-
Seminars in Ophthalmology Nov 2020: Over the next 25 years, the global prevalence of diabetes is expected to grow to affect 700 million individuals. Consequently, an unprecedented number of patients will... (Review)
Review
: Over the next 25 years, the global prevalence of diabetes is expected to grow to affect 700 million individuals. Consequently, an unprecedented number of patients will be at risk for vision loss from diabetic eye disease. This demand will almost certainly exceed the supply of eye care professionals to individually evaluate each patient on an annual basis, signaling the need for 21st century tools to assist our profession in meeting this challenge. Methods: Review of available literature on artificial intelligence (AI) as applied to diabetic retinopathy (DR) detection and prediction: The field of AI has seen exponential growth in evaluating fundus photographs for DR. AI systems employ machine learning and artificial neural networks to teach themselves how to grade DR from libraries of tens of thousands of images and may be able to predict future DR progression based on baseline fundus photographs. : AI algorithms are highly promising for the purposes of DR detection and will likely be able to reliably predict DR worsening in the future. A deeper understanding of these systems and how they interpret images is critical as they transition from the bench into the clinic.
Topics: Algorithms; Artificial Intelligence; Diabetic Retinopathy; Humans; Machine Learning; Mass Screening; Neural Networks, Computer; Photography
PubMed: 33539253
DOI: 10.1080/08820538.2020.1855358 -
Seminars in Neurology Oct 2015Although cerebral small vessel disease has been linked to stroke and dementia, due to limitations of current neuroimaging technology, direct in vivo visualization of... (Review)
Review
Although cerebral small vessel disease has been linked to stroke and dementia, due to limitations of current neuroimaging technology, direct in vivo visualization of changes in the cerebral small vessels (e.g., cerebral arteriolar narrowing, tortuous microvessels, blood-brain barrier damage, capillary microaneurysms) is difficult to achieve. As the retina and the brain share similar embryological origin, anatomical features, and physiologic properties with the cerebral small vessels, the retinal vessels offer a unique and easily accessible "window" to study the correlates and consequences of cerebral small vessel diseases in vivo. The retinal microvasculature can be visualized, quantified and monitored noninvasively using ocular fundus photography. Recent clinic- and population-based studies have demonstrated a close link between retinal vascular changes seen on fundus photography and stroke and dementia, suggesting that ocular fundus photography may provide insights to the contribution of microvascular disease to stroke and dementia. In this review, we summarize current knowledge on retinal vascular changes, such as retinopathy and changes in retinal vascular measures with stroke and dementia as well as subclinical makers of cerebral small vessel disease, and discuss the possible clinical implications of these findings in neurology. Studying pathologic changes of retinal blood vessels may be useful for understanding the etiology of various cerebrovascular conditions; hence, ocular fundus photography can be potentially translated into clinical practice.
Topics: Cerebral Small Vessel Diseases; Dementia; Fundus Oculi; Humans; Photography; Retinal Vessels; Stroke
PubMed: 26444393
DOI: 10.1055/s-0035-1563570 -
Translational Vision Science &... Jun 2021The purpose of this study was to determine factors affecting predominantly peripheral lesion (PPL) grading, such as qualitative versus quantitative assessment, device...
PURPOSE
The purpose of this study was to determine factors affecting predominantly peripheral lesion (PPL) grading, such as qualitative versus quantitative assessment, device type, and severity of diabetic retinopathy (DR) in ultrawide field color images (UWF-CIs).
METHODS
Patients with DR had UWF-CI qualitatively graded for PPL using standardized techniques and had hemorrhages/microaneurysms (H/Mas) individually annotated for quantitative PPL grading on two different ultrawide field devices.
RESULTS
Among 791 eyes of 481 patients, 38.2% had mild nonproliferative DR (NPDR), 34.7% had moderate NPDR, and 27.1% had severe NPDR to proliferative DR (PDR). The overall agreement between qualitative and quantitative PPL grading was moderate (ĸ = 0.423, P < 0.001). Agreement rates were fair in eyes with mild NPDR (ĸ = 0.336, P < 0.001) but moderate in eyes with moderate NPDR (ĸ = 0.525, P < 0.001) and severe NPDR-PDR (ĸ = 0.409, P < 0.001). Increasing thresholds for quantitative PPL determination improved agreement rates, with peak agreements at H/Ma count differences of six for mild NPDR, five for moderate NPDR, and nine for severe NPDR-PDR. Based on ultrawide field device type (California = 412 eyes vs. 200Tx = 379 eyes), agreement between qualitative and quantitative PPL grading was moderate for all DR severities in both devices (ĸ = 0.369-0.526, P < 0.001) except for mild NPDR on the 200Tx, which had poor agreement (ĸ = 0.055, P = 0.478).
CONCLUSIONS
Determination of PPL varies between standard qualitative and quantitative grading and is dependent on NPDR severity, device type, and magnitude of lesion differences used for quantitative assessment.
TRANSLATIONAL RELEVANCE
Prior UWF studies have not accounted for imaging and grading factors that affect PPL, such factors need to be reviewed when assessing thresholds for DR progression rates.
Topics: Diabetic Retinopathy; Eye; Humans; Microaneurysm; Severity of Illness Index
PubMed: 34100926
DOI: 10.1167/tvst.10.7.6 -
Artificial Intelligence in Medicine Mar 2020In this paper, we propose a novel method for the detection of small lesions in digital medical images. Our approach is based on a multi-context ensemble of convolutional...
In this paper, we propose a novel method for the detection of small lesions in digital medical images. Our approach is based on a multi-context ensemble of convolutional neural networks (CNNs), aiming at learning different levels of image spatial context and improving detection performance. The main innovation behind the proposed method is the use of multiple-depth CNNs, individually trained on image patches of different dimensions and then combined together. In this way, the final ensemble is able to find and locate abnormalities on the images by exploiting both the local features and the surrounding context of a lesion. Experiments were focused on two well-known medical detection problems that have been recently faced with CNNs: microcalcification detection on full-field digital mammograms and microaneurysm detection on ocular fundus images. To this end, we used two publicly available datasets, INbreast and E-ophtha. Statistically significantly better detection performance were obtained by the proposed ensemble with respect to other approaches in the literature, demonstrating its effectiveness in the detection of small abnormalities.
Topics: Breast Neoplasms; Deep Learning; Fundus Oculi; Humans; Image Processing, Computer-Assisted; Mammography; Neural Networks, Computer
PubMed: 32143786
DOI: 10.1016/j.artmed.2019.101749 -
The Cochrane Database of Systematic... Dec 2018Diabetic retinopathy is one of the major causes of blindness and the number of cases has risen in recent years. Herbal medicine has been used to treat diabetes and its... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Diabetic retinopathy is one of the major causes of blindness and the number of cases has risen in recent years. Herbal medicine has been used to treat diabetes and its complications including diabetic retinopathy for thousands of years around the world. However, common practice is not always evidence-based. Evidence is needed to help people with diabetic retinopathy or doctors to make judicious judgements about using herbal medicine as treatment.
OBJECTIVES
To evaluate the effectiveness and harm of single herbal medicine for diabetic retinopathy.
SEARCH METHODS
We searched CENTRAL, which contains the Cochrane Eyes and Vision Trials Register, MEDLINE, Embase, OpenGrey, the ISRCTN registry, ClinicalTrials.gov and the ICTRP. The date of the search was 12 June 2018. We also searched the following Chinese databases in June 2013: Chinese BioMedical Literature Database (CBM), Traditional Chinese Medical Literature Analysis and Retrieval System (TCMLARS), Wanfang China Dissertation Database (CDDB), Wanfang China Conference Paper Database (CCPD) and the Index to Chinese Periodical Literature.
SELECTION CRITERIA
We included randomised controlled trials (RCTs) and quasi-RCTs that investigated the effects of any single herb (or extracts from a single herb) as a treatment for people with diabetic retinopathy. We considered the following comparators: placebo, no treatment, non-herbal (conventional) medicine or surgical treatment.
DATA COLLECTION AND ANALYSIS
Two review authors independently extracted data and assessed the risk of bias in the studies. Our prespecified outcomes were: progression of diabetic retinopathy, visual acuity, microaneurysms and haemorrhages in the retina, blood glycated haemoglobin A1c (HbA1c) (%) and adverse effects. We performed meta-analyses using risk ratios (RR) for dichotomous outcomes and mean differences (MD) for continuous outcomes, with 95% confidence intervals (CI). We assessed the certainty of the evidence using GRADE.
MAIN RESULTS
We included 10 studies involving 754 participants, of which nine were conducted in China and one in Poland. In all studies, participants in both groups received conventional treatment for diabetic retinopathy which included maintaining blood glucose and lipids using medicines and keeping a stable diabetic diet. In three studies, the comparator group also received an additional potentially active comparator in the form of a vasoprotective drug. The single herbs or extracts included Ruscus extract tablet, Sanqi Tongshu capsule, tetramethylpyrazine injection, Xueshuantong injection, Puerarin injection and Xuesaitong injection. The Sanqi Tongshu capsule, Xueshuantong injection and Xuesaitong injection were all made from the extract of Radix Notoginseng (San qi) and the main ingredient was sanchinoside. The risk of bias was high in all included studies mainly due to lack of masking (blinding). None of the studies reported the primary outcome of this review, progression of retinopathy.Combined analysis of herbal interventions suggested that people who took these herbs in combination with conventional treatment may have been more likely to gain 2 or more lines of visual acuity compared to people who did not take these herbs when compared to conventional intervention alone at the end of treatment (RR 1.26, 95% CI 1.08 to 1.48; 5 trials, 541 participants; low-certainty evidence). Subgroup analyses based on the different single herbs found no evidence for different effects of different herbs, but the power of this analysis was low. One study reported Sanqi Tongshu capsule might be associated with a greater reduction in microaneurysms and haemorrhages in the retina (very low-certainty evidence). The pooled analysis of two studies on tetramethylpyrazine or Xueshuantong injection showed such herbs may have had little effect on lowering HbA1c (MD 0.00, 95% CI -0.58 to 0.58; 215 participants; low-certainty evidence).There was very low-certainty evidence on adverse events. Two studies reported minor adverse events such as uncomfortable stomach, urticaria, dizziness and headache. There was no report of observation on adverse events in the other studies.
AUTHORS' CONCLUSIONS
No conclusions could be drawn about the effect of any single herb or herbal extract on diabetic retinopathy from the current available evidence. It was difficult to exclude the placebo effect as a possible explanation for observed differences due to the lack of placebo control in the included studies. Further adequately designed trials are needed to establish the evidence.
Topics: China; Diabetic Retinopathy; Drugs, Chinese Herbal; Ginsenosides; Humans; Isoflavones; Microaneurysm; Phytotherapy; Plants, Medicinal; Pyrazines; Randomized Controlled Trials as Topic; Retinal Hemorrhage; Ruscus; Saponins; Vasodilator Agents; Visual Acuity
PubMed: 30566763
DOI: 10.1002/14651858.CD007939.pub2 -
American Journal of Ophthalmology Case... Jun 2020A 63-year-old healthy woman was referred for a retinal examination. Dilated fundus examination of the left eye revealed small retinal hemorrhage with surrounding...
A 63-year-old healthy woman was referred for a retinal examination. Dilated fundus examination of the left eye revealed small retinal hemorrhage with surrounding exudation, most consistent with a large retinal microaneurysm, which was confirmed by fluorescein angiography and optical coherence tomography angiography (OCT-A). OCT-A has the potential to clearly delineate the anatomy of retinal aneurysms and could be used for diagnosis and surveillance, possibly replacing the current gold-standard fluorescein angiography.
PubMed: 32373757
DOI: 10.1016/j.ajoc.2020.100690 -
Sensors (Basel, Switzerland) Apr 2022Fundus is the only structure that can be observed without trauma to the human body. By analyzing color fundus images, the diagnosis basis for various diseases can be...
Fundus is the only structure that can be observed without trauma to the human body. By analyzing color fundus images, the diagnosis basis for various diseases can be obtained. Recently, fundus image segmentation has witnessed vast progress with the development of deep learning. However, the improvement of segmentation accuracy comes with the complexity of deep models. As a result, these models show low inference speeds and high memory usages when deploying to mobile edges. To promote the deployment of deep fundus segmentation models to mobile devices, we aim to design a lightweight fundus segmentation network. Our observation comes from the fact that high-resolution representations could boost the segmentation of tiny fundus structures, and the classification of small fundus structures depends more on local features. To this end, we propose a lightweight segmentation model called LightEyes. We first design a high-resolution backbone network to learn high-resolution representations, so that the spatial relationship between feature maps can be always retained. Meanwhile, considering high-resolution features means high memory usage; for each layer, we use at most 16 convolutional filters to reduce memory usage and decrease training difficulty. LightEyes has been verified on three kinds of fundus segmentation tasks, including the hard exudate, the microaneurysm, and the vessel, on five publicly available datasets. Experimental results show that LightEyes achieves highly competitive segmentation accuracy and segmentation speed compared with state-of-the-art fundus segmentation models, while running at 1.6 images/s Cambricon-1A speed and 51.3 images/s GPU speed with only 36k parameters.
Topics: Humans; Exudates and Transudates; Fundus Oculi; Image Processing, Computer-Assisted; Neural Networks, Computer; Retinal Vessels
PubMed: 35590802
DOI: 10.3390/s22093112 -
Computer Methods and Programs in... Feb 2017Diabetic retinopathy (DR) is a major cause of visual impairment, and the analysis of retinal image can assist patients to take action earlier when it is more likely to...
Diabetic retinopathy (DR) is a major cause of visual impairment, and the analysis of retinal image can assist patients to take action earlier when it is more likely to be effective. The accurate segmentation of blood vessels in the retinal image can diagnose DR directly. In this paper, a novel scheme for blood vessel segmentation based on discriminative dictionary learning (DDL) and sparse representation has been proposed. The proposed system yields a strong representation which contains the semantic concept of the image. To extract blood vessel, two separate dictionaries, for vessel and non-vessel, capable of providing reconstructive and discriminative information of the retinal image are learned. In the test step, an unseen retinal image is divided into overlapping patches and classified to vessel and non-vessel patches. Then, a voting scheme is applied to generate the binary vessel map. The proposed vessel segmentation method can achieve the accuracy of 95% and a sensitivity of 75% in the same range of specificity 97% on two public datasets. The results show that the proposed method can achieve comparable results to existing methods and decrease false positive vessels in abnormal retinal images with pathological regions. Microaneurysm (MA) is the earliest sign of DR that appears as a small red dot on the surface of the retina. Despite several attempts to develop automated MA detection systems, it is still a challenging problem. In this paper, a method for MA detection, which is similar to our vessel segmentation approach, is proposed. In our method, a candidate detection algorithm based on the Morlet wavelet is applied to identify all possible MA candidates. In the next step, two discriminative dictionaries with the ability to distinguish MA from non-MA object are learned. These dictionaries are then used to classify the detected candidate objects. The evaluations indicate that the proposed MA detection method achieves higher average sensitivity about 2-15%, compared to existing methods.
Topics: Algorithms; Blood Vessels; Humans; Microaneurysm
PubMed: 28187898
DOI: 10.1016/j.cmpb.2016.10.015 -
Evidence-based Complementary and... 2017We assess the clinical effect of compound Danshen dripping pill (CDDP) for treating diabetic retinopathy (DR). (Review)
Review
OBJECTIVE
We assess the clinical effect of compound Danshen dripping pill (CDDP) for treating diabetic retinopathy (DR).
METHODS
Electronic databases were searched from January 2001 to October 2016 to locate randomized controlled trials (RCTs). Efficacy was measured as main outcome and microaneurysms, hemorrhage, exudate, vision, and fundus fluorescein angiography (FFA) were measured as second outcomes. Methodological quality for each study was evaluated, RevMan 5 software was used to assess treatment effects, and GRADE was used to rate quality of evidence.
RESULTS
We located 13 RCTs and methodological quality was evaluated as high risk. Statistics indicated CDDP for treating DR was better than controls and DR risk was reduced 64% with CDDP (RR: 0.36, = 0.68); retinal microaneurysms (MD = -4.32NO, < 0.00001); retinal hemorrhages (MD = -0.70PD, = 0.03); exudate improvements (MD = -0.09PD, = 0.79); visual changes (MD = -0.12 letter, = 0.006); FFA (RR: 0.40, = 0.003). About GRADE, quality of evidence was "low." . CDDP may be safe and efficacious for treating or delaying DR and may improve vision or delay vision loss.
PubMed: 29081817
DOI: 10.1155/2017/4848076 -
PLoS Computational Biology Jan 2022Microaneurysms (MAs) are one of the earliest clinically visible signs of diabetic retinopathy (DR). MA leakage or rupture may precipitate local pathology in the...
Microaneurysms (MAs) are one of the earliest clinically visible signs of diabetic retinopathy (DR). MA leakage or rupture may precipitate local pathology in the surrounding neural retina that impacts visual function. Thrombosis in MAs may affect their turnover time, an indicator associated with visual and anatomic outcomes in the diabetic eyes. In this work, we perform computational modeling of blood flow in microchannels containing various MAs to investigate the pathologies of MAs in DR. The particle-based model employed in this study can explicitly represent red blood cells (RBCs) and platelets as well as their interaction in the blood flow, a process that is very difficult to observe in vivo. Our simulations illustrate that while the main blood flow from the parent vessels can perfuse the entire lumen of MAs with small body-to-neck ratio (BNR), it can only perfuse part of the lumen in MAs with large BNR, particularly at a low hematocrit level, leading to possible hypoxic conditions inside MAs. We also quantify the impacts of the size of MAs, blood flow velocity, hematocrit and RBC stiffness and adhesion on the likelihood of platelets entering MAs as well as their residence time inside, two factors that are thought to be associated with thrombus formation in MAs. Our results show that enlarged MA size, increased blood velocity and hematocrit in the parent vessel of MAs as well as the RBC-RBC adhesion promote the migration of platelets into MAs and also prolong their residence time, thereby increasing the propensity of thrombosis within MAs. Overall, our work suggests that computational simulations using particle-based models can help to understand the microvascular pathology pertaining to MAs in DR and provide insights to stimulate and steer new experimental and computational studies in this area.
Topics: Blood Flow Velocity; Computer Simulation; Diabetic Retinopathy; Erythrocytes; Hematocrit; Humans; Microaneurysm; Retinal Vessels; Thrombosis
PubMed: 34986147
DOI: 10.1371/journal.pcbi.1009728