INTRODUCTION: Detection of neurological conditions is of high importance in the current context of increasingly ageing populations. Imaging of the retina and the optic nerve head represents a unique opportunity to detect brain diseases, but requires specific human expertise. We review the current outcomes of artificial intelligence (AI) methods applied to retinal imaging for the detection of neurological and neuro-ophthalmic conditions. METHOD: Current and emerging concepts related to the detection of neurological conditions, using AI-based investigations of the retina in patients with brain disease were examined and summarised. RESULTS: Papilloedema due to intracranial hypertension can be accurately identified with deep learning on standard retinal imaging at a human expert level. Emerging studies suggest that patients with Alzheimer's disease can be discriminated from cognitively normal individuals, using AI applied to retinal images. CONCLUSION Recent AI-based systems dedicated to scalable retinal imaging have opened new perspectives for the detection of brain conditions directly or indirectly affecting retinal structures. However, further validation and implementation studies are required to better understand their potential value in clinical practice.
Humans ; Artificial Intelligence ; Brain/diagnostic imaging* ; Retina ; Optic Disk ; Aging

OBJECTIVE: To observe the effect of acupuncture on visual acuity, intraocular pressure, visual field, retinal and choroidal thickness on optic disc and macular area in patients with optic atrophy. METHODS: A total of 33 patients with optic atrophy were treated with acupuncture. Acupuncture was given at Chengqi (ST 1), Shangjingming (Extra), Qiuhou (EX-HN 7) and Fengchi (GB 20) etc., 30 min each time, once a day, for 14 days. The visual acuity, intraocular pressure, visual field indexes (mean deviation [MD], pattern standard deviation [PSD] and visual field index [VFI]), optic disc retinal nerve fiber layer thickness, macular retinal thickness and choroidal thickness of optic disc and sub-foveal were compared before and after treatment. RESULTS: Compared before treatment, the visual acuity was increased (P<0.05), the MD value was decreased (P<0.05), the thickness of nerve fiber layer on the upper temporal side of optic disc was thinner (P<0.05), and the choroidal thickness of average, nasal side and lower temporal side of optic disc was increased (P<0.05). There was significant correlation between visual field MD and retinal nerve fiber layer thickness in different quadrants before and after treatment (P<0.01). CONCLUSION Acupuncture could improve visual acuity, increase choroidal thickness in part of optic disc area in patients with optic atrophy.
Acupuncture Therapy ; Humans ; Optic Atrophy/therapy* ; Optic Disk/diagnostic imaging* ; Retina/diagnostic imaging* ; Tomography, Optical Coherence

Glaucoma is the leading cause of irreversible blindness, but its early symptoms are not obvious and are easily overlooked, so early screening for glaucoma is particularly important. The cup to disc ratio is an important indicator for clinical glaucoma screening, and accurate segmentation of the optic cup and disc is the key to calculating the cup to disc ratio. In this paper, a full convolutional neural network with residual multi-scale convolution module was proposed for the optic cup and disc segmentation. First, the fundus image was contrast enhanced and polar transformation was introduced. Subsequently, W-Net was used as the backbone network, which replaced the standard convolution unit with the residual multi-scale full convolution module, the input port was added to the image pyramid to construct the multi-scale input, and the side output layer was used as the early classifier to generate the local prediction output. Finally, a new multi-tag loss function was proposed to guide network segmentation. The mean intersection over union of the optic cup and disc segmentation in the REFUGE dataset was 0.904 0 and 0.955 3 respectively, and the overlapping error was 0.178 0 and 0.066 5 respectively. The results show that this method not only realizes the joint segmentation of cup and disc, but also improves the segmentation accuracy effectively, which could be helpful for the promotion of large-scale early glaucoma screening.
Diagnostic Techniques, Ophthalmological ; Fundus Oculi ; Glaucoma/diagnostic imaging* ; Humans ; Neural Networks, Computer ; Optic Disk/diagnostic imaging*

Glaucoma is one of blind causing diseases. The cup-to-disc ratio is the main basis for glaucoma screening. Therefore, it is of great significance to precisely segment the optic cup and disc. In this article, an optic cup and disc segmentation model based on the linear attention and dual attention is proposed. Firstly, the region of interest is located and cropped according to the characteristics of the optic disc. Secondly, linear attention residual network-34 (ResNet-34) is introduced as a feature extraction network. Finally, channel and spatial dual attention weights are generated by the linear attention output features, which are used to calibrate feature map in the decoder to obtain the optic cup and disc segmentation image. Experimental results show that the intersection over union of the optic disc and cup in Retinal Image Dataset for Optic Nerve Head Segmentation (DRISHTI-GS) dataset are 0.962 3 and 0.856 4, respectively, and the intersection over union of the optic disc and cup in retinal image database for optic nerve evaluation (RIM-ONE-V3) are 0.956 3 and 0.784 4, respectively. The proposed model is better than the comparison algorithm and has certain medical value in the early screening of glaucoma. In addition, this article uses knowledge distillation technology to generate two smaller models, which is beneficial to apply the models to embedded device.
Humans ; Optic Disk/diagnostic imaging* ; Glaucoma/diagnosis* ; Algorithms ; Diagnostic Techniques, Ophthalmological ; Databases, Factual

The existing retinal vessels segmentation algorithms have various problems that the end of main vessels are easy to break, and the central macula and the optic disc boundary are likely to be mistakenly segmented. To solve the above problems, a novel retinal vessels segmentation algorithm is proposed in this paper. The algorithm merged together vessels contour information and conditional generative adversarial nets. Firstly, non-uniform light removal and principal component analysis were used to process the fundus images. Therefore, it enhanced the contrast between the blood vessels and the background, and obtained the single-scale gray images with rich feature information. Secondly, the dense blocks integrated with the deep separable convolution with offset and squeeze-and-exception (SE) block were applied to the encoder and decoder to alleviate the gradient disappearance or explosion. Simultaneously, the network focused on the feature information of the learning target. Thirdly, the contour loss function was added to improve the identification ability of the blood vessels information and contour information of the network. Finally, experiments were carried out on the DRIVE and STARE datasets respectively. The value of area under the receiver operating characteristic reached 0.982 5 and 0.987 4, respectively, and the accuracy reached 0.967 7 and 0.975 6, respectively. Experimental results show that the algorithm can accurately distinguish contours and blood vessels, and reduce blood vessel rupture. The algorithm has certain application value in the diagnosis of clinical ophthalmic diseases.
Algorithms ; Fundus Oculi ; Optic Disk ; ROC Curve ; Retinal Vessels/diagnostic imaging*

BACKGROUNDOptical coherence tomography (OCT) angiography is a novel technique by which we can detect the local perfusion of fundus directly. The aim of this study was to evaluate the reproducibility of optic disc and macular flow perfusion parameters in rhesus monkeys using OCT angiography.

METHODSEighteen healthy monkeys (18 eyes) were subjected to optic disc and macula flow index measurements via a high-speed and high-resolution spectral-domain OCT XR Avanti with a split-spectrum amplitude de-correlation angiography algorithm. Right eye was imaged 3 times during the first examination and once during each of the two following examinations. The intra-visit and inter-visit intraclass correlation coefficients (ICCs) were both determined.

RESULTSThe average flow indices of the four optic disc area layers were 0.171 ± 0.009 (optic nerve head), 0.015 ± 0.004 (vitreous), 0.052 ± 0.009 (radial peripapillary capillary), and 0.167 ± 0.011 (choroid). Average flow indices of the four macula area layers were 0.044 ± 0.011 (superficial retina), 0.036 ± 0.011 (deep retina), 0.016 ± 0.009 (outer retina), and 0.155 ± 0.013 (choroid). Intra-visit (ICC value: 0.821-0.954) and inter-visit (ICC value: 0.844-0.899) repeatability were both high.

CONCLUSIONSThe study is about the reproducibility of optic disc and macular perfusion parameters as measured by OCT angiography in healthy rhesus monkeys. Flow index measurement reproducibility is high for both the optic disc and macula of normal monkey eyes. OCT angiography might be a useful technique to assess changes when examining monkeys with experimental ocular diseases.

Angiography ; Animals ; Macaca mulatta ; Macula Lutea ; blood supply ; diagnostic imaging ; Male ; Optic Disk ; blood supply ; diagnostic imaging ; Reproducibility of Results ; Tomography, Optical Coherence ; methods

PURPOSE: We evaluated fundus and fluorescein angiography (FAG) findings and characteristics that can help distinguish nonarteritic anterior ischemic optic neuropathy (NAION) from optic neuritis (ON). METHODS: Twenty-three NAION patients and 17 ON with disc swelling patients were enrolled in this study. We performed fundus photography and FAG. The disc-swelling pattern, hyperemia grade, presence of splinter hemorrhages, cotton-wool spots, artery/vein ratio and degree of focal telangiectasia were investigated. The FAG findings for each patient were compared with respect to the following features: the pattern of disc leakage in the early phase, arteriovenous (artery/vein) transit time (second), and the presence and pattern of the filling delay. RESULTS: Cotton-wool spots, focal telangiectasia, and venous congestion were more common in the affected eyes of NAION patients. Upon FAG, 76.5% of the patients in the ON group exhibited normal choroidal circulation. However, 56.5% of patients in the NAION group demonstrated abnormal filling defects, such as peripapillary, generalized, or watershed zone filling delays. CONCLUSIONS: Fundus findings, including cotton-wool spots, focal telangiectasia, and venous congestion in the affected eye, may be clues that can be used to diagnose NAION. In addition, choroidal insufficiencies on FAG could be also helpful in differentiating NAION from ON.
Choroid/blood supply/*diagnostic imaging ; Female ; Fluorescein Angiography/*methods ; Fundus Oculi ; Humans ; Male ; Middle Aged ; Optic Disk/blood supply/*diagnostic imaging ; Optic Neuritis/*diagnosis ; Optic Neuropathy, Ischemic/*diagnosis ; Photography/*methods ; Retrospective Studies

PURPOSE: To investigate the relationship between vitamin D and glaucoma. METHODS: This retrospective, cross-sectional study included subjects who underwent a health screening at the Health Screening Center of Kangbuk Samsung Hospital from August 2012 to July 2013. All fundus photographs were reviewed by ophthalmologists. The ophthalmologists determined if an eye was glaucomatous based on the criteria set forth by the International Society of Geographical and Epidemiological Ophthalmology and by the appearance of the retinal nerve fiber layer and optic disc. If the subjects previously underwent an ophthalmologic examination, they were enrolled based on the documented history. In addition to fundus photographs, each participant underwent a systemic examination including blood sampling and sociodemographic and behavioral questionnaires. The subjects were divided into five groups according to serum 25-hydroxyvitamin D (25(OH)D) level. Multivariate logistic regression models were constructed to assess possible associations between elevated glaucoma risk and systemic factors with a p < 0.2 on univariate analysis. RESULTS: Of the 169,208 subjects older than 20 years, 123,331 were eligible for the study. There was no difference in the prevalence of glaucoma according to quintile of serum 25(OH)D level based on sex (p = 0.412 for males, p = 0.169 for females). According to the multivariable-adjusted logistic analysis, the odds ratio of glaucoma for the fourth quintile was significantly lower than that of the first quintile in females (odds ratio, 0.713; 95% confidence interval, 0.520 to 0.979). CONCLUSIONS: Lower 25(OH)D level was significantly associated with an elevated risk of glaucoma in females compared with higher 25(OH)D level. Further evaluation is needed to investigate the relationship between glaucoma and vitamin D.
Adult ; Cross-Sectional Studies ; Female ; Follow-Up Studies ; Glaucoma/diagnosis/*epidemiology/etiology ; Humans ; Incidence ; Intraocular Pressure ; Male ; Optic Disk/diagnostic imaging ; Prevalence ; Republic of Korea/epidemiology ; Retrospective Studies ; Vitamin D/*blood ; Vitamin D Deficiency/blood/complications/*epidemiology ; Young Adult

Background: Currently, spectral-domain optical coherence tomography (SD-OCT) appears to be a new type of glaucoma diagnostic tool. Thus, this study aimed to evaluate the effectiveness of glaucoma diagnostic parameters from SD-OCT of patients with different severities of myopia. Methods: This was a cross-sectional study. A total of 248 participants (248 eyes) were enrolled, including 51 cases in the early primary open-angle glaucoma group, 79 cases in the control group (0.50 D to -0.50 D, excluding -0.50 D), 47 cases in the low-myopic group (-0.50 to -3.00 D, excluding -3.00 D), 43 cases in the moderate-myopic group (-3.00 to -6.00 D, excluding -6.00 D), and 28 cases in the high-myopic group (≤-6.00 D). All participants were examined using the Humphrey visual field test and SD-OCT. The SD-OCT parameters of the retinal nerve fiber layer (RNFL) and ganglion cell complex were analyzed statistically using the receiver operating characteristic curve and area under the curve (AUC). Results: The AUC showed that the best parameters for the control and low-myopic groups were the inferior and inferior temporal RNFL thicknesses (AUC >0.94), respectively; for the moderate- and high-myopic groups, the best parameter was the temporal low RNFL thickness (AUC, 0.926 and 0.896, respectively). The AUC of the inferior parameters of the moderate-myopic group (0.864) was lower, ranked 15 among all RNFL parameters. When the sensitivity was fixed at 85%, the specificity of the inferior, superior, inferior temporal, and superior temporal quadrants was higher (>80%) in the control and low-myopic groups, while they were lower (20-60%) for the moderate- and high-myopia groups. The green color based on the OCT database was also less for the high-myopic group compared with that of other groups (P < 0.05). Conclusions Glaucoma diagnostic parameters from SD-OCT were not clinically effective for the moderate- and high-myopic groups. The specificities were low. The moderate- and high-myopic groups require comprehensive analyses for the diagnoses of glaucoma. The SD-OCT database should be improved to better indicate the level of myopia based on the corresponding diopter readings.
Aged ; Case-Control Studies ; Cross-Sectional Studies ; Female ; Glaucoma ; diagnostic imaging ; Glaucoma, Open-Angle ; Humans ; Male ; Middle Aged ; Nerve Fibers ; Optic Disk ; ROC Curve ; Retinal Ganglion Cells ; Tomography, Optical Coherence ; Visual Fields

PURPOSE: To compare clinical, angiographic, and optical coherence tomographic characteristics between eyes with acute Vogt-Koyanagi-Harada (VKH) disease and eyes with acute bilateral central serous chorioretinopathy (CSC), and to demonstrate distinguishing features between the two diseases in confusing cases. METHODS: The medical records of 35 patients with VKH disease and 25 patients with bilateral CSC were retrospectively reviewed. Characteristics according to slit-lamp biomicroscopy, ophthalmoscopy, fundus photography, fluorescein angiography, indocyanine green angiography, and spectral-domain optical coherence tomography were compared between the two diseases. RESULTS: Five of 35 patients (10 of 70 eyes, 14.3%) with VKH disease were initially misdiagnosed as CSC patients, and six of 25 patients (12 of 50 eyes, 24%) with bilateral CSC were initially misdiagnosed as patients with VKH disease. Pigment epithelial detachment in CSC and optic disc hyperemia in VKH disease show the highest positive predictive values of 100% for each disease. CONCLUSIONS: Optic disc hyperemia in VKH disease and pigment epithelial detachment in bilateral CSC are the most specific clinical manifestations of each disease at initial patient presentation.
Acute Disease ; Adult ; Aged ; Aged, 80 and over ; Central Serous Chorioretinopathy/*diagnostic imaging ; Female ; Fluorescein Angiography ; Humans ; Hyperemia/diagnosis ; Indocyanine Green/administration & dosage ; Male ; Middle Aged ; Multimodal Imaging ; Ophthalmoscopy ; Optic Disk/blood supply ; Photography ; Retinal Detachment/diagnosis ; Retinal Pigment Epithelium/pathology ; Retrospective Studies ; Slit Lamp Microscopy ; Tomography, Optical Coherence ; Uveomeningoencephalitic Syndrome/*diagnostic imaging ; Young Adult