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

BACKGROUNDMorphological changes of the vasculature system in patients with myopia have been observed by Doppler ultrasound and fundus fluorescein angiography (FFA); however, these studies have limitations. Doppler ultrasound provides low-resolution images which are mainly obtained from visualized large vessels, and FFA is an invasive examination. Optic coherence tomography (OCT) angiography is a noninvasive, high-resolution measurement for vascular density. The purpose of this study was to investigate the change of vascular density in myopic eyes using OCT angiography.

METHODSThis cross-sectional study includes a total of 91 eyes from 47 participants including control, moderate, and high myopia that were evaluated by OCT angiography. Patients with myopia were recruited from the Refractive Department, Shenzhen Aier Eye Hospital, from August 5, 2015 to April 1, 2016. Emmetropic eyes were from healthy volunteers. The vascular density at macula and optic disc regions, ganglion cell complex (GCC) thickness, and retinal nerve fiber layer (RNFL) thickness were measured. Their relationships with axial length (AL) and refractive error were analyzed. One-way analysis of variance (ANOVA), Pearson's correlation, and generalized estimating equation were used for statistical analysis.

RESULTSBoth superficial and deep macular vascular density were highest in control (25.64% ± 3.76% and 37.12% ± 3.66%, respectively), then in moderate myopia (21.15% ± 5.33% and 35.35% ± 5.50%, respectively), and lowest in high myopia group (19.64% ± 3.87% and 32.81% ± 6.29%, respectively) (F = 13.74 and 4.57, respectively; both P < 0.001). Both superficial (β = -0.850 and 0.460, respectively) and deep (β = -0.766 and 0.396, respectively) macular vascular density were associated with AL and spherical equivalent (all P < 0.001). Superficial macular vascular density was associated with GCC thickness (β = 0.244, P = 0.040), independent of spherical equivalent. The vascular density in optic disc region had no difference among the three groups, and it was not associated with AL, spherical equivalent, or RNFL thickness.

CONCLUSIONOur results suggested that with the increase of myopia, the vascular density decreased in macular region, but not in optic disc region.

Adult ; Cross-Sectional Studies ; Eye ; blood supply ; Female ; Fluorescein Angiography ; Humans ; Macula Lutea ; pathology ; physiopathology ; Male ; Middle Aged ; Myopia ; pathology ; physiopathology ; Optic Disk ; pathology ; physiopathology ; Prospective Studies ; Retina ; pathology ; physiopathology ; Retinal Ganglion Cells ; pathology ; Tomography, Optical Coherence ; Young Adult