China
Africa
Explore chapters and articles related to this topic
Multiphoton imaging of the retina
Published in Pablo Artal, Handbook of Visual Optics, 2017
Robin Sharma, Jennifer J. Hunter
Second, light has to propagate from the anterior optics to the photoreceptors through the inner retina. Except for recent results in horizontal cell imaging (Guevara-Torres et al., 2015), typically inner retinal layers remain hidden during ophthalmic imaging because they are naturally translucent. Not only do inner retinal cells play a crucial role in retinal function and neural processing, they can get severely affected during disease progression. For instance, ganglion cells die during prevalent eye diseases such as glaucoma (Weinreb et al., 2014) that can lead to an irreversible vision loss and is one of the most common causes of blindness in the world. While individual photoreceptors and retinal pigment epithelium (RPE) cells are routinely imaged using conventional AO ophthalmoscopy, these techniques have not been able to resolve individual ganglion cells or other cell classes in the inner retina without the use of exogenous fluorophores.
An Integration of Blockchain and Machine Learning into the Health Care System
Published in Om Prakash Jena, Sabyasachi Pramanik, Ahmed A. Elngar, Machine Learning Adoption in Blockchain-Based Intelligent Manufacturing, 2022
Mahita Sri Arza, Sandeep Kumar Panda
Glaucoma is a prevalent type of eye disease. It is caused by an increase in intraocular pressure (IOP), which leads to loss of vision due to optic nerve damage. Even though an increase in IOP does not necessarily indicate glaucoma, it is a significant factor of risk and a cause of glaucomatous optic neuropathy. If glaucoma goes undiagnosed and untreated, it can cause irreversible blindness [24]. In industrialized countries such as the United States, glaucoma is the leading cause of vision impairment and complete loss of sight [25] [26]. Over the last few decades, significant advances were made in the automation of the diagnosis and prediction of glaucoma using various ML models.
Conclusion and Future Scope
Published in Arwa Ahmed Gasm Elseid, Alnazier Osman Mohammed Hamza, Computer-Aided Glaucoma Diagnosis System, 2020
Arwa Ahmed Gasm Elseid, Alnazier Osman Mohammed Hamza
In conclusion, glaucoma is a group of eye diseases that have no symptoms and, if not detected at an early stage, may cause permanent blindness; some preceding structural damage to the retina is one of the marked symptoms of glaucoma. It is diagnosed by an examination of the size, structure, shape, and color of the optic disc, optic cup, and retinal nerve fiber layer (RNFL), and, due to the subjectivity of human experience, fatigue factor, etc., there is a need for a CAD system to manage large volumes of data and provide objective assessments for decision support and help in labor-intensive, observer-driven tasks using the fundus images, which, is among one of the main biomedical imaging techniques to analyze the internal structure of the retina. The proposed technique provides a novel algorithm to detect glaucoma from a digital fundus image. It uses MATLAB® software evaluated on a RIM_ONE (version two) database, containing digital fundus images from 158 patients (118 healthy images and 40 glaucomatous images) and DRISHTI_GS, which contains 101 digital fundus images (70 glaucomatous images and 31 healthy images), and RIM-ONE (version one) (200 healthy images and 250 glaucomatous images), where the proposed approach used to detect glaucoma was carried out via three steps: firstly, OD and OC segmentation. In OD and OC segmentation several steps were done like pre-processing, thresholding, boundary smoothing, and disc reconstruction to a full circle, where OD segmentation achieved a best dice coefficient (DSC) of 90% and a Structural Similarity (SSIM) of 83%, and OC segmentation results were a dice coefficient of 73% and a Structural Similarity (SSIM) of 93%, and cup segmentation achieved an SSIM of 93%; secondly, shape, color, and texture features were extracted from the segmented parts and then the most relevant features were selected; thirdly, many types of classifier were applied to find the best classification accuracy via a set of color-based, shape-based, and texture features by extracting 13 shape features from disc and cup, and extracting 25 texture features from RNFL (retinal nerve fiber layer) using the gray level co-occurrence method, Tamar algorithm, and 3 color features for each of disc, cup, and RNFL. Next, best features were selected by T-test method and Sequential feature selection (SFS) to introduce eight features (cup minor axes, disc and cup mean, standard deviation, and RNFL standard deviation and coarseness) with an average accuracy of 97%, maximizing the area under the curve (AUC) 0.99 using the SVM classifier. The key contribution in this work proposes new features that are suitable for glaucoma detection.
Trace elements exposure and risk in age-related eye diseases: a systematic review of epidemiological evidence
Published in Journal of Environmental Science and Health, Part C, 2021
Onyinyechi Bede-Ojimadu, Chinna N. Orish, Beatrice Bocca, Flavia Ruggieri, Chiara Frazzoli, Orish E. Orisakwe
Vision plays pivotal role in every facet and stage of human life. In 2017, vision impairment, including blindness, was ranked the third cause among all impairments for years lived with disability.1 Although vision loss and blindness affect people of all ages, the majority of people with vision impairments are over the age of 50 years.2 Age-related eye diseases, including cataract, age-related macular degeneration (AMD), glaucoma and diabetic retinopathy (DR) are the leading causes of moderate to severe vision impairment and blindness globally.2,3 Recent reports from WHO2 indicate that about 45% (1 billion) of an estimated 2.2 billion cases of vision impairment, could be prevented.2 Although age and genetics have been reported as common risk factors,4–6 exposures to environmental trace elements have also been suggested as co-risk factors in the pathogenesis of age-related eye diseases.7,8 However, the understanding of the role of trace elements exposure in these diseases remains limited.
Exudates detection in fundus images using mean-shift segmentation and adaptive thresholding
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2019
Abderrahmane Elbalaoui, Mohamed Fakir
Diabetic retinopathy (DR) is an eye disease caused by the increase in insulin in blood and the leading cause of blindness. The World Diabetes Foundation estimates that there will be over 438 million people with diabetes worldwide by 2030. There are approximately 93 million people with DR, 17 million with proliferative DR, 21 million with diabetic macular oedema and 28 million with VTDR worldwide. Early detection of DR through screening can prevent blindness and allow for maintenance of good vision. Diabetic retinopathy is characterised by the development of retinal microaneurysms, haemorrhages and exudates. These exudates are small white or yellowish white deposits with sharp margins. They are located in the outer layers of the retina, deep to the retinal vessels. Figure 1 shows digital retinal image with exudates.