An enhanced OCT image captioning system to assist ophthalmologists in detecting and classifying eye diseases

2020 ◽  
Vol 28 (5) ◽  
pp. 975-988
Author(s):  
Sivamurugan Vellakani ◽  
Indumathi Pushbam
Keyword(s):  
Short Term Memory ◽  
Clinical Decision ◽  
True Positive Rate ◽  
Eye Diseases ◽  
Age Related Macular Degeneration ◽  
Superior Performance ◽  
Image Captioning ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Age Related

Human eye is affected by the different eye diseases including choroidal neovascularization (CNV), diabetic macular edema (DME) and age-related macular degeneration (AMD). This work aims to design an artificial intelligence (AI) based clinical decision support system for eye disease detection and classification to assist the ophthalmologists more effectively detecting and classifying CNV, DME and drusen by using the Optical Coherence Tomography (OCT) images depicting different tissues. The methodology used for designing this system involves different deep learning convolutional neural network (CNN) models and long short-term memory networks (LSTM). The best image captioning model is selected after performance analysis by comparing nine different image captioning systems for assisting ophthalmologists to detect and classify eye diseases. The quantitative data analysis results obtained for the image captioning models designed using DenseNet201 with LSTM have superior performance in terms of overall accuracy of 0.969, positive predictive value of 0.972 and true-positive rate of 0.969using OCT images enhanced by the generative adversarial network (GAN). The corresponding performance values for the Xception with LSTM image captioning models are 0.969, 0.969 and 0.938, respectively. Thus, these two models yield superior performance and have potential to assist ophthalmologists in making optimal diagnostic decision.

Prediction of OCT images of short-term response to anti-VEGF treatment for neovascular age-related macular degeneration using generative adversarial network

2020 ◽  
Vol 104 (12) ◽  
pp. 1735-1740 ◽  
Author(s):  
Yutong Liu ◽  
Jingyuan Yang ◽  
Yang Zhou ◽  
Weisen Wang ◽  
Jianchun Zhao ◽  
...  
Keyword(s):  
Macular Degeneration ◽  
Image Synthesis ◽  
Age Related Macular Degeneration ◽  
Short Term ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Age Related ◽  
Synthetic Images ◽  
Endothelial Growth Factor ◽  
Term Response

Background/aimsThe aim of this study was to generate and evaluate individualised post-therapeutic optical coherence tomography (OCT) images that could predict the short-term response of antivascular endothelial growth factor therapy for typical neovascular age-related macular degeneration (nAMD) based on pretherapeutic images using generative adversarial network (GAN).MethodsA total of 476 pairs of pretherapeutic and post-therapeutic OCT images of patients with nAMD were included in training set, while 50 pretherapeutic OCT images were included in the tests set retrospectively, and their corresponding post-therapeutic OCT images were used to evaluate the synthetic images. The pix2pixHD method was adopted for image synthesis. Three experiments were performed to evaluate the quality, authenticity and predictive power of the synthetic images by retinal specialists.ResultsWe found that 92% of the synthetic OCT images had sufficient quality for further clinical interpretation. Only about 26%–30% synthetic post-therapeutic images could be accurately identified as synthetic images. The accuracy to predict macular status of wet or dry was 0.85 (95% CI 0.74 to 0.95).ConclusionOur results revealed a great potential of GAN to generate post-therapeutic OCT images with both good quality and high accuracy.

Application of 25-National Eye Institute Visual Function Questionnaire in ophthalmological patients

2020 ◽  
Vol 2 (3) ◽  
pp. 1-8
Author(s):  
Luciano Mesquite Simmo ◽  
Carissa Fouad Ibrahim ◽  
Senice Alvarenga Rodrigues Silva ◽  
Thai Nunes Andrade ◽  
Doora Faleiros Leite ◽  
...  
Keyword(s):  
Visual Function ◽  
Peripheral Vision ◽  
Statistical Significance ◽  
Eye Diseases ◽  
Age Related Macular Degeneration ◽  
Control Group ◽  
Ischemic Optic Neuropathy ◽  
Age Related ◽  
Visual Function Questionnaire ◽  
The Impact

Objective: To compare the vision-targeted health related quality of life (HRQOL) between neuro-ophthalmological patients and other eye diseases by the National Eye Institute 25-Item Visual Function Questionnaire. Methods: Cross sectional study with a control group and patients with the following pathologies: primary open-angle glaucoma (POAG), diabetic retinopathy (DR), age-related macular degeneration (ARMD), non-arteritic ischemic optic neuropathy (NAION), intracranial hypertension (IH), optic neuritis (ON), ptosis and cataract. Results: All comparisons of the subscales scores among the control group and the patient groups were statistically significant (p<0.05) except for “ocular pain” (p=0.160), “social functioning” (p=0.052) and “peripheral vision” (p=0.112). The control group had the best scores across all dimensions of the NEI VFQ-25. Interestingly, the ARMD and cataract groups presented the best and worst total scores of NEI VFQ-25, respectively. The lowest subscales scores were found in the cataract, in the NAION/ON, and in the POAG groups. Finally, the comparison between the NAION/ON/IH patients and the other eye diseases did not show statistical significance in any subscale. Conclusion: The NEI VFQ-25 showed the impact of various eye conditions in vision-targeted HRQOL, and no difference was measured between neuro-ophthalmological patients and other eye diseases

scholarly journals Posterior segment eye diseases in Ijebu, Southwestern Nigeria

2018 ◽  
Vol 6 (1) ◽  
pp. 8
Author(s):  
Tayo Julius Bogunjoko ◽  
Adekunle O. Hassan ◽  
Adunola Ogunro ◽  
Toyin Akanbi ◽  
Bidemi Abudu
Keyword(s):  
Diabetic Retinopathy ◽  
Posterior Segment ◽  
Eye Diseases ◽  
Age Related Macular Degeneration ◽  
Systematic Sampling ◽  
Slit Lamp ◽  
Central Visual Field ◽  
Southwestern Nigeria ◽  
Ogun State ◽  
Age Related

Background: To review cases of posterior segment eye diseases (PSEDs) seen at the Eye Foundation Centre Ijebu, Nigeria in a 5 year period for planning purposes.Methods: Data was collected from patients’ case notes from January 2006 to December 2011. A systematic sampling of 468 patients from 1173 case notes of patient with (PSEDs) was done. Information retrieved was: age, sex, state of residence and diagnosis. All patients were examined by the glaucoma and the vitroretinal specialist as the case may be. They had visual acuity, refraction, slit lamp examination (including intraocular pressure (IOP) with Goldman applanation tonometer), and dilated fundoscopy with (bilateral indirect ophthalmoscopy) BIO, slit lamp using 20 D, 78 D and 90 D respectively. The glaucoma patients in addition had central visual field (CVF), Central cornea thickness (CCT), fundus photograph and in some cases optical coherence tomography (OCT) done in addition to the above.Results: The mean age was 59.98 years (SD 17.67) and the age range is 5-95 years. Males outnumbered females by 63% to 37%. The diseases were more common in age group 61 to 80. Patients’ attendances were mostly from Ijebu division of Ogun state (57%). Glaucoma is the commonest cause of attendance 262 (56%) followed by diabetic retinopathy 29 (6.2%) and age-related macular degeneration (ARMD) 28 (6.0%).Conclusions: Glaucoma, diabetic retinopathy and ARMD were noted as the commonest PSEDs in Ijebu division in Southwestern Nigeria.

scholarly journals Inhibition of APE1/Ref-1 for Neovascular Eye Diseases: From Biology to Therapy

2021 ◽  
Vol 22 (19) ◽  
pp. 10279
Author(s):  
Gabriella D. Hartman ◽  
Nathan A. Lambert-Cheatham ◽  
Mark R. Kelley ◽  
Timothy W. Corson
Keyword(s):  
Vision Loss ◽  
Eye Diseases ◽  
Age Related Macular Degeneration ◽  
Neuroprotective Effects ◽  
Multifunctional Protein ◽  
Age Related ◽  
Transcription Factor Activation ◽  
Molecule Inhibitor ◽  
Orally Bioavailable ◽  
Endothelial Growth Factor

Proliferative diabetic retinopathy (PDR), neovascular age-related macular degeneration (nvAMD), retinopathy of prematurity (ROP) and other eye diseases are characterized by retinal and/or choroidal neovascularization, ultimately causing vision loss in millions of people worldwide. nvAMD and PDR are associated with aging and the number of those affected is expected to increase as the global median age and life expectancy continue to rise. With this increase in prevalence, the development of novel, orally bioavailable therapies for neovascular eye diseases that target multiple pathways is critical, since current anti-vascular endothelial growth factor (VEGF) treatments, delivered by intravitreal injection, are accompanied with tachyphylaxis, a high treatment burden and risk of complications. One potential target is apurinic/apyrimidinic endonuclease 1/reduction-oxidation factor 1 (APE1/Ref-1). The multifunctional protein APE1/Ref-1 may be targeted via inhibitors of its redox-regulating transcription factor activation activity to modulate angiogenesis, inflammation, oxidative stress response and cell cycle in neovascular eye disease; these inhibitors also have neuroprotective effects in other tissues. An APE1/Ref-1 small molecule inhibitor is already in clinical trials for cancer, PDR and diabetic macular edema. Efforts to develop further inhibitors are underway. APE1/Ref-1 is a novel candidate for therapeutically targeting neovascular eye diseases and alleviating the burden associated with anti-VEGF intravitreal injections.

scholarly journals Therapeutic effect of Keap1-Nrf2-ARE pathway-related drugs on age-related eye diseases through anti-oxidative stress

2021 ◽  
Vol 14 (8) ◽  
pp. 1260-1273
Author(s):  
Zi-Yan Cai ◽  
◽  
Ke Liu ◽  
Xuan-Chu Duan ◽  
◽  
...  
Keyword(s):  
Oxidative Stress ◽  
Vision Loss ◽  
Eye Diseases ◽  
The Body ◽  
Age Related Macular Degeneration ◽  
Therapeutic Effects ◽  
Related Factor ◽  
Classical Pathway ◽  
Age Related ◽  
Important Relationship

Age-related eye diseases, including cataract, glaucoma, diabetic retinopathy (DR), and age-related macular degeneration (AMD), are the leading causes of vision loss in the world. Several studies have shown that the occurrence and development of these diseases have an important relationship with oxidative stress in the eye. The Keap1-Nrf2-ARE pathway is a classical pathway that resists oxidative stress and inflammation in the body. This pathway is also active in the development of age-related eye diseases. A variety of drugs have been shown to treat age-related eye diseases through the Keap1-Nrf2-ARE (Kelch-like ECH-Associating protein 1- nuclear factor erythroid 2 related factor 2-antioxidant response element) pathway. This review describes the role of oxidative stress in the development of age-related eye diseases, the function and regulation of the Keap1-Nrf2-ARE pathway, and the therapeutic effects of drugs associated with this pathway on age-related eye diseases.

scholarly journals Convolutional Neural Network Audio Classifier for Alarm Sound Detection

2019 ◽  
Vol 8 (6) ◽  
pp. 4554-4557
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Short Term Memory ◽  
Sound Recognition ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Differential Network ◽  
Sound Detection ◽  
Long Short Term Memory ◽  
Lstm Network

Neural Networks (ANN) has evolved through many stages in the last three decades with many researchers contributing in this challenging field. With the power of math complex problems can also be solved by ANNs. ANNs like Convolutional Neural Network (CNN), Deep Neural network, Generative Adversarial Network (GAN), Long Short Term Memory (LSTM) network, Recurrent Neural Network (RNN), Ordinary Differential Network etc., are playing promising roles in many MNCs and IT industries for their predictions and accuracy. In this paper, Convolutional Neural Network is used for prediction of Beep sounds in high noise levels. Based on Supervised Learning, the research is developed the best CNN architecture for Beep sound recognition in noisy situations. The proposed method gives better results with an accuracy of 96%. The prototype is tested with few architectures for the training and test data out of which a two layer CNN classifier predictions were the best.

Intraocular exosomes in eye diseases

2021 ◽  
Vol 21 ◽  
Author(s):  
Hui Zhang ◽  
Xiaomin Zhang ◽  
Xiaorong Li
Keyword(s):  
Messenger Rna ◽  
Biological Fluids ◽  
Eye Diseases ◽  
Age Related Macular Degeneration ◽  
Pathological State ◽  
Barrier Dysfunction ◽  
Blood Retinal Barrier ◽  
Ecm Remodeling ◽  
Age Related ◽  
Eye Tissues

: Exosomes, nanosized extracellular vesicles with a size of 30–150nm, contain many biological materials, such as messenger RNA (mRNA), microRNA (miRNA), proteins, and transcription factors. It has been identified in all biological fluids and recognized as an important part of intercellular communication. While the role of exosomes in cancer has been studied in-depth, our understanding of their relevance for ocular tissues has just begun to evolve. Intraocular fluids, including aqueous humor and vitreous humor, play a role in nourishing eye tissues and in expelling metabolites. In the pathological state, intraocular exosomes can mediate pathological processes such as ECM remodeling, retinal inflammation, and blood-retinal barrier dysfunction. Herein, we reviewed the latest advances of intraocular exosomes in the research of several eye diseases, including glaucoma, age-related macular degeneration, myopia, and ocular tumors, and discuss how intraocular exosomes contribute to the pathogenesis and progression of multiple eye diseases.

Sign in / Sign up

Export Citation Format

Share Document