Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 5.346
Filtrar
1.
Lancet Digit Health ; 3(1): e10-e19, 2021 01.
Artigo em Inglês | MEDLINE | ID: mdl-33735063

RESUMO

BACKGROUND: Diabetic retinopathy screening is instrumental to preventing blindness, but scaling up screening is challenging because of the increasing number of patients with all forms of diabetes. We aimed to create a deep-learning system to predict the risk of patients with diabetes developing diabetic retinopathy within 2 years. METHODS: We created and validated two versions of a deep-learning system to predict the development of diabetic retinopathy in patients with diabetes who had had teleretinal diabetic retinopathy screening in a primary care setting. The input for the two versions was either a set of three-field or one-field colour fundus photographs. Of the 575 431 eyes in the development set 28 899 had known outcomes, with the remaining 546 532 eyes used to augment the training process via multitask learning. Validation was done on one eye (selected at random) per patient from two datasets: an internal validation (from EyePACS, a teleretinal screening service in the USA) set of 3678 eyes with known outcomes and an external validation (from Thailand) set of 2345 eyes with known outcomes. FINDINGS: The three-field deep-learning system had an area under the receiver operating characteristic curve (AUC) of 0·79 (95% CI 0·77-0·81) in the internal validation set. Assessment of the external validation set-which contained only one-field colour fundus photographs-with the one-field deep-learning system gave an AUC of 0·70 (0·67-0·74). In the internal validation set, the AUC of available risk factors was 0·72 (0·68-0·76), which improved to 0·81 (0·77-0·84) after combining the deep-learning system with these risk factors (p<0·0001). In the external validation set, the corresponding AUC improved from 0·62 (0·58-0·66) to 0·71 (0·68-0·75; p<0·0001) following the addition of the deep-learning system to available risk factors. INTERPRETATION: The deep-learning systems predicted diabetic retinopathy development using colour fundus photographs, and the systems were independent of and more informative than available risk factors. Such a risk stratification tool might help to optimise screening intervals to reduce costs while improving vision-related outcomes. FUNDING: Google.


Assuntos
Aprendizado Profundo , Retinopatia Diabética/diagnóstico , Idoso , Área Sob a Curva , Técnicas de Diagnóstico Oftalmológico , Feminino , Humanos , Estimativa de Kaplan-Meier , Masculino , Pessoa de Meia-Idade , Fotografação , Prognóstico , Curva ROC , Reprodutibilidade dos Testes , Medição de Risco/métodos
4.
Vestn Oftalmol ; 137(1): 123-129, 2021.
Artigo em Russo | MEDLINE | ID: mdl-33610160

RESUMO

Diabetic retinopathy (DR) and age-related macular degeneration (AMD) comprise a significant socio-medical problem for Russia. The article presents an analysis aimed at identifying the prerequisites for further research on the socio-economic consequences of retinal pathology. Studying the epidemiological aspects of DR and AMD, as well as the conditions for receiving medical aid helped define the main approaches to assessing the economic burden of retinal diseases in Russia. It also revealed the problems associated with completeness of registration and accounting of patients, the disparity between the volume of medical aid required and funding, and between the required and provided assistance for patients with these pathologies in clinical practice. Analysis of the disease cost will allow not only to determine the socio-economic consequences of retinal diseases, but also to find further directions for improving the quality of medical care for patients with DR and AMD in order to reduce its economic cost for the state and society. Evidently, there is a need for comprehensive assessment of the total burden of retinal diseases in Russia that would serve as a basis for subsequent assessment of the economic effectiveness of prevention and treatment measures.


Assuntos
Diabetes Mellitus , Retinopatia Diabética , Degeneração Macular , Efeitos Psicossociais da Doença , Retinopatia Diabética/diagnóstico , Retinopatia Diabética/epidemiologia , Retinopatia Diabética/terapia , Humanos , Degeneração Macular/diagnóstico , Degeneração Macular/epidemiologia , Degeneração Macular/terapia , Federação Russa/epidemiologia , Fatores Socioeconômicos
5.
Arq Bras Oftalmol ; 84(1): 37-44, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33470340

RESUMO

PURPOSE: We aimed to evaluate the use of automated quantitative static and dynamic pupillometry in screening patients with type 2 diabetes mellitus and different stages of diabetic retinopathy. METHOD: 155 patients with type 2 diabetes mellitus (diabetes mellitus group) were included in this study and another 145 age- and sex-matched healthy individuals to serve as the control group. The diabetes mellitus group was divided into three subgroups: diabetes mellitus without diabetic retinopathy (No-diabetic retinopathy), nonproliferative diabetic retinopathy, and proliferative diabetic retinopathy. Static and dynamic pupillometry were performed using a rotating Scheimpflug camera with a topography-based system. RESULTS: In terms of pupil diameter in both static and dynamic pupillometry (p<0.05), statistically significant differences were observed between the diabetes mellitus and control groups and also between the subgroups No-diabetic retinopathy, nonproliferative diabetic retinopathy, and proliferative diabetic retinopathy subgroups. But it was noted that No-diabetic retinopathy and nonproliferative diabetic retinopathy groups have showed similarities in the findings derived from static pupillometry under mesopic and photopic conditions. The two groups also appeared similar at all points during the dynamic pupillometry (p>0.05). However, it could be concluded that the proliferative diabetic retinopathy group was significantly different from the rest of the subgroups, No-diabetic retinopathy and nonproliferative diabetic retinopathy groups, in terms of all the static pupillometry measurements (p<0.05). The average speed of dilation was also significantly different between the diabetes mellitus and control groups and among the diabetes mellitus subgroups (p<0.001). While weak to moderate significant correlations were found between all pupil diameters in static and dynamic pupillometry with the duration of diabetes mellitus (p<0.05 for all), the HbA1c values showed no statistically significant correlations with any of the investigated static and dynamic pupil diameters (p>0.05 for all). CONCLUSION: This study revealed that the measurements derived from automated pupillometry are altered in patients with type 2 diabetes mellitus. The presence of nonproliferative diabetic retinopathy does not have a negative effect on pupillometry findings, but with proliferative diabetic retinopathy, significant alterations were observed. These results suggest that using automated quantitative pupillometry may be useful in verifying the severity of diabetic retinopathy.


Assuntos
Diabetes Mellitus Tipo 2 , Retinopatia Diabética , Diabetes Mellitus Tipo 2/complicações , Retinopatia Diabética/diagnóstico , Humanos
12.
Adv Exp Med Biol ; 1307: 357-373, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-32166636

RESUMO

Human eye is one of the important organs in human body, with iris, pupil, sclera, cornea, lens, retina and optic nerve. Many important eye diseases as well as systemic diseases manifest themselves in the retina. The most widespread causes of blindness in the industrialized world are glaucoma, Age Related Macular Degeneration (ARMD), Diabetic Retinopathy (DR) and Diabetic Macula Edema (DME). The development of a retinal image analysis system is a demanding research topic for early detection, progression analysis and diagnosis of eye diseases. Early diagnosis and treatment of retinal diseases are essential to prevent vision loss. The huge and growing number of retinal disease affected patients, cost of current hospital-based detection methods (by eye care specialists) and scarcity in the number of ophthalmologists are the barriers to achieve the recommended screening compliance in the patient who is at the risk of retinal diseases. Developing an automated system which uses pattern recognition, computer vision and machine learning to diagnose retinal diseases is a potential solution to this problem. Damage to the tiny blood vessels in the retina in the posterior part of the eye due to diabetes is named as DR. Diabetes is a disease which occurs when the pancreas does not secrete enough insulin or the body does not utilize it properly. This disease slowly affects the circulatory system including that of the retina. As diabetes intensifies, the vision of a patient may start deteriorating and leading to DR. The retinal landmarks like OD and blood vessels, white lesions and red lesions are segmented to develop automated screening system for DR. DME is an advanced symptom of DR that can lead to irreversible vision loss. DME is a general term defined as retinal thickening or exudates present within 2 disk diameter of the fovea center; it can either focal or diffuse DME in distribution. In this paper, review the algorithms used in diagnosis of DR and DME.


Assuntos
Diabetes Mellitus , Retinopatia Diabética , Edema Macular , Algoritmos , Retinopatia Diabética/diagnóstico , Edema , Humanos , Edema Macular/diagnóstico , Retina
13.
Int J Mol Sci ; 21(24)2020 Dec 15.
Artigo em Inglês | MEDLINE | ID: mdl-33334029

RESUMO

Transforming growth factor ß1 (TGFß1) is a proinflammatory cytokine that has been implicated in the pathogenesis of diabetic retinopathy (DR), particularly in the late phase of disease. The aim of the present study was to validate serum TGFß1 as a diagnostic and prognostic biomarker of DR stages. Thirty-eight subjects were enrolled and, after diagnosis and evaluation of inclusion and exclusion criteria, were assigned to six groups: (1) healthy age-matched control, (2) diabetic without DR, (3) non-proliferative diabetic retinopathy (NPDR) naïve to treatment, (4) NPDR treated with intravitreal (IVT) aflibercept, (5) proliferative diabetic retinopathy (PDR) naïve to treatment and (6) PDR treated with IVT aflibercept. Serum levels of vascular endothelial growth factor A (VEGF-A), placental growth factor (PlGF) and TGFß1 were measured by means of enzyme-linked immunosorbent assay (ELISA). Foveal macular thickness (FMT) in enrolled subjects was evaluated by means of structural-optical coherence tomography (S-OCT). VEGF-A serum levels decreased in NPDR and PDR patients treated with aflibercept, compared to naïve DR patients. PlGF serum levels were modulated only in aflibercept-treated NPDR patients. Particularly, TGFß1 serum levels were predictive of disease progression from NPDR to PDR. A Multivariate ANOVA analysis (M-ANOVA) was also carried out to assess the effects of fixed factors on glycated hemoglobin (HbA1c) levels, TGFß1, and diabetes duration. In conclusion, our data have strengthened the hypothesis that TGFß1 would be a biomarker and pharmacological target of diabetic retinopathy.


Assuntos
Biomarcadores/sangue , Retinopatia Diabética/sangue , Fator de Crescimento Transformador beta/sangue , Fator A de Crescimento do Endotélio Vascular/antagonistas & inibidores , Idoso , Idoso de 80 Anos ou mais , Diabetes Mellitus Tipo 2/complicações , Diabetes Mellitus Tipo 2/tratamento farmacológico , Diabetes Mellitus Tipo 2/metabolismo , Retinopatia Diabética/diagnóstico , Retinopatia Diabética/tratamento farmacológico , Feminino , Humanos , Peptídeos e Proteínas de Sinalização Intercelular/sangue , Masculino , Terapia de Alvo Molecular , Curva ROC , Tomografia de Coerência Óptica
14.
Rom J Ophthalmol ; 64(3): 285-291, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33367162

RESUMO

Purpose: To describe the central three-dimensional (3D) thickness profile of the macula (CMT) and the subfoveal choroidal region (SFCT) in diabetic retinopathy (DR) following panretinal laser photocoagulation (PRP) using swept-source optical coherence tomography (SS-OCT). Methods: A prospective observational study including 17 eyes with proliferative DR (PDR) and 27 eyes with severe nonproliferative DR (sNPDR)] for whom PRP was done. All subjects received SS-OCT imaging before and 3 months after PRP (POM#3). SFCT and CMT changes were analysed at both visits. Intraclass Correlation Coefficients (ICC) and Coefficients of Variation (COV) were used to test the accuracy of thickness data. Results: SFCT has thinned from 233 ± 54 µm before PRP treatment to 216 ± 51 µm 3 months later (p < 0.001). Likewise, CMT declined at POM#3 as compared to pre-PRP status (p<0.001). SFCT was thinner in PDR before and at POM#3 (p<0.05) than sNPDR; whereas, no significant difference was observed in CMT between both groups in the two visits. No significant changes were found between groups in SFCT and CMT at POM#3. Regarding reliability, ICCSFCT=0.98 and ICCCMT=0.99. The COVs for CMT and SFCT were 5.03% and 5.91%, respectively. Conclusion: The mean SFCT and CMT decreased 3 months after PRP. We also reported reliability of SFCT measurements in DR using SS-OCT. Abbreviations: SS = Swept-Source, TD = time domain, SD = spectral domain, FD = Fourier-domain, 3D = three-dimensional, 2D = two-dimensional.


Assuntos
Corioide/patologia , Retinopatia Diabética/diagnóstico , Fotocoagulação a Laser/métodos , Retina/patologia , Tomografia de Coerência Óptica/métodos , Retinopatia Diabética/cirurgia , Feminino , Angiofluoresceinografia/métodos , Seguimentos , Fundo de Olho , Humanos , Masculino , Pessoa de Meia-Idade , Reprodutibilidade dos Testes , Retina/cirurgia , Estudos Retrospectivos
16.
Zhonghua Yi Xue Za Zhi ; 100(48): 3835-3840, 2020 Dec 29.
Artigo em Chinês | MEDLINE | ID: mdl-33371627

RESUMO

Objective: To investigate the diagnostic accuracy and efficiency of an artificial intelligence (AI) triaging model in a diabetic retinopathy (DR) screening program. Methods: A DR screening program was conducted in Kashi City and Kizilsu Kirghiz Autonomous Prefecture of the Xinjiang Uyur Autonomous Region from May to July 2018, and 8 005 patients with diabetes mellitus were included. Fundus images, one centered at optic disc and one centered at macula, were taken for both eyes. A previously validated AI algorithm was applied as the first step to identify the patients with all 4 images. If the images were classified as gradable and negative DR, an AI-generated report was immediately provided without sending to manual grading, and 1/3 of these patients were randomly sampled for manual grading and quality control (group A). For the patients with at least one image classified as ungradable or positive for any DR, all images were sent for manual grading (group B). Finally, 300 patients were randomly selected from group A and group B respectively for accuracy assessment, where the patients and their images were classified by a specialist panel for referral DR (pre-proliferative DR, or proliferative DR, and/or diabetic macular edema). Results: Among 8 005 patients for DR screening [including 3 220 males and 4 785 females, aged (58.3±10.6) years], after AI triaging, 5 267 (65.8%) potentially received reports from AI system and 2 738 (34.2%) required manual grading. In group A, the accuracy and specificity of AI classification and manual grading on referral DR were all 100%. In group B, the accuracy of AI and manual grading were 75.8% and 90.3%, respectively, while the sensitivity of AI and manual grading was 100% and 79.1%, respectively. Conclusion: AI alleviates 60% of the workload of manual grading without missing any referral patients with the aid of the current AI triaging model.


Assuntos
Diabetes Mellitus , Retinopatia Diabética , Edema Macular , Idoso , Inteligência Artificial , China , Retinopatia Diabética/diagnóstico , Feminino , Humanos , Masculino , Programas de Rastreamento , Pessoa de Meia-Idade , Triagem
17.
Vestn Oftalmol ; 136(6. Vyp. 2): 171-176, 2020.
Artigo em Russo | MEDLINE | ID: mdl-33371646

RESUMO

Vitreoretinal surgery (VRS) is the «gold standard¼ for surgical treatment of patients with proliferative diabetic retinopathy (PDR). However, the timing for the removal of primary cataract in this category of patients remains uncertain. PURPOSE: To evaluate the effectiveness of multistage surgical treatment of patients with advanced PDR complicated with primary cataract. MATERIAL AND METHODS: The study involved 94 cases of surgical treatment of patients with PDR and complicated primary cataract. These patients were divided into two groups depending on the treatment tactics. In the first group, patients were subjected to a two-step surgical procedure: VRS with silicone oil tamponade performed as the first step in their treatment followed by phacoemulsification, silicone oil removal, and IOL implantation, respectively, as the second step. In subgroup 1a - VRS was performed with standard pharmacological support. In subgroup 1b - intravitreal injection of angiogenesis inhibitors preceded VRS. In the second group, the first step was phacoemulsification performed simultaneously with vitreoretinal surgery with silicone oil tamponade; the second step consisted of removing silicone oil from the vitreous cavity. Subgroup 2a - surgical treatment was performed with standard pharmacological support (similar to subgroup 1a). Subgroup 2b - intravitreal injection of anti-VEGF drugs preceded VRS. RESULTS: Visual functions improved in 88.8% and 83.4% of cases in subgroups 1a and 1b, and in 51.3% and 66.7% in subgroups 2a and 2b, respectively. CONCLUSIONS: The study confirms the effectiveness of staged (multi-step) surgical treatment of patients with advanced proliferative diabetic retinopathy and complicated primary cataract. Conducting phacoemulsification sometime later along with silicone oil removal in PDR patients with preoperative intravitreal injection of angiogenesis inhibitors is a gentler approach for the anatomic structures of the eye during the first stage (VRS) and contributes to the reduction in the number of intraoperative and postoperative complications.


Assuntos
Catarata , Diabetes Mellitus , Retinopatia Diabética , Facoemulsificação , Descolamento Retiniano , Catarata/complicações , Catarata/diagnóstico , Retinopatia Diabética/complicações , Retinopatia Diabética/diagnóstico , Retinopatia Diabética/cirurgia , Humanos , Facoemulsificação/efeitos adversos , Complicações Pós-Operatórias/etiologia , Descolamento Retiniano/complicações , Descolamento Retiniano/diagnóstico , Óleos de Silicone , Vitrectomia
18.
Vestn Oftalmol ; 136(6. Vyp. 2): 185-194, 2020.
Artigo em Russo | MEDLINE | ID: mdl-33371648

RESUMO

Despite the high clinical effectiveness and widespread introduction of anti-angiogenesis (anti-VEGF) therapy into practice, its long-term effect on the development of structural changes in the treatment of primary open-angle glaucoma (POAG) patients with diabetic macular edema (DME) hasn't been studied sufficiently and so presents certain interest. PURPOSE: To study the effect of anti-VEGF therapy on the structural and functional state of the retina and optic nerve in patients with DME and POAG. MATERIAL AND METHODS: The study included 72 patients (132 eyes): the 1st group - 22 patients (40 eyes) with stage I POAG and DME, the 2nd group - 25 patients (46 eyes) with DME receiving anti-VEGF therapy. The 3rd group (control) consisted of 25 patients (46 eyes) with stage I POAG. The observation period lasted 24 months. The average number of injections was 8.48±3.65. The indicators for evaluation were: visual acuity, tonometry, perimetry, optical coherence tomography (OCT) of the optic nerve and macular region. RESULTS: By the end of the observation period, the increase in IOP in the groups was +0.82 (4.4%), 0.41 (2.4%), 0.65 (3.6%) mm Hg. In the group of comorbid patients, a small-scale increase trend of BCVA was noted: +0.05 (6.6%), a decrease in MD by -2.48 Db (92.1%), an increase in excavation volume by 0.16 (43.2%) mm3, decrease in the area of RA by 0.3 mm2 (12.7%). A decrease in retinal nerve fibers layer (RNFL) thickness of 6.55 µm (7.8%), mainly the superior (9.2%), inferior (7.3%) and nasal sectors (7.9%). Loss of GCL+IPL 8.68 µm (12.7%) in the superior (19%), superonasal (20.2%) and inferonasal (20.7%) sectors. CONCLUSION: The combined course of POAG and DME is accompanied by a decrease in the functional and structural parameters of the retina and optic nerve, and a higher rate of progression of glaucomatous optic neuropathy. Long-term results did not reveal a significant deterioration in the structural parameters of the optic disc and retina against the background of anti-VEGF therapy when comparing the study groups.


Assuntos
Diabetes Mellitus , Retinopatia Diabética , Glaucoma de Ângulo Aberto , Edema Macular , Disco Óptico , Retinopatia Diabética/complicações , Retinopatia Diabética/diagnóstico , Retinopatia Diabética/tratamento farmacológico , Glaucoma de Ângulo Aberto/complicações , Glaucoma de Ângulo Aberto/diagnóstico , Glaucoma de Ângulo Aberto/tratamento farmacológico , Humanos , Pressão Intraocular , Edema Macular/diagnóstico , Edema Macular/tratamento farmacológico , Edema Macular/etiologia , Fibras Nervosas , Tomografia de Coerência Óptica
19.
Lancet Digit Health ; 2(5): e240-e249, 2020 05.
Artigo em Inglês | MEDLINE | ID: mdl-33328056

RESUMO

BACKGROUND: Deep learning is a novel machine learning technique that has been shown to be as effective as human graders in detecting diabetic retinopathy from fundus photographs. We used a cost-minimisation analysis to evaluate the potential savings of two deep learning approaches as compared with the current human assessment: a semi-automated deep learning model as a triage filter before secondary human assessment; and a fully automated deep learning model without human assessment. METHODS: In this economic analysis modelling study, using 39 006 consecutive patients with diabetes in a national diabetic retinopathy screening programme in Singapore in 2015, we used a decision tree model and TreeAge Pro to compare the actual cost of screening this cohort with human graders against the simulated cost for semi-automated and fully automated screening models. Model parameters included diabetic retinopathy prevalence rates, diabetic retinopathy screening costs under each screening model, cost of medical consultation, and diagnostic performance (ie, sensitivity and specificity). The primary outcome was total cost for each screening model. Deterministic sensitivity analyses were done to gauge the sensitivity of the results to key model assumptions. FINDINGS: From the health system perspective, the semi-automated screening model was the least expensive of the three models, at US$62 per patient per year. The fully automated model was $66 per patient per year, and the human assessment model was $77 per patient per year. The savings to the Singapore health system associated with switching to the semi-automated model are estimated to be $489 000, which is roughly 20% of the current annual screening cost. By 2050, Singapore is projected to have 1 million people with diabetes; at this time, the estimated annual savings would be $15 million. INTERPRETATION: This study provides a strong economic rationale for using deep learning systems as an assistive tool to screen for diabetic retinopathy. FUNDING: Ministry of Health, Singapore.


Assuntos
Inteligência Artificial , Análise Custo-Benefício , Retinopatia Diabética/diagnóstico , Técnicas de Diagnóstico Oftalmológico/economia , Processamento de Imagem Assistida por Computador/economia , Modelos Biológicos , Telemedicina/economia , Adulto , Idoso , Árvores de Decisões , Diabetes Mellitus , Retinopatia Diabética/economia , Custos de Cuidados de Saúde , Humanos , Aprendizado de Máquina , Programas de Rastreamento/economia , Pessoa de Meia-Idade , Oftalmologia/economia , Fotografação , Exame Físico , Retina/patologia , Sensibilidade e Especificidade , Singapura , Telemedicina/métodos
20.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1404-1407, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018252

RESUMO

Diabetic retinopathy (DR) is a progressive eye disease that affects a large portion of working-age adults. DR, which may progress to an irreversible state that causes blindness, can be diagnosed with a comprehensive dilated eye exam. With the eye dilated, the Doctor takes pictures of the inside of the eye via a medical procedure called Fluorescein Angiography, in which a dye is injected into the bloodstream. The dye highlights the blood vessels in the back of the eye so they can be photographed. In addition, the Doctor may request an Optical Coherence Tomography (OCT) exam, by which cross-sectional photos of the retina are produced to measure the thickness of the retina. Early prognostication is vital in treating the disease and preventing it from progressing into advanced irreversible stages. Skilled medical personnel and necessary medical facilities are required to detect DR in its five major stages. In this paper, we propose a diagnostic tool to detect Diabetic retinopathy from fundus images by using an ensemble of multi-inception CNN networks. Our inception block consists of three Convolutional layers with kernel sizes of 3x3, 5x5, and 1x1 that are concatenated deeply and forwarded to the max-pooling layer. We experimentally compare our proposed method with two pre-trained models: VGG16 and GoogleNets. The experiment results show that the proposed method can achieve an accuracy of 93.2% by an ensemble of 10 random networks, compared to 81% obtained with transfer learning based on VGG19.


Assuntos
Diabetes Mellitus , Retinopatia Diabética , Estudos Transversais , Retinopatia Diabética/diagnóstico , Fundo de Olho , Humanos , Redes Neurais de Computação , Tomografia de Coerência Óptica
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...