
Argon Laser ◽  
Diabetic Patients ◽  
Nonproliferative Diabetic Retinopathy ◽  
Argon Laser Photocoagulation ◽  
Clinically Significant Macular Edema ◽  
Clinically Significant

The Early Treatment Diabetic Retinopathy Study (ETDRS) was a randomized clinical trial involving nearly four thousand diabetic patients with early proliferative retinopathy, moderate to severe nonproliferative retinopathy, and/or diabetic macular edema in each eye. This paper (ETDRS report number 1) describes the findings in the subgroup of eyes in the ETDRS that were identified as having mild to moderate nonproliferative diabetic retinopathy and macular edema. The analysis showed that immediate focal argon laser photocoagulation of “clinically significant” diabetic macular edema substantially reduced the risk of visual loss, increased the chance of visual improvement, decreased the frequency of persistent macular edema, and caused only minor visual field losses. The authors recommended immediate focal argon laser photocoagulation for all eyes with clinically significant macular edema and mild or moderate nonproliferative diabetic retinopathy, regardless of the level of visual acuity.

scholarly journals Detection of Diabetic Macular Edema in Optical Coherence Tomography Image Using an Improved Level Set Algorithm

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Zhenhua Wang ◽  
Wenping Zhang ◽  
Yanan Sun ◽  
Mudi Yao ◽  
Biao Yan
Keyword(s):  
Optical Coherence Tomography ◽  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Level Set ◽  
Diabetic Patients ◽  
Optical Coherence Tomography Image ◽  
Optical Coherence ◽  
Oct Image ◽  
Novel Algorithm

Diabetic macular edema (DME) is a major cause of visual loss in the patients with diabetic retinopathy. DME detection in Optical Coherence Tomography (OCT) image contributes to the early diagnosis of diabetic retinopathy and blindness prevention. Currently, DME detection in the OCT image mainly relies on the handwork by the experienced clinician. It is a laborious, time-consuming, and challenging work to organize a comprehensive DME screening for diabetic patients. In this study, we proposed a novel algorithm for the detection and segmentation of DME region in OCT image based on the K-means clustering algorithm and improved Selective Binary and Gaussian Filtering regularized level set (SBGFRLS) algorithm named as SBGFRLS-OCT algorithm. SBGFRLS-OCT algorithm was compared with the current level set algorithms, including C-V (Chan-Vese), GAC (geodesic active contour), and SBGFRLS, to estimate the performance of DME detection. SBGFRLS-OCT algorithm was also compared with the clinician to estimate the precision, sensitivity, and specificity of DME segmentation. Compared with C-V, GAC, and SBGFRLS algorithm, the SBGFRLS-OCT algorithm enhanced the accuracy and reduces the processing time of DME detection. Compared with manual DME segmentation, the SBGFRLS-OCT algorithm achieved a comparable precision (97.7%), sensitivity (91.8%), and specificity (99.2%). Collectively, this study presents a novel algorithm for DME detection in the OCT image, which can be used for mass diabetic retinopathy screening.

scholarly journals Association of periodontitis and diabetic macular edema in various stages of diabetic retinopathy

2021 ◽  
Author(s):  
Marlene Lindner ◽  
Behrouz Arefnia ◽  
Domagoj Ivastinovic ◽  
Harald Sourij ◽  
Ewald Lindner ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Cross Sectional Study ◽  
Diabetic Patients ◽  
Pocket Depth ◽  
Cross Sectional ◽  
Early Stages ◽  
Surface Areas ◽  
Late Stages

Abstract Objectives Periodontitis and diabetes are known to have a bidirectional relationship. Diabetic macular edema is a complication of diabetes that is strongly influenced by inflammatory pathways. However, it remains to be established whether inflammation at other locations, such as periodontitis, affects diabetic macular edema. Here, we investigated the prevalence of periodontitis in patients treated for diabetic macular edema. Materials and methods Patients with diabetic macular edema were recruited for this cross-sectional study at the Medical University of Graz. Macular edema was documented by optical coherence tomography. Periodontal status was assessed by computerized periodontal probing and panoramic X-ray imaging. Bleeding on probing, clinical attachment level, probing pocket depth, and plaque index were compared between different stages of diabetic retinopathy. Results Eighty-three eyes of 45 patients with diabetic macular edema were enrolled. Forty-four eyes (53.0%) had early stages of diabetic retinopathy (mild and moderate), and 39 eyes (47.0%) had late stages (severe and proliferative). Patients with mild or moderate DR were more likely to have more severe periodontal conditions than patients with severe or proliferative DR. Fourteen patients with mild DR (82.4%), 7 patients with moderate DR (87.5%), 4 patients with severe DR (100.0%), and 15 patients with proliferative DR (93.8%) had some degree of PD. The periodontal inflamed surface areas and the percentages of tooth sites that bled on probing were significantly higher in patients with early stages of diabetic retinopathy than in those with late stages of the disease (p < 0.05). Patients with periodontal inflamed surface areas of more than 500 mm2 required significantly more intravitreal injections in the last year than those with milder forms of periodontitis (n = 6.9 ± 3.1 versus n = 5.0 ± 3.5, p = 0.03). Conclusion In patients with diabetic macular edema, periodontitis is more prevalent in early stages of diabetic retinopathy. We suggest regular dental check-ups for diabetic patients, especially when diabetic macular edema is already present. Clinical relevance Patients with diabetic macular edema should be screened for periodontitis and vice versa, particularly early in the course of diabetes.

scholarly journals A predictive screening tool to detect diabetic retinopathy or macular edema in primary health care: construction, validation and implementation on a mobile application

PeerJ ◽  
2015 ◽  
Vol 3 ◽  
pp. e1404 ◽  
Author(s):  
Cesar Azrak ◽  
Antonio Palazón-Bru ◽  
Manuel Vicente Baeza-Díaz ◽  
David Manuel Folgado-De la Rosa ◽  
Carmen Hernández-Martínez ◽  
...  
Keyword(s):  
Visual Acuity ◽  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Care Physician ◽  
Mobile App ◽  
Diabetic Patients ◽  
Binary Logistic Regression Model ◽  
Foveal Thickness ◽  
Cross Sectional

The most described techniques used to detect diabetic retinopathy and diabetic macular edema have to be interpreted correctly, such that a person not specialized in ophthalmology, as is usually the case of a primary care physician, may experience difficulties with their interpretation; therefore we constructed, validated and implemented as a mobile app a new tool to detect diabetic retinopathy or diabetic macular edema (DRDME) using simple objective variables. We undertook a cross-sectional, observational study of a sample of 142 eyes from Spanish diabetic patients suspected of having DRDME in 2012–2013. Our outcome was DRDME and the secondary variables were: type of diabetes, gender, age, glycated hemoglobin (HbA1c), foveal thickness and visual acuity (best corrected). The sample was divided into two parts: 80% to construct the tool and 20% to validate it. A binary logistic regression model was used to predict DRDME. The resulting model was transformed into a scoring system. The area under the ROC curve (AUC) was calculated and risk groups established. The tool was validated by calculating the AUC and comparing expected events with observed events. The construction sample (n= 106) had 35 DRDME (95% CI [24.1–42.0]), and the validation sample (n= 36) had 12 DRDME (95% CI [17.9–48.7]). Factors associated with DRDME were: HbA1c (per 1%) (OR = 1.36, 95% CI [0.93–1.98],p= 0.113), foveal thickness (per 1 µm) (OR = 1.03, 95% CI [1.01–1.04],p< 0.001) and visual acuity (per unit) (OR = 0.14, 95% CI [0.00–0.16],p< 0.001). AUC for the validation: 0.90 (95% CI [0.75–1.00],p< 0.001). No significant differences were found between the expected and the observed outcomes (p= 0.422). In conclusion, we constructed and validated a simple rapid tool to determine whether a diabetic patient suspected of having DRDME really has it. This tool has been implemented on a mobile app. Further validation studies are required in the general diabetic population.

scholarly journals Iterative Update of a Random Forest Classifier for Diabetic Retinopathy

2021 ◽  
Author(s):  
Jordi Pascual-Fontanilles ◽  
Aida Valls ◽  
Antonio Moreno ◽  
Pedro Romero-Aroca
Keyword(s):  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Random Forest ◽  
Random Forests ◽  
Random Forest Classifier ◽  
Diabetic Patients ◽  
Similar Data ◽  
Machine Learning Classification ◽  
Inherent Ambiguity ◽  
New Iterative Method

Random Forests are well-known Machine Learning classification mechanisms based on a collection of decision trees. In the last years, they have been applied to assess the risk of diabetic patients to develop Diabetic Retinopathy. The results have been good, despite the unbalance of data between classes and the inherent ambiguity of the problem (patients with similar data may belong to different classes). In this work we propose a new iterative method to update the set of trees in the Random Forest by considering trees generated from the data of the new patients that are visited in the medical centre. With this method, it has been possible to improve the results obtained with standard Random Forests.

scholarly journals Incidence of diabetic eye disease in accordance with duration, glycemic control, blood and ocular pressure

2017 ◽  
Vol 70 (11-12) ◽  
pp. 353-358
Author(s):  
Vladimir Canadanovic ◽  
Sandra Jovanovic ◽  
Sofija Davidovic ◽  
Ana Oros ◽  
Vladislav Dzinic ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Diabetic Retinopathy ◽  
Glycemic Control ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Proliferative Diabetic Retinopathy ◽  
Glycosylated Hemoglobin ◽  
Diabetic Patients ◽  
Duration Of Diabetes ◽  
Group I

Introduction. Diabetic retinopathy remains the leading cause of visual disability and blindness among professionally active adults in economically developed societies, which is of particular concern because the prevalence and incidence of diabetes mellitus is expected to increase sharply during the next decade. There are several known factors responsible for the development of diabetic retinopathy, duration of disease and blood sugar level being the most important ones. Material and Methods. Prospective study of 280 diabetic patients (diabetes mellitus type 2) divided into 3 groups according to the duration of diabetes mellitus. All diabetic patients underwent complete ophthalmological examination in artificial mydriasis and optic coherence tomography. A full medical history included patient age, the time elapsed from diabetes diagnosis, current treatment of diabetes, presence of hypertension and glycemic control assessed by glycosylated hemoglobin measurement. Results. The mean age of patients was 63.5 years (SD?6.5, range 57-70 years). Mean duration of diabetes was 7.3 years in group I, 12.4 years in group II and 17.2 years in group III. The average value of glycosylated hemoglobin was 6.58% in the group I, 7.64% in the group II and 8.29% in the third group of patients. No statistically significant difference in intraocular pressure and the level of blood pressure were found among groups. Cataract was present in 104 patients (37.1%). Complications related to diabetes among all patients included in our study were: nonproliferative diabetic retinopathy in 48.5%, proliferative diabetic retinopathy in 25.7% and diabetic macular edema in 22.5% of patients. Conclusion. The duration of diabetes is one of the most significant factors for the development of diabetic maculopathy and the progression from nonproliferative to its proliferative stage. There is significantly higher incidence of proliferative diabetic retinopathy and diabetic macular edema in patients with increased serum level of glycosylated hemoglobin. Diabetes accompanied by hypertension is related to worsening of the clinical course of diabetic eye diseases and developing diabetic macular edema and proliferative diabetic retinopathy.

Image Processing for the Detection of Diabetic Retinopathy and Diabetic Macular Edema

2019 ◽  
Vol 3 (1) ◽  
Author(s):  
R. Manjula Sri ◽  
K.M. M. Rao
Keyword(s):  
Image Processing ◽  
Diabetic Retinopathy ◽  
Macular Edema ◽  
Blood Vessels ◽  
Diabetic Macular Edema ◽  
Severity Index ◽  
Diabetic Patients ◽  
Color Analysis ◽  
Hard Exudates ◽  
Patients With Diabetes

Diabetic retinopathy (DR) and diabetic macular edema (DME) are common microvascular retinal diseases in patients with diabetes. The diabetic patients may have a sudden and devastating impact on visual acuity, in the long run leading to blindness. Advanced stages of DR are characterized by the growth of abnormal retinal blood vessels secondary to ischemia. These blood vessels grow in an attempt to supply oxygenated blood to the hypoxic retina. At any time during the progression of DR, patients with diabetes can also develop DME, which involves retinal thickening in the macular area. In the present paper, algorithms are developed to detect DR and DME. For detecting DR the abnormalities in the retina blood vessels are detected by classifying the common abnormalities namely microaneurisms, hard exudates, heammorages and cotton wool spots. DME is detected by finding the nearness of Hard exudate to macula. The macula and hard exudates are localized using image processing techniques. Severity of DME is assessed based on the nearest exudates, their area and color analysis. The algorithm is tested with 65 DR and DME images with severity index 0, 1 and 2 from MESSIDOR database.

Sign in / Sign up

Export Citation Format

Share Document