Retinopathy Lesions Research Articles

Severity Grading and Early Retinopathy Lesion Detection through Hybrid Inception-ResNet Architecture.

Diabetic retinopathy (DR) is a diabetes disorder that disturbs human vision. It starts due to the damage in the light-sensitive tissues of blood vessels at the retina. In the beginning, DR may show no symptoms or only slight vision issues, but in the long run, it could be a permanent source of impaired vision, simply known as blindness in the advanced as well as in developing nations. This could be prevented if DR is identified early enough, but it can be challenging as we know the disease frequently shows rare signs until it is too late to deliver an effective cure. In our work, we recommend a framework for severity grading and early DR detection through hybrid deep learning Inception-ResNet architecture with smart data preprocessing. Our proposed method is composed of three steps. Firstly, the retinal images are preprocessed with the help of augmentation and intensity normalization. Secondly, the preprocessed images are given to the hybrid Inception-ResNet architecture to extract the vector image features for the categorization of different stages. Lastly, to identify DR and decide its stage (e.g., mild DR, moderate DR, severe DR, or proliferative DR), a classification step is used. The studies and trials have to reveal suitable outcomes when equated with some other previously deployed approaches. However, there are specific constraints in our study that are also discussed and we suggest methods to enhance further research in this field.

Comparison of Two Ultra-Widefield Cameras With High Image Resolution and Wider View for Identifying Diabetic Retinopathy Lesions.

PurposeTo compare the effectiveness of the Optos P200dTx and Zeiss Clarus 500 fundus cameras in detecting diabetic retinopathy (DR) lesions.MethodsA cross-sectional study was conducted among 243 patients with clinically diagnosed diabetes mellitus who were referred for an eye examination from two tertiary eye care centers in Chennai, India. Patients underwent DR screening based on mydriatic fundal images acquired by both fundal cameras. Fundal images from the two separate devices for each eye were compared based on accurately identified pathological retinal lesions with respect to type and location.ResultsWhen studying lesions of the central retina, they were better identified by the Zeiss Clarus compared with the Optos P200dTx, with six out of eight being statistically significant (P < 0.05). However, lesions of the mid-peripheral retina and peripheral retina were better identified by the Optos P200dTx than the Zeiss Clarus, with three out of eight lesions and five out of eight lesions being statistically significant (P < 0.05), respectively. Based on the color and size of lesions, the Optos P200dTx had a higher chance (59.6%) of missing white lesions than did the Zeiss Clarus (17%) (P < 0.0001). Consequently, small- and medium-sized lesions were missed more by the Optos P200dTx (30.72% and 32.63%, respectively) than the Zeiss Clarus (22.3% and 19.30%, respectively).ConclusionsThe capability of detecting or missing a particular DR lesion among diabetics differed between the two cameras based on effective field of view, resolution, and the retinal zone being imaged.Translational RelevanceThe choice of which ultra-widefield camera to be used for screening DR can be based on the greater prevalence of central versus peripheral retinal lesions noted in the patient population seen in a clinical practice.

Deep Bayesian baseline for segmenting diabetic retinopathy lesions: Advances and challenges.

Early diagnosis of retinopathy is essential for preventing retinal complications and visual impairment due to diabetes. For the detection of retinopathy lesions from retinal images, several automatic approaches based on deep neural networks have been developed in the recent years. Most of the proposed methods produce point estimates of pixels belonging to the lesion areas and give no or little information on the uncertainty of method predictions. However, the latter can be essential in the examination of the medical condition of the patient when the goal is early detection of abnormalities. This work extends the recent research with a Bayesian framework by considering the parameters of a convolutional neural network as random variables and utilizing stochastic variational dropout based approximation for uncertainty quantification. The framework includes an extended validation procedure and it allows analyzing lesion segmentation distributions, model calibration and prediction uncertainties. Also the challenges related to the deep probabilistic model and uncertainty quantification are presented. The proposed method achieves area under precision-recall curve of 0.84 for hard exudates, 0.641 for soft exudates, 0.593 for haemorrhages, and 0.484 for microaneurysms on IDRiD dataset.

Weakly supervised anomaly segmentation in retinal OCT images using an adversarial learning approach.

Lesion detection is a critical component of disease diagnosis, but the manual segmentation of lesions in medical images is time-consuming and experience-demanding. These issues have recently been addressed through deep learning models. However, most of the existing algorithms were developed using supervised training, which requires time-intensive manual labeling and prevents the model from detecting unaware lesions. As such, this study proposes a weakly supervised learning network based on CycleGAN for lesions segmentation in full-width optical coherence tomography (OCT) images. The model was trained to reconstruct underlying normal anatomic structures from abnormal input images, then the lesions can be detected by calculating the difference between the input and output images. A customized network architecture and a multi-scale similarity perceptual reconstruction loss were used to extend the CycleGAN model to transfer between objects exhibiting shape deformations. The proposed technique was validated using an open-source retinal OCT image dataset. Image-level anomaly detection and pixel-level lesion detection results were assessed using area-under-curve (AUC) and the Dice similarity coefficient, producing results of 96.94% and 0.8239, respectively, higher than all comparative methods. The average test time required to generate a single full-width image was 0.039 s, which is shorter than that reported in recent studies. These results indicate that our model can accurately detect and segment retinopathy lesions in real-time, without the need for supervised labeling. And we hope this method will be helpful to accelerate the clinical diagnosis process and reduce the misdiagnosis rate.

Fusion of multi-source retinal fundus images via automatic registration for clinical diagnosis

Diabetic retinopathy, age-related macular degeneration and glaucoma, are the leading causes of visual impairment or blindness of the population across different ages. Retinal fundus imaging is a clinically regular tool for the diagnosis of retinal diseases. In the interest of having a comprehensive understanding of the fundus condition, it is valuable to leverage multiple fundus images from different modalities. However, a direct fusion of the multi-source fundus images eases to mis-align the physiological structure or spatial position due to possible eyeball rotations or head movements. The problem turns out to be more severe if the images were corrupted by ill conditions on eyes, such as micro-bleeding and plaques. To tackle this problem, we propose a multi-source registration model for retinal fundus images. Our proposed method considers multiple correspondences and dual structural constraints during the registration process. The method firstly selects adequate feature points by an adjustable threshold selection strategy. Then a feature-guided correspondence estimation model is established to build complementary features. Finally, their spatial transformation is built by using mean shift evolution. The evolution is guided by Tikhonov regularization on dual geometric structures. It overcomes the mess of mean shift vector field and mitigating the ill-posed displacement in field recovery. We have conducted our method on the collected 220 multi-source retinal fundus image pairs, which involve minor and larger displacement or severe retinopathy lesions, as well as additive different intensities of Gaussian noises. Extensive experiments demonstrate that the proposed method consistently outperforms seven feature-based methods.

An Effective Method for Detecting and Classifying Diabetic Retinopathy Lesions Based on Deep Learning.

Diabetic retinopathy occurs as a result of the harmful effects of diabetes on the eyes. Diabetic retinopathy is also a disease that should be diagnosed early. If not treated early, vision loss may occur. It is estimated that one third of more than half a million diabetic patients will have diabetic retinopathy by the 22nd century. Many effective methods have been proposed for disease detection with deep learning. In this study, unlike other studies, a deep learning-based method has been proposed in which diabetic retinopathy lesions are detected automatically and independently of datasets, and the detected lesions are classified. In the first stage of the proposed method, a data pool is created by collecting diabetic retinopathy data from different datasets. With Faster RCNN, lesions are detected, and the region of interests are marked. The images obtained in the second stage are classified using the transfer learning and attention mechanism. The method tested in Kaggle and MESSIDOR datasets reached 99.1% and 100% ACC and 99.9% and 100% AUC, respectively. When the obtained results are compared with other results in the literature, it is seen that more successful results are obtained.

Diabetic Retinopathy Fundus Image Classification and Lesions Localization System Using Deep Learning.

Diabetic retinopathy (DR) is a disease resulting from diabetes complications, causing non-reversible damage to retina blood vessels. DR is a leading cause of blindness if not detected early. The currently available DR treatments are limited to stopping or delaying the deterioration of sight, highlighting the importance of regular scanning using high-efficiency computer-based systems to diagnose cases early. The current work presented fully automatic diagnosis systems that exceed manual techniques to avoid misdiagnosis, reducing time, effort and cost. The proposed system classifies DR images into five stages—no-DR, mild, moderate, severe and proliferative DR—as well as localizing the affected lesions on retain surface. The system comprises two deep learning-based models. The first model (CNN512) used the whole image as an input to the CNN model to classify it into one of the five DR stages. It achieved an accuracy of 88.6% and 84.1% on the DDR and the APTOS Kaggle 2019 public datasets, respectively, compared to the state-of-the-art results. Simultaneously, the second model used an adopted YOLOv3 model to detect and localize the DR lesions, achieving a 0.216 mAP in lesion localization on the DDR dataset, which improves the current state-of-the-art results. Finally, both of the proposed structures, CNN512 and YOLOv3, were fused to classify DR images and localize DR lesions, obtaining an accuracy of 89% with 89% sensitivity, 97.3 specificity and that exceeds the current state-of-the-art results.

Comparison of Ultra-Widefield Imaging and Standard Imaging in Assessment of Early Treatment Diabetic Retinopathy Severity Scale

PurposeTo compare Early Treatment Diabetic Retinopathy Study (ETDRS) severity levels between standard 7-field imaging and ultra-widefield (UWF) imaging and to incorporate peripheral diabetic retinopathy (DR) lesions into the ETDRS grading system.DesignCross-sectional Study.ParticipantsPaired images from 192 eyes (189 participants) with diabetic retinopathy were included.MethodsThe ETDRS levels were determined by masked graders in 3 ways: standard 7-field imaging, UWF within the 7-field region (7-field UWF imaging), and the entire UWF image (global ETDRS imaging).Main Outcome MeasuresPercentage agreement between 7-field and UWF imaging for ETDRS levels.ResultsOf the 166 paired images evaluated, exact agreement was found in 48.8% of eyes between standard 7-field and 7-field UWF ETDRS levels with a weighted κ value of 0.59 (95% confidence interval [CI], 0.5–0.68). Agreement rates varied with DR severity and were least in early DR (30.8%) and moderate nonproliferative DR (26.5%) groups. In 156 eyes with 7-field UWF ETDRS and global UWF ETDRS levels, exact agreement was found in 143 eyes (92%), with a weighted κ value of 0.9 (95% CI, 0.9–0.98). The peripheral lesions contributed to a higher DR severity in 8% and changed the eye to a proliferative DR level in 2%. Reproducibility of the 3 ETDRS evaluations was comparable with a weighted κ value of 0.57 with standard 7-field imaging, 0.65 with 7-field UWF imaging, and 0.60 with global ETDRS scale imaging.ConclusionsModerate agreement was found in the ETDRS DR severity scale between standard 7-field and UWF imaging, indicating caution in interchanging data from the 2 methods. Both methods showed good reproducibility for clinical trial outcome of 2-step change. The global ETDRS scale provides a comprehensive score to incorporate peripheral changes into the ETDRS scale. The implications of the global scale on progression rate are yet to be determined.

Incremental learning for exudate and hemorrhage segmentation on fundus images

Deep-learning-based segmentation methods have shown great success across many medical image applications. However, the custom training paradigms suffer from a well-known constraint of the requirement of pixel-wise annotations, which is labor-intensive, especially when they are required to learn new classes incrementally. Contemporary incremental learning focuses on dealing with catastrophic forgetting in image classification and object detection. However, this work aims to promote the performance of the current model to learn new classes with the help of the previous model in the context of incremental learning of instance segmentation. It enormously benefits the current model when the labeled data is limited because of the high labor intensity of manual labeling. In this paper, on the Diabetic Retinopathy (DR) lesion segmentation problem, a novel incremental segmentation paradigm is proposed to distill the knowledge of the previous model to improve the current model. Remarkably, we propose various approaches working on the class-based alignment of the probability maps of the current and the previous model, accounting for the difference between the background classes of the two models. The experimental evaluation of DR lesion segmentation shows the effectiveness of the proposed approaches.

Testing Segmentation Popular Loss and Variations in Three Multiclass Medical Imaging Problems

Image structures are segmented automatically using deep learning (DL) for analysis and processing. The three most popular base loss functions are cross entropy (crossE), intersect-over-the-union (IoU), and dice. Which should be used, is it useful to consider simple variations, such as modifying formula coefficients? How do characteristics of different image structures influence scores? Taking three different medical image segmentation problems (segmentation of organs in magnetic resonance images (MRI), liver in computer tomography images (CT) and diabetic retinopathy lesions in eye fundus images (EFI)), we quantify loss functions and variations, as well as segmentation scores of different targets. We first describe the limitations of metrics, since loss is a metric, then we describe and test alternatives. Experimentally, we observed that DeeplabV3 outperforms UNet and fully convolutional network (FCN) in all datasets. Dice scored 1 to 6 percentage points (pp) higher than cross entropy over all datasets, IoU improved 0 to 3 pp. Varying formula coefficients improved scores, but the best choices depend on the dataset: compared to crossE, different false positive vs. false negative weights improved MRI by 12 pp, and assigning zero weight to background improved EFI by 6 pp. Multiclass segmentation scored higher than n-uniclass segmentation in MRI by 8 pp. EFI lesions score low compared to more constant structures (e.g., optic disk or even organs), but loss modifications improve those scores significantly 6 to 9 pp. Our conclusions are that dice is best, it is worth assigning 0 weight to class background and to test different weights on false positives and false negatives.

Systematic Comparison of Heatmapping Techniques in Deep Learning in the Context of Diabetic Retinopathy Lesion Detection.

PurposeHeatmapping techniques can support explainability of deep learning (DL) predictions in medical image analysis. However, individual techniques have been mainly applied in a descriptive way without an objective and systematic evaluation. We investigated comparative performances using diabetic retinopathy lesion detection as a benchmark task.MethodsThe Indian Diabetic Retinopathy Image Dataset (IDRiD) publicly available database contains fundus images of diabetes patients with pixel level annotations of diabetic retinopathy (DR) lesions, the ground truth for this study. Three in advance trained DL models (ResNet50, VGG16 or InceptionV3) were used for DR detection in these images. Next, explainability was visualized with each of the 10 most used heatmapping techniques. The quantitative correspondence between the output of a heatmap and the ground truth was evaluated with the Explainability Consistency Score (ECS), a metric between 0 and 1, developed for this comparative task.ResultsIn case of the overall DR lesions detection, the ECS ranged from 0.21 to 0.51 for all model/heatmapping combinations. The highest score was for VGG16+Grad-CAM (ECS = 0.51; 95% confidence interval [CI]: [0.46; 0.55]). For individual lesions, VGG16+Grad-CAM performed best on hemorrhages and hard exudates. ResNet50+SmoothGrad performed best for soft exudates and ResNet50+Guided Backpropagation performed best for microaneurysms.ConclusionsOur empirical evaluation on the IDRiD database demonstrated that the combination DL model/heatmapping affects explainability when considering common DR lesions. Our approach found considerable disagreement between regions highlighted by heatmaps and expert annotations.Translational RelevanceWe warrant a more systematic investigation and analysis of heatmaps for reliable explanation of image-based predictions of deep learning models.

A Fuzzy clustering Approach for Micro Aneurysm Lesion Detection in Diabetic Retinopathy

Diabetic retinopathy (DR) be the significant difficulty of diabetes, and micro aneurysm (MA) is an earliest diabetic retinopathy lesion, making early detection of MA a key factor in diabetic retinopathy. DR is a direct or indirect effect on human vision caused by chronic diabetes. During its early stages DR is asymptomatic, and the late diagnosis leads to undeviating vision loss. The computer-assisted diagnosis helps with prompt and effective care, with the aid of medical photos. MA mark the beginning of DR making it a vital screening stage for this disorder. Diabetic retinopathy is a persistent infection of eye that can be the reason of blindness unless it is diagnosed and treated in due course. Early discovery with analysis of diabetic retinopathy is vital to vision preservation of patient. Precise recognition of MA be the crucial method towards early diagnosis of DR, since they occur as the first symptom of the disease. The segmentation of MA is performed using the Fuzzy C algorithm, and the extraction of features is performed with Gray Level Co-occurrence Matrix ( GLCM) as the set of characteristic for KNN. This technique aims to improve classification accuracy within an ensemble. A procedure is suggested here that recognizes the first DR sign called MA using images from the retinal fundus. Effective diagnosis of DR is very critical in the defense of patients' right to see. The procedure proposed is tested using publicly available databases of retinal images and greater accuracy is achieved.

Automated Diagnostic Hybrid Lesion Detection System for Diabetic Retinopathy Abnormalities

Background: Early diagnosis, monitoring disease progression, and timely treatment of Diabetic Retinopathy (DR) abnormalities can efficiently prevent visual loss. A prediction system for the early intervention and prevention of eye diseases is important. The contrast of raw fundus image is also a hindrance in effective manual lesion detection technique. Methods: In this research paper, an automated lesion detection diagnostic scheme has been proposed for early detection of retinal abnormalities of red and yellow pathological lesions. The algorithm of the proposed Hybrid Lesion Detection (HLD) includes retinal image pre-processing, blood vessel extraction, optical disc localization and detection stages for detecting the presence of diabetic retinopathy lesions. Automated diagnostic systems assist the ophthalmologists practice manual lesion detection techniques which are tedious and time-consuming. Detailed statistical analysis is performed on the extracted shape, intensity and GLCM features and the optimal features are selected to classify DR abnormalities. Exhaustive statistical investigation of the proposed approach using visual and empirical analysis resulted in 31 significant features. Results: The results show that the HLD approach achieved good classification results in terms of three statistical indices: accuracy, 98.9%; sensitivity, 97.8%; and specificity, 100% with significantly less complexity. Conclusion: The proposed technique with optimal features demonstrates improvement in accuracy as compared to state of the art techniques using the same database.

COMPARISON BETWEEN STANDARD AND WIDEFIELD FLUORESCIEN ANGIOOGRAPHY IN DETECTING NEW VESSELS IN DIABETIC RETINOPATHY PATIENTS

• Diabetic retinopathy (DR) is a sight-threatening complication of diabetes and is known to be the leading cause of blindness.• Fluorescein angiography is one of the most important tools for evaluating diabetic retinopathy.• The peripheral retina is the site of many diabetic retinopathy lesions, Therefore evaluation of the retinal periphery is important for screening, diagnosis, monitoring, and treatment of DR• Conventional (FA) covers retinal area of 30°- 60° in one exposure. Hence it is a time-consuming procedure to angiograph the retinal periphery and it depends on patient`s cooperation and operator`s expertise. • Recently, Heidelberg Spectralis ultra-widefield angiography module was developed and it consists of an interchangeable noncontact 102° lens that attaches to the camera head to provide high-contrast, undistorted and evenly illuminated 102° images in one exposure and at the same time point. Aim of the work:• The aim of this study is to compare the HEIDELBERG SPECTRALIS Standard field 55° lens and UWF 102° lens in diagnosis and evaluation of severity of DR and detection of new vascularization.

Differential distribution of manifest lesions in diabetic retinopathy by fundus fluorescein angiography and fundus photography

BackgroundTo analyze the distribution of manifest lesions of diabetic retinopathy (DR) by fundus fluorescein angiography (FFA) and color fundus photography (FP).MethodsA total of 566 eyes of 324 Chinese patients diagnosed with DR were included in this retrospective study. DR severity was graded by the international grading criterion. The distributions of microaneurysms (MA), intraretinal hemorrhages/exudates (He/Ex), intraretinal microvascular abnormality (IRMA), capillary nonperfusion areas (NPA), and neovascularization (NV) were estimated by multiple logistic regression analyse based on nine-field FFA and FP images.ResultsIn mild nonproliferative diabetic retinopathy (NPDR), the highest frequency of MA was found in the posterior pole (67.7%), followed by the inferior nasal (59.4%), and the nasal (55.4%) fields. In moderate NPDR, MA frequently distributed in the posterior pole (98.0%), nasal (97.0%), superior (96.0%), inferior nasal (94.9%), and inferior (92.9%) fields, whereas He/Ex were most prevalent in the posterior pole (69.7%). In severe NPDR and proliferative DR, IRMA, NPA, and NV were more frequent in the nasal field, particularly in the inferior nasal field (60.3, 38.7, and 76.0%, respectively). All lesions were more observed in the combined posterior pole, nasal, and inferior nasal fields than in the posterior pole or combined two fields in the early and severe stages of DR (P < 0.05).ConclusionsThe manifest lesions of DR were common in the nasal field besides the posterior pole in Chinese patients. A combined examination of the posterior pole, nasal, and inferior nasal mid-peripheral retina would help to detect different retinal lesions of DR.Trial registrationClinicalTrial. gov, NCT03528720. Registered 18 May 2018 - Retrospectively registered.

Interaction Between the Distribution of Diabetic Retinopathy Lesions and the Association of Optical Coherence Tomography Angiography Scans With Diabetic Retinopathy Severity

Studies have not yet determined whether the distribution of lesions in the retinal periphery alters the association between the severity of diabetic retinopathy (DR) and macular vessel density. To evaluate the association of DR lesion distribution with optical coherence tomography angiography (OCTA) metrics and DR severity. This cross-sectional observational study was conducted at a tertiary care center for diabetic eye disease among 225 patients with type 1 or 2 diabetes who had undergone imaging between February 15, 2016, and December 31, 2019. Optical coherence tomography angiography 3 × 3-mm macular scans and ultra-widefield color imaging. Optical coherence tomography angiography vessel density in the superficial capillary plexus, intermediate capillary plexus, and deep capillary plexus and choriocapillaris flow density. The severity of DR and the predominantly peripheral lesions (PPL) were evaluated from ultra-widefield color imaging. The study evaluated 352 eyes (225 patients; 125 men [55.6%]; mean [SD] age, 52.1 [15.1] years), of which 183 eyes (52.0%) had mild nonproliferative diabetic retinopathy (NPDR), 71 eyes (20.2%) had moderate NPDR, and 98 eyes (27.8%) had severe NPDR or proliferative diabetic retinopathy (PDR). In eyes with no PPL (209 [59.4%]), the mean (SD) vessel density in the superficial capillary plexus (mild NPDR, 38.1% [4.7%]; moderate NPDR, 36.4% [4.6%]; severe NPDR or PDR, 34.1% [4.1%]; P < .001) and the deep capillary plexus (mild NPDR, 45.8% [3.0%]; moderate NPDR, 45.8% [2.2%]; severe NPDR or PDR, 44.5% [1.9%]; P = .002), as well as the mean (SD) choriocapillaris flow density (mild NPDR, 69.7% [6.2%]; moderate NPDR, 67.6% [5.6%]; severe NPDR or PDR, 67.1% [5.6%]; P = .01), decreased with increasing DR severity. These associations remained statistically significant even after correcting for age, signal strength index, spherical equivalent, duration of diabetes, type of diabetes, and correlation between eyes of the same patient. In eyes with PPL (143 [40.6%]), mean (SD) vessel density in the superficial capillary plexus (mild NPDR, 34.1% [4.1%]; moderate NPDR, 35.2% [4.1%]; severe NPDR or PDR, 36.0% [4.3%]; P = .42) and the deep capillary plexus (mild NPDR, 44.5% [1.7%]; moderate NPDR, 45.4% [1.4%]; severe NPDR or PDR, 44.9% [1.5%]; P = .81), as well as the mean (SD) choriocapillaris flow density (mild NPDR, 67.1% [5.6%]; moderate NPDR, 69.3% [4.6%]; severe NPDR or PDR, 68.3% [5.6%]; P = .49), did not appear to change with increasing DR severity. These results suggest that central retinal vessel density is associated with DR severity in eyes without, but not with, PPL. These findings suggest a potential need to stratify future optical coherence tomography angiography studies of eyes with DR by the presence or absence of PPL. If DR onset and worsening are associated with the location of retinal nonperfusion, assessment of global retinal nonperfusion using widefield angiography may improve the ability to evaluate DR severity and risk of DR worsening over time.

Association of glucose metabolism and retinopathy signs in non-diabetic individuals in midlife-The Northern Finland Birth Cohort 1966 study.

Diabetic retinopathy is a microvascular complication of hyperglycaemia. Little is known about the association of glucose metabolism and retinopathy signs in the non-diabetic middle-aged population. We studied prevalence of retinopathy in a subsample of Northern Finland Birth Cohort study (NFBC1966) of 1809 subjects, at 47 years of age, without previously diagnosed type 2 diabetes and/or blood pressure-lowering medication. All participants underwent clinical evaluations including an oral glucose tolerance test (glucose and insulin values measured at 0, 30, 60 and 120 min) and HbA1c. The retinopathy signs were diagnosed by fundus photographs and classified according to the Eurodiab classification scheme. The overall prevalence of newly diagnosed retinopathy was 1.4%. The retinopathy signs were significantly associated with increased 30 min, 1-h and 2-h glucose levels and 2-h insulin level in an OGTT. After adjustment with systolic blood pressure, only 30 min glucose, 1-h glucose and 2-h insulin levels were associated with retinopathy signs. Our findings show the potential role of 30 min and 1-h post-load glucose and 2-h insulin levels as risk factors for retinopathy lesions among the participants without previously diagnosed diabetes or hypertensive medication.

Adaptive machine learning classification for diabetic retinopathy

Diabetic retinopathy is the main cause of the blindness worldwide. However, the diabetic retinopathy is hard to be detected in the initial stages, and the procedure of diagnostic can be time-consuming even for experienced-experts. The segment based learning approach has shown the benefits over learning technique for detection of diabetic retinopathy: only the annotation of image level is required get the lesions and detection of diabetic retinopathy. Anyways, the performance of existing methods are limited by the utilization of handcrafted features. This paper proposes the segment based learning approach for detection of diabetic retinopathy, which mutually learns classifiers and features from the data and gets significant development on recognizing the images of diabetic retinopathy and their inside the lesions. Specifically, the pre-trained CNN is adapted to get the segment level DRE (Diabetic retinopathy Estimation) and then Integrating all segment level of (DRM) is utilized to make the classification of diabetic retinopathy images. Lastly, an end-to-end segment based learning approach to deal with the irregular lesions of diabetic retinopathy. For detection of the diabetic retinopathy images obtain area under of ROC curve is 0.963 on the Kaggle dataset and also obtains sensitivity and specificity 96.37% and 96.37% on the higher specificity and sensitivity that outperforms much better than existing model.

Efficacy of pharmacotherapy follow-up care in Brazilian patients with type 2 diabetes mellitus: a randomized controlled trial

Objective: To evaluate the efficacy of pharmaceutical care in improving outcomes of Brazilian outpatients with type 2 diabetes mellitus. Methods: In this single-blind, controlled trial, 71 outpatients were randomized into two groups: pharmaceutical care intervention (managed using pharmacotherapy follow-up protocol); and control (managed using standard dispensing procedures). Outcomes included hospitalization, severe complication (retinopathy, renal insufficiency, hypoglycemia, coronaropathy or foot lesion), and the values of A1c hemoglobin (HbA1c), capillary glycaemia (CG), blood pressure (BP), total cholesterol (TC) and body mass index (BMI). All patients were followed for 12 months and drug-related problems (DRP) were described in intervention group. The groups were compared using the Student´s t-test, Tukey-Kramer, Chi-square and Fisher exact tests. Results: No significant difference in baseline clinical characteristics of the intervention (n= 36) and control groups (n= 35) (p&gt;0.05). The groups did not differ for the outcome hypoglycemia, CG, BP, HbA1c, TC and BMI (p&gt;0.05), but CG and HbA1c levels decreased at 3, 6 and 12 months, in both groups (p≤0.05). A total of 56 DRP were observed in intervention group and the pharmacist resolved approximately 60% of these. Conclusion: Improvements in the glycemic parameters of outpatients with type 2 diabetes mellitus attended within a community pharmacy were observed. Studies involving larger samples are needed to confirm the benefits of pharmacotherapy follow-up care for key clinical outcomes in these patients. The trial was registered in Clinicaltrials.gov: Record NCT03196336.

Quantitative Assessment of the Severity of Diabetic Retinopathy

To determine whether a quantitative approach to assessment of the severity of diabetic retinopathy (DR) lesions on ultrawide field (UWF) images can provide new parameters to predict progression to proliferative diabetic retinopathy (PDR). One hundred forty six eyes from 73 participants with DR and 4 years of follow-up data were included in this post hoc analysis, which was based on a cohort of 100 diabetic patients enrolled in a previously published prospective, comparative study of UWF imaging at the Joslin Diabetes Center. Diabetic Retinopathy Severity Score level was determined at baseline and 4-year follow-up visits using mydriatic 7-standard field Early Treatment Diabetic Retinopathy Study (ETDRS) photographs. All individual DR lesions (hemorrhage [H], microaneurysm [ma], cotton wool spot [CWS], intraretinal microvascular abnormality [IRMA]) were manually segmented on stereographic projected UWF. For each lesion type, the frequency/number, surface area, and distances from the optic nerve head (ONH) were computed. These quantitative parameters were compared between eyes that progressed to PDR in 4 years and eyes that did not progress. Univariable and multivariable logistic regression analyses were performed to identify parameters that were associated with an increased risk for progression to PDR. A total of 146 eyes of 73 subjects were included in the final analysis. The mean age of the study cohort was 53.1 years, and 42 (56.8%) subjects were female. The number and surface area of H/ma's and CWSs were significantly (P ≤ .05) higher in eyes that progressed to PDR compared with eyes that did not progress by 4 years. Similarly, H/ma's and CWSs were located further away from the ONH (ie, more peripheral) in eyes that progressed (P < .05). DR lesion parameters that conferred a statistically significant increased risk for proliferative diabetic retinopathy in the multivariate model included hemorrhage area (odds ratio [OR], 2.63; 95% confidence interval [CI], 1.25-5.53), and greater distance of hemorrhages from the ONH (OR, 1.24; 95% CI, 0.97-1.59). Quantitative analysis of DR lesions on UWF images identifies new risk parameters for progression to PDR including the surface area of hemorrhages and the distance of hemorrhages from the ONH. Although these risk factors will need to be confirmed in larger, prospective studies, they highlight the potential for quantitative lesion analysis to inform the design of a more precise and complete staging system for diabetic retinopathy severity in the future. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.