Digital Retinal Images Research Articles

Choroidal Neovascularisation Classification on Fundus Retinal Images Using Local Linear Estimator

Choroidal neovascularization describes the abnormal growth of vessels from the choriocapillaris through the Bruch membrane into the space beneath the retinal pigment epithelium or the space beneath the retina. Choroidal neovascularization detection is considered to be the most important feature in the pathogenesis and treatment of a number of chorioretinal disorders, one of which to detection in digital fundus retinal images. In this study, we classify choroidal neovascularization by using statistical modeling approach based on local linear estimator. Based on 40 in samples and 10 out samples data images, we obtain the same accuracy of classification of 90 percent and their sensitivity are 90 percent and 83.33 percent, respectively. So, we conclude that the local linear is a good estimator to classify choroidal neovascularization on fundus retinal image.

Diabetic Retinopathy Assessment Variability Among Eye Care Providers in an Urban Teleophthalmology Program.

Background: Teleophthalmology is an evidence-based method for diabetic eye screening. It is unclear whether the type of eye care provider performing teleophthalmology interpretation produces significant variability.Introduction: We assessed grading variability between an optometrist, general ophthalmologist, and retinal specialist using images from an urban, diabetic retinopathy teleophthalmology program.Methods: Three readers evaluated digital retinal images in 100 cases (178 eyes from 90 patients with type 2 diabetes). Fisher's exact test, percent agreement, and the observed proportion of positive (Ppos) or negative agreement (Pneg) were used to assess variability.Results: Among cases deemed gradable by all three readers (n = 65), there was substantial agreement on absence of any retinopathy (88% ± 4.6%, Pneg = 0.91–0.95), presence of moderate nonproliferative or worse retinopathy (87% ± 3.9%, Ppos = 0.67–1.00), and presence of macular edema (99% ± 0.9%, Ppos = 0.67–1.00). There was limited agreement regarding presence of referable nondiabetic eye pathology (61% ± 11%, Ppos = 0.21–0.59) and early, nonroutine referral for a follow-up clinical eye exam (66% ± 8.1%, Ppos = 0.19–0.54). Among all cases (n = 100), there was acceptable agreement regarding which had gradable images (77% ± 5.0%, Ppos = 0.50–0.90).Discussion: Inclusion of multiple types of eye care providers as teleophthalmology readers is unlikely to produce significant variability in the assessment of diabetic retinopathy among high-quality images. Greater variability was found regarding image gradability, nondiabetic eye pathology, and recommended clinical referral times.Conclusions: Our results suggest that more extensive training and uniform referral standards are needed to improve consensus on image gradability, referable nondiabetic eye pathology, and recommended clinical referral times.

Retinal Blood Vessel Extraction From Fundus Images Using Improved Otsu Method

In the present time, the identification of blood vessels is a basic task for diagnosis of various eye abnormalities. So, this article offers an instinctive approach for identification of blood vessels in ophthalmoscope images. This approach includes three different phases: pre-processing, vessel extraction and post-processing for getting a final vessel segmentation outcome. In the presented method, formerly log transformation and contrast limited adaptive histogram equalization are used for the enhancement of retinal images. The enhanced image is then filtered using a morphological opening operation and subsequently the optic disk is removed. The second phase includes the application of the improved Otsu method on the pre-processed image for the identification of blood vessels. Lastly, the resultant vessel-segmented image is obtained by using the morphological cleaning operation. The proposed method is fast, time efficient, and gives consistent accuracy for all retinal images. It is more robust and easier to implement compared to other traditional methods. The performance of the presented method is evaluated using ten different mathematical measures. It achieves average sensitivity, specificity and accuracy of 0.710, 0.982 and 0.956 for the digital retinal images for vessel extraction (DRIVE) database, 0.738, 0.982 and 0.954 for the structure analysis of the retina (STARE) database and 0.737, 0.964 and 0.949 for the child heart and health study in England (CHASE_DB1) database. The presented method also performs better in segmenting thin vessels by giving average accuracies of 0.964, 0.954 and 0.965 for DRIVE, STARE and CHASE_DB1 databases respectively.

Polynomial modeling of retinal vessels for tortuosity measurement

Tortuosity is one of the micro vascular change that is observed in many retinopathies. Its early detection can prevent the progression of various retinopathies to a critical stage at which a person may become blind. Here, we propose a novel method for the measurement of tortuosity by polynomial modeling of retinal vessels for the analysis of hypertensive retinopathy. The proposed method is tested on a set of 30 arteries and 30 veins vessel images collected from the Retinal Vessel Tortuosity Dataset (RET-TORT). Also, 90 vessel segments from Digital Retinal Images for Vessel Extraction (DRIVE) and 149 vessel segments from High Resolution Fundus (HRF) databases are used for tortuosity evaluation. The experimental results demonstrate that the order of the polynomial increases with the increase in the tortuosity of the blood vessels. Hence, the order of the polynomial can be used as a parameter to classify vessels as non-tortuous and tortuous. The results of the method are also evaluated subjectively and the inter-rater agreement analysis is made by using Fleiss Kappa index. The Spearman's rank order correlation coefficient is used to analyze the correlation between the ranking provided by the expert in the RET-TORT database and the ranking obtained by the proposed method. The results demonstrate that this method is capable of evaluating the tortuosity and classify vessel segments into non-tortuous or tortuous effectively.

A novel diagnostic information based framework for super-resolution of retinal fundus images

Advancements in tele-medicine have led to the development of portable and cheap hand-held retinal imaging devices. However, the images obtained from these devices have low resolution (LR) and poor quality that may not be suitable for retinal disease diagnosis. Therefore, this paper proposes a novel framework for the super-resolution (SR) of the LR fundus images. The method takes into consideration the diagnostic information in the fundus images during the SR process. In this work, SR is performed on the zone of interest of the fundus images. Clinical information of the selected zone is captured using the Shannon entropy, the contrast sensitivity index (CSI), the multi-resolution (MR) intra-band energy and the MR inter-band eigen features. The support vector machine (SVM) classifier is used to decide the clinical significance of the zone. Highly accurate learning based SR method or the bicubic interpolation is applied to the selected zone based on the classification output. The method is tested on the Standard Diabetic Retinopathy Database Calibration level 1 (DIARETDB1) and the Digital Retinal Images for Vessel Extraction (DRIVE) databases. Classification accuracy of 85.22% and 85.77% is achieved for the DIARETDB1 and DRIVE databases respectively. The SR performance of the algorithm is quantified in terms of peak signal to noise ratio (PSNR), structural similarity index measure (SSIM) and computational time. The proposed diagnostic information based SR achieves computational time efficiency without compromising with the high resolution (HR) reconstruction accuracy of the fundus image zones.

Automated techniques for blood vessels segmentation through fundus retinal images: A review.

Retina is the interior part of human's eye, has a vital role in vision. The digital image captured by fundus camera is very useful to analyze the abnormalities in retina especially in retinal blood vessels. To get information of blood vessels through fundus retinal image, a precise and accurate vessels segmentation image is required. This segmented blood vessel image is most beneficial to detect retinal diseases. Many automated techniques are widely used for retinal vessels segmentation which is a primary element of computerized diagnostic systems for retinal diseases. The automatic vessels segmentation may lead to more challenging task in the presence of lesions and abnormalities. This paper briefly describes the various publicly available retinal image databases and various machine learning techniques. State of the art exhibited that researchers have proposed several vessel segmentation methods based on supervised and supervised techniques and evaluated their results mostly on publicly datasets such as digital retinal images for vessel extraction and structured analysis of the retina. A comprehensive review of existing supervised and unsupervised vessel segmentation techniques or algorithms is presented which describes the philosophy of each algorithm. This review will be useful for readers in their future research.

Imaging in Retinopathy of Prematurity.

Retinopathy of prematurity (ROP) is a leading cause of preventable childhood blindness worldwide. Barriers to ROP screening and difficulties with subsequent evaluation and management include poor access to care, lack of physicians trained in ROP, and issues with objective documentation. Digital retinal imaging can help address these barriers and improve our knowledge of the pathophysiology of the disease. Advancements in technology have led to new, non-mydriatic and mydriatic cameras with wider fields of view as well as devices that can simultaneously incorporate fluorescein angiography, optical coherence tomography (OCT), and OCT angiography. Image analysis in ROP is also being employed through smartphones and computer-based software. Telemedicine programs in the United States and worldwide have utilized imaging to extend ROP screening to infants in remote areas and have shown that digital retinal imaging can be reliable, accurate, and cost-effective. In addition, tele-education programs are also using digital retinal images to increase the number of healthcare providers trained in ROP. Although indirect ophthalmoscopy is still an important skill for screening, digital retinal imaging holds promise for more widespread screening and management of ROP.

Retinal Blood Vessel Segmentation as a Tool to Detect Diabetic Retinopathy

The retina is an important part of the eye for humans. In besides its main function as part of the sense of sight, in the world medically, the retina after an image can be used to detect a number diseases, such as diabetic retinopathy. To detect a number of diseases, Retinal digital images taken using a digital fundus camera are used. In detecting diabetic retinopathy, digital images are needed segmented retina. Nevertheless, automatic segmentation of digital images the retina is a complex work, given the presence of artifacts as well as noise on the retinal digital image, evenly illuminated, intensity low, low contrast, and varying lengths of retinal blood vessels. In this research, a blood vessel segmentation software system has been designed through three stages image processing, namely (i) preprocessing, (ii) improving image quality, (iii) and segmentation of retinal blood vessels. With three image processing stages, the performance value is obtained, i.e . 84.62 .

Edge, Ridge, and Blob Detection with Symmetric Molecules

We present a novel approach to the detection and characterization of edges, ridges, and blobs in two-dimensional images which exploits the symmetry properties of directionally sensitive analyzing functions in multiscale systems that are constructed in the framework of alpha-molecules. The proposed feature detectors are inspired by the notion of phase congruency, stable in the presence of noise, and by definition invariant to changes in contrast. We also show how the behavior of coefficients corresponding to differently scaled and oriented analyzing functions can be used to obtain a comprehensive characterization of the geometry of features in terms of local tangent directions, widths, and heights. The accuracy and robustness of the proposed measures are validated and compared to various state-of-the-art algorithms in extensive numerical experiments in which we consider sets of clean and distorted synthetic images that are associated with reliable ground truths. To further demonstrate the applicability, we show how the proposed ridge measure can be used to detect and characterize blood vessels in digital retinal images and how the proposed blob measure can be applied to automatically count the number of cell colonies in a Petri dish.

Automated Segmentation of Optic Disc and Cup in Color Fundus Images

An automatic Optic disc and Optic cup detection technique which is an important step in developing systems for computer-aided eye disease diagnosis is presented in this paper. This paper presents an algorithm for localization and segmentation of optic disc from digital retinal images. OD localization is achieved by circular Hough transform using morphological preprocessing and segmentation is achieved by watershed transformation. Optic cup segmentation is achieved by marker controlled watershed transformation. The optic disc to cup ratio (CDR) is calculated which is an important parameter for glaucoma diagnosis. The presented algorithm is evaluated against publically available DRIVE dataset. The presented methodology achieved 88% average sensitivity and 80% average overlap. The average CDR detected is 0.1983.

The Accuracy of Digital Imaging in Diagnosis of Retinopathy of Prematurity in Iran: A Pilot Study.

Purpose:To evaluate sensitivity and specificity of digital retinal image reading in the diagnosis of referral-warranted retinopathy of prematurity (ROP).Methods:Infants referred to the ROP clinic underwent fundus examination through indirect ophthalmoscopy. Fundus photographs were acquired using RetCam (shuttle 2; Clarity medical systems, Pleasanton, CA, USA). Four retinal specialists who were blind to patients’ information reviewed the RetCam fundus photographs. By comparing the results of photographs’ readings with that of indirect ophthalmoscopy as the gold standard, the sensitivity and specificity of telescreening was determined.Results:A total of 147 treatment-naïve patients met the inclusion criteria and were enrolled in the study. Mean gestational age (GA) was 28.6 ± 2.0 weeks. Digital retinal imaging had sensitivity of 85% and specificity of 35% in detecting referral-warranted ROP in our study. Positive predictive value of digital photography was 80%, and negative predictive value was 43%.Conclusion:Digital photography for diagnosis of ROP may show good potential as a screening modality in developing countries. It can facilitate early diagnosis, prevent unnecessary referrals, and be implemented for investigational purpose. However, the overall study result did not provide evidence to propose digital photography as a substitute for indirect ophthalmoscopy in the diagnosis of ROP.

Automated Exudates Detection in Retinal Fundus Image Using Morphological Operator and Entropy Maximization Thresholding

Blindness which is considered as degrading disabling disease is the final stage that occurs when a certain threshold of visual acuity is overlapped. It happens with vision deficiencies that are pathologic states due to many ocular diseases. Among them, diabetic retinopathy is nowadays a chronic disease that attacks most of diabetic patients. Early detection through automatic screening programs reduces considerably expansion of the disease. Exudates are one of the earliest signs. This paper presents an automated method for exudates detection in digital retinal fundus image. The first step consists of image enhancement. It focuses on histogram expansion and median filter. The difference between filtered image and his inverse reduces noise and removes background while preserving features and patterns related to the exudates. The second step refers to blood vessel removal by using morphological operators. In the last step, we compute the result image with an algorithm based on Entropy Maximization Thresholding to obtain two segmented regions (optical disk and exudates) which were highlighted in the second step. Finally, according to size criteria, we eliminate the other regions obtain the regions of interest related to exudates. Evaluations were done with retinal fundus image DIARETDB1 database. DIARETDB1 gathers high-quality medical images which have been verified by experts. It consists of around 89 colour fundus images of which 84 contain at least mild non-proliferative signs of the diabetic retinopathy. This tool provides a unified framework for benchmarking the methods, but also points out clear deficiencies in the current practice in the method development. Comparing to other recent methods available in literature, we found that the proposed algorithm accomplished better result in terms of sensibility (94.27%) and specificity (97.63%).

A Fundus Retinal Vessels Segmentation Scheme Based on the Improved Deep Learning U-Net Model

Retinal vascular segmentation is very important for diagnosing fundus diseases. However, the existing methods of retinal vascular segmentation have some problems, such as low microvascular segmentation and wrong segmentation of pathological information. To solve these problems, we developed a fundus retinal vessels segmentation based on the improved deep learning U-Net model. First, enhance the retinal images. Second, add the residual module in the process of designing the network structure, which solved the problem of the traditional deep learning U-Net model is not deep enough. By using the improved deep learning U-Net model, it can connect the output of the convolutional layer with the output of the deconvolution layer to avoid low-level information sharing, and solved the problem of performance degradation of deep convolutional neural networks in residual networks under extreme depth conditions. By verifying on the DRIVE (digital retinal images for vessel extraction) dataset, the segmentation accuracy, sensitivity, and specificity of the proposed method are 96.50%, 93.1%, and 98.63% respectively.

The relationship between obstructive sleep apnea and diabetic retinopathy in type 2 diabetes patients, Zagazig University Hospitals, Egypt

Background and objective Obstructive sleep apnea (OSA) and type 2 diabetes mellitus (T2DM) commonly coexist. Both could be associated with a number of pathophysiological derangements involved in the development of diabetic retinopathy (DR). So, the aim of this study was to assess the possible association between OSA and DR. Patients and methods This is a cross-sectional observational study that was conducted on patients with T2DM. Two-field 45°-digital retinal images for each eye were used to evaluate DR and graded according to the English National Screening Program guidelines. OSA was evaluated on the basis of an inpatient overnight sleep study (polysomnography) using a computerized polysomnogram device. Results This work recruited 110 patients. OSA was observed in 60% (66 patients). OSA was found to be independently associated with both advanced DR [preprolifrative (R2) or proliferative (R3)] (odds ratio=6.29; 95% confidence interval: 1.08–6.65; P=0.04) and maculopathy (odds ratio=12.92; 95% confidence interval: 3.97–4.79; P Conclusion OSA was independently associated with advanced DR and maculopathy in T2DM patients. Moreover, severity of OSA was directly related to DR grade.

Diagnostic Accuracy of Digital Retinal Fundus Image Analysis in Detecting Diabetic Maculopathy in Type 2 Diabetes Mellitus

Background: Digital retinal imaging is the gold standard technique for diabetic retinopathy (DR) and diabetic macular oedema (DME) assessment during DR screening. Objectives: To evaluate the diagnostic accuracy of digital retinal fundus image (DRFI) analysis in detecting DME using three manual grading systems (MGS) and comparing it with optical coherence tomography (OCT) findings. Method: A total of 287 DRFI of 287 eyes were analysed. Non-stereoscopic 45° images were acquired using a Kowa VX-20 camera and were graded according to three MGS: Early Treatment Diabetic Retinopathy Study (ETDRS), International Clinical Diabetic Retinopathy (ICDR), and United Kingdom National Screening Committee (UKNSC). The two graders were masked to the patient’s clinical DR status. DME characteristics were analysed using OCTs. Results: A very good agreement in detecting DME was found with Cohen’s κ = 0.83 (ICDR vs. ETDRS), κ = 0.83 (ICDR vs. UKNSC), and κ = 0.82 (ETDRS vs. UKNSC). Sensitivity and specificity of DRFI analysis in DME assessment were 70.0 and 69.6% for UKNSC, 71.9 and 67.4% for ETDRS, and 70.9 and 65.2% for ICDR, respectively. Positive and negative predictive values were 91.7 and 32.7% for UKNSC, 91.4 and 33.3% for ETDRS, and 90.7 and 31.9% for ICDR, respectively. On OCT scans, micro-architectural damages of both inner and outer retinal layers and mean ganglion cell layer thickness showed a significant association with the presence of DME detected with DRFI analysis. Conclusions: Despite the low negative predictive value, the good specificity and sensitivity of DRFI in detecting DME make it a useful tool in a routine clinical setting, and its potential in diabetic eye screening is yet to be realized.

Exporting Diabetic Retinopathy Images from VA VistA Imaging for Research.

The US Department of Veterans Affairs has been acquiring store and forward digital diabetic retinopathy surveillance retinal fundus images for remote reading since 2007. There are 900+ retinal cameras at 756 acquisition sites. These images are manually read remotely at 134 sites. A total of 2.1 million studies have been performed in the teleretinal imaging program. The human workload for reading images is rapidly growing. It would be ideal to develop an automated computer algorithm that detects multiple eye diseases as this would help standardize interpretations and improve efficiency of the image readers. Deep learning algorithms for detection of diabetic retinopathy in retinal fundus photographs have been developed and there are needs for additional image data to validate this work. To further this research, the Atlanta VA Health Care System (VAHCS) has extracted 112,000 DICOM diabetic retinopathy surveillance images (13,000 studies) that can be subsequently used for the validation of automated algorithms. An extensive amount of associated clinical information was added to the DICOM header of each exported image to facilitate correlation of the image with the patient's medical condition. The clinical information was saved as a JSON object and stored in a single Unlimited Text (VR = UT) DICOM data element. This paper describes the methodology used for this project and the results of applying this methodology.

Retinal Blood Vessel Segmentation by Using Matched Filtering and Fuzzy C-means Clustering with Integrated Level Set Method for Diabetic Retinopathy Assessment

BackgroundThe condition of blood vessel network in the retina is an essential part of diagnosing various problems associated with eyes, such as diabetic retinopathy.MethodsIn this study, an automatic retinal vessel segmentation utilising fuzzy c-means clustering and level sets is proposed. Retinal images are contrast-enhanced utilising contrast limited adaptive histogram equalisation while the noise is reduced by using mathematical morphology followed by matched filtering steps that use Gabor and Frangi filters to enhance the blood vessel network prior to clustering. A genetic algorithm enhanced spatial fuzzy c-means method is then utilised for extracting an initial blood vessel network, with the segmentation further refined by using an integrated level set approach.ResultsThe proposed method is validated by using publicly accessible digital retinal images for vessel extraction, structured analysis of the retina and Child Heart and Health Study in England (CHASE_DB1) datasets. These datasets are commonly used for benchmarking the accuracy of retinal vessel segmentation methods where it was shown to achieve a mean accuracy of 0.961, 0.951 and 0.939, respectively.ConclusionThe proposed segmentation method was able to achieve comparable accuracy to other methods while being very close to the manual segmentation provided by the second observer in all datasets.

BAT algorithm inspired retinal blood vessel segmentation

The automated extraction of retinal blood vessels is the course of action in the medical analysis of retinal diseases. The proposed methodology for the retinal vessel segmentation is based on BAT algorithm and random forest classifier. A feature vector of 40-dimensional including local, phase and morphological features is extracted and the feature set which minimises the classifier error is identified by BAT algorithm. The selected features are also identified as the dominant features in the classification. Performance of the proposed method is analysed by the publicly available databases such as digital retinal images for vessel extraction and structured analysis of the retina. The authors’ proposed method is highly sensitive to identify the blood vessels, in view of the fact that it corresponds to the ability of the method to identify the blood vessels correctly. BAT algorithm-based proposed method achieves very high sensitivity and accuracy of about 82.85 and 95.34%, respectively.

A framework for retinal vessel segmentation from fundus images using hybrid feature set and hierarchical classification

Retinal blood vessels play an imperative role in detection of many ailments, such as cardiovascular diseases, hypertension, and diabetic retinopathy. The automated way of segmenting vessels from retinal images can help in early detection of many diseases. In this paper, we propose a framework based on hybrid feature set and hierarchical classification approach to segment blood vessels from digital retinal images. Firstly, we apply bidirectional histogram equalization on the inverted green channel to enhance the fundus image. Six discriminative feature extraction methods have been employed comprising of local intensities, local binary patterns, histogram of gradients, divergence of vector field, high-order local autocorrelations, and morphological transformation. The selection of feature sets has been carried out by classifying vessel and background pixels using random forests and evaluating the segmentation performance for each category of features. The selected feature sets are then used in conjunction with our proposed hierarchical classification approach to segment the vessels. The proposed framework has been tested on the DRIVE, STARE, and CHASEDB1 which are the benchmark datasets for retinal vessel segmentation methods. The results obtained from the experimental analysis show that the proposed framework can achieve better results than most state-of-the-art methods.

A retinal vessel detection approach using convolution neural network with reinforcement sample learning strategy

Computer-aided detection (CAD) provides an efficient way to assist doctors to interpret fundus images. In a CAD system, retinal vessel (RV) detection is an important step to identify the retinal disease regions automatically and accurately. However, RV detection is still a challenging problem due to variations in morphology of the vessels on a noisy background. In this paper, we formulate the detection task as a classification problem and solve it using a convolutional neural network (CNN) as a two-class classifier. The proposed model has 2 convolution layers, 2 pooling layers, 1 dropout layer and 1 loss layer. The contributions of the algorithm are two-fold. First, a new model of CNN is designed to automatically extract features and classify the retinal vessel region. Compared to traditional classification procedures, it is fully automatic and does not need preprocessing and manual extraction and description of features. Second, a novel reinforcement sample learning scheme is proposed to train the CNN with fewer iterations of epochs and less training time. The proposed model is trained and tested using the Digital Retinal Images for Vessel Extraction (DRIVE) and Structured Analysis of the Retina (STARE) data sets. The proposed CNN achieves better performance and significantly outperforms the state-of-the-art for automatic retinal vessel segmentation on the DRIVE data set with 91.99% accuracy and 0.9652 AUC score (area under ROC), and on the STARE data set with 92.20% accuracy and 0.9440 AUC value. We further compare our result with several state-of-the-art methods based on AUC values. The comparison shows that our proposal yields the second best AUC value. This demonstrates the efficiency of the proposed method without pre-processing and with high accuracy and training speed.