Advances in retina imaging as potential biomarkers for early diagnosis of Alzheimer's disease

A review on the new age methodologies for early detection of Alzheimer's and Parkinson's disease

BACKGROUNDS

Neurodegenerative diseases (NDDs) such as Alzheimer's (AD) and Parkinson's (PD) are often diagnosed late, impeding effective treatment; therefore, early detection is imperative. Modern methodologies can serve a pivotal role in fulfilling the crucial need for timely detection and intervention in this context.

OBJECTIVES

Evaluate early detection's significance and summarize key technologies (biomarkers, neuroimaging, AI/ML, genetics, digital health) for enhanced diagnostic strategies in AD and PD.

METHODS

This study employs a focused descriptive review approach, encompassing analysis of peer-reviewed articles and clinical trials from existing literature, to provide a nuanced exploration of the subject matter.

FINDINGS

This review underscores the efficacy of non-invasive biomarkers, biosensors and emerging promising technologies for advancing early diagnosis of AD and PD.

CONCLUSION

The landscape of early NDD detection has been reshaped by technology, yet challenges persist, encompassing the domains of validation and ethics. A collaborative effort between medical professionals, researchers and technologists is imperative to effectively address and combat NDDs.

Neuron-level explainable AI for Alzheimer's Disease assessment from fundus images

Alzheimer's Disease (AD) is a progressive neurodegenerative disease and the leading cause of dementia. Early diagnosis is critical for patients to benefit from potential intervention and treatment. The retina has emerged as a plausible diagnostic site for AD detection owing to its anatomical connection with the brain. However, existing AI models for this purpose have yet to provide a rational explanation behind their decisions and have not been able to infer the stage of the disease's progression. Along this direction, we propose a novel model-agnostic explainable-AI framework, called Granula ̲ r Neuron-le v ̲ el Expl a ̲ iner (LAVA), an interpretation prototype that probes into intermediate layers of the Convolutional Neural Network (CNN) models to directly assess the continuum of AD from the retinal imaging without the need for longitudinal or clinical evaluations. This innovative approach aims to validate retinal vasculature as a biomarker and diagnostic modality for evaluating Alzheimer's Disease. Leveraged UK Biobank cognitive tests and vascular morphological features demonstrate significant promise and effectiveness of LAVA in identifying AD stages across the progression continuum.

Recent Advances in Fluorescent Theranostics for Alzheimer's Disease: A Comprehensive Survey on Design, Synthesis, and Properties

Alzheimer's disease (AD) is the most common form of neurodegenerative dementia that is rapidly becoming a major health problem, especially in developed countries because of their increasing life expectancy. Two main problems are often associated with the disease: (i) the absence of a widely accessible "gold-standard" for early diagnosis and (ii) lack of effective therapies with disease-modifying effects. The recent success of the monoclonal antibody lecanemab played an important role not only in clarifying a possible druggable pathway but also in spelling the revival of small molecule drug discovery. Unlike bulky biologics, small molecules are structurally less complex, generally cheaper, and compatible with at-home oral consumption, making it feasible for people to start their drug regimen early and stay on it longer. In this sense, small-molecule near-infrared fluorescent theranostics have been gaining more and more attention from the scientific community, as they have the potential to simultaneously provide diagnostic outputs and deliver therapeutic action, paving the way toward personalized medicine in AD patients. They also have the potential to shift the diagnostic "status-quo" from expensive and limited-access PET radiotracers toward inexpensive and handy imaging tools widely available for primary patient screening and preclinical animal studies. Herein, we review the most recent advances in the field of fluorescent theranostics for Alzheimer's disease, detailing their design strategies, synthetic approaches and imaging and therapeutic properties in vitro and in vivo. With this Review, we intend to provide a milestone in the acquired knowledge in the field of AD theranostics, encouraging the future development of properly designed theranostic compounds with improved chances to reach clinical applications.

Intrinsic signal optoretinography of dark adaptation abnormality due to rod photoreceptor degeneration

This research aims to investigate the potential of using intrinsic optical signal (IOS) optoretinography (ORG) to objectively detect dark adaptation (DA) abnormalities related to rod photoreceptor degeneration. Functional optical coherence tomography (OCT) was employed in both wild-type (WT) and retinal degeneration 10 (rd10) mice to conduct this assessment. Dynamic OCT measurements captured the changes in retinal thickness and reflectance from light-to-dark transition. Comparative analysis revealed significant IOS alterations within the outer retina. Specifically, a reduction in thickness from external limiting membrane (ELM) peak to retinal pigment epithelium (RPE) peak was observed (WT: 1.13 ± 0.69 µm, 30 min DA; rd10: 2.64 ± 0.86 µm, 30 min DA), as well as a decrease in the intensity of the inner segment ellipsoid zone (EZ) in 30 min DA compared to light adaptation (LA). The reduction of relative EZ intensity was notable in rd10 after 5 min DA and in WT after 15 min DA, with a distinguishable difference between rd10 and WT after 10 min DA. Furthermore, our findings indicated a significant decrease in the relative intensity of the hypo-reflective band between EZ and RPE in rd10 retinas during DA, which primarily corresponds to the outer segment (OS) region. In conclusion, the observed DA-IOS abnormalities, including changes in ELM-RPE thickness, EZ, and OS intensity, hold promise as differentiators between WT and rd10 mice before noticeable morphological abnormalities occur. These findings suggest the potential of this non-invasive imaging technique for the early detection of dysfunction in retinal photoreceptors.

Non-invasive in vivo imaging of brain and retinal microglia in neurodegenerative diseases

Microglia play crucial roles in immune responses and contribute to fundamental biological processes within the central nervous system (CNS). In neurodegenerative diseases, microglia undergo functional changes and can have both protective and pathogenic roles. Microglia in the retina, as an extension of the CNS, have also been shown to be affected in many neurological diseases. While our understanding of how microglia contribute to pathological conditions is incomplete, non-invasive in vivo imaging of brain and retinal microglia in living subjects could provide valuable insights into their role in the neurodegenerative diseases and open new avenues for diagnostic biomarkers. This mini-review provides an overview of the current brain and retinal imaging tools for studying microglia in vivo. We focus on microglia targets, the advantages and limitations of in vivo microglia imaging approaches, and applications for evaluating the pathogenesis of neurological conditions, such as Alzheimer's disease and multiple sclerosis.

Deep Learning Models for the Screening of Cognitive Impairment Using Multimodal Fundus Images

OBJECTIVE

We aimed to develop a deep learning system capable of identifying subjects with cognitive impairment quickly and easily based on multimodal ocular images.

DESIGN

Cross sectional study.

SUBJECTS

Participants of Beijing Eye Study 2011 and patients attending Beijing Tongren Eye Center and Beijing Tongren Hospital Physical Examination Center.

METHODS

We trained and validated a deep learning algorithm to assess cognitive impairment using retrospectively collected data from the Beijing Eye Study 2011. Cognitive impairment was defined as a Mini-Mental State Examination score < 24. Based on fundus photographs and OCT images, we developed 5 models based on the following sets of images: macula-centered fundus photographs, optic disc-centered fundus photographs, fundus photographs of both fields, OCT images, and fundus photographs of both fields with OCT (multimodal). The performance of the models was evaluated and compared in an external validation data set, which was collected from patients attending Beijing Tongren Eye Center and Beijing Tongren Hospital Physical Examination Center.

MAIN OUTCOME MEASURES

Area under the curve (AUC).

RESULTS

A total of 9424 retinal photographs and 4712 OCT images were used to develop the model. The external validation sets from each center included 1180 fundus photographs and 590 OCT images. Model comparison revealed that the multimodal performed best, achieving an AUC of 0.820 in the internal validation set, 0.786 in external validation set 1, and 0.784 in external validation set 2. We evaluated the performance of the multi-model in different sexes and different age groups; there were no significant differences. The heatmap analysis showed that signals around the optic disc in fundus photographs and the retina and choroid around the macular and optic disc regions in OCT images were used by the multimodal to identify participants with cognitive impairment.

CONCLUSIONS

Fundus photographs and OCT can provide valuable information on cognitive function. Multimodal models provide richer information compared with single-mode models. Deep learning algorithms based on multimodal retinal images may be capable of screening cognitive impairment. This technique has potential value for broader implementation in community-based screening or clinic settings.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

The association of global vessel width with cognitive decline and cerebral small vessel disease burden in the KaiLuan study

Background

As the retinal microvasculature shares similarities with the cerebral microvasculature, numerous studies have shown that retinal vascular is associated with cognitive decline. In addition, several population-based studies have confirmed the association between retinal vascular and cerebral small vessel disease (CSVD) burden. However, the association of retinal vascular with CSVD burden as well as cognitive function has not been explored simultaneously. This study investigated the relations of retinal microvascular parameters (RMPs) with CSVD burden and cognitive function.

Methods

We conducted a cross-sectional study of participants in the KaiLuan study. Data were collected from subjects aged ≥18 years old who could complete retinal photography and brain magnetic resonance imaging (MRI) between December 2020 to October 2021 in the Kailuan community of Tangshan. RMPs were evaluated using a deep learning system. The cognitive function was measured using the Montreal Cognitive Assessment (MoCA). We conducted logistic regression models, and mediation analysis to evaluate the associations of RMPs with CSVD burden and cognitive decline.

Results

Of the 905 subjects (mean age: 55.42±12.02 years, 54.5% female), 488 (53.9%) were classified with cognitive decline. The fractal dimension (FD) [odds ratio (OR), 0.098, 95% confidence interval (CI): 0.015-0.639, P=0.015] and global vein width (OR: 1.010, 95% CI: 1.005-1.015, P<0.001) were independent risk factors for cognitive decline after adjustment for potential confounding factors. The global artery width was significantly associated with severe CSVD burden (OR: 0.985, 95% CI: 0.974-0.997, P=0.013). The global vein width was sightly associated with severe CSVD burden (OR: 1.005, 95% CI: 1.000-1.010, P=0.050) after adjusting for potential confounders. The multivariable-adjusted odds ratios (95% CI) in highest tertile versus lowest tertile of global vein width were 1.290 (0.901-1.847) for cognitive decline and 1.546 (1.004-2.290) for severe CSVD burden, respectively. Moreover, CSVD burden played a partial mediating role in the association between global vein width and cognitive function (mediating effect 6.59%).

Conclusions

RMPs are associated with cognitive decline and the development of CSVD. A proportion of the association between global vein width and cognitive decline may be attributed to the presence of CSVD burden.

Structural and Metabolic Retinal Changes Associated With Mild Cognitive Impairment in Type 2 Diabetes

Type 2 diabetes is associated with cognitive impairment and a twofold increased risk of dementia compared with age-matched individuals without diabetes. Given that the eye and the brain share similar embryologic origin and anatomical features, the retina offers a unique window to the brain. In this study, we wanted to determine whether there was a difference in retinal imaging-based neuronal and vascular markers in individuals with type 2 diabetes with or without mild cognitive impairment (MCI). We included 134 persons with type 2 diabetes. Based on neuropsychological tests, the prevalence of MCI was 28%. We performed seven-field color fundus photos, optical coherence tomography (OCT), OCT-angiography (OCT-A), and retinal oximetry to analyze retinal markers. In a multivariable cluster analysis, persons with MCI had a significantly thinner macular retinal nerve fiber layer and macular ganglion cell layer, and less venular oxygen saturation in the nasal quadrant compared with those without MCI. There were no differences in retinal vessel density, fractal dimension, width, tortuosity, or OCT-A markers. People with type 2 diabetes and MCI demonstrate alterations in retinal structure and metabolism, suggesting noninvasive retinal markers may be useful to detect people with type 2 diabetes at risk for cognitive dysfunction.

ARTICLE HIGHLIGHTS

Type 2 diabetes is associated with mild cognitive impairment (MCI). Therefore, retinal and cerebral neurodegeneration may run in parallel. To assess whether there was a difference in retinal structure, vessel, and metabolic parameters in individuals with MCI. We found those with MCI had a thinner macular retinal nerve fiber layer, macular ganglion cell layer, and less venular oxygen saturation. We suggest noninvasive retinal markers may be useful to detect those at risk of cognitive dysfunction.

Relationship of retinal capillary plexus and ganglion cell complex with mild cognitive impairment and dementia

OBJECTIVE

To investigate relationship of the retinal capillary plexus (RCP) and ganglion cell complex (GCC) with mild cognitive impairment (MCI) and dementia in a community-based study1.

METHODS

This cross-sectional study incorporated the participants of the Jidong Eye Cohort Study. Optical coherence tomography angiography was performed to obtain RCP vessel density and GCC thickness with detailed segments. The Mini-mental State Examination and Montreal Cognitive Assessment were used to assess cognitive status by professional neuropsychologists. Participants were thus divided into three groups: normal, mild cognitive impairment, and dementia. Multivariable analysis was used to measure relationship of ocular parameters with cognitive impairment.

RESULTS

Of the 2678 participants, the mean age was 44.1 ± 11.7 years. MCI and dementia occurred in 197 (7.4%) and 80 (3%) participants, respectively. Compared to the normal group, the adjusted odds ratio (OR) with the 95% confidence interval was 0.76 (0.65-0.90) for the correlation of lower deep RCP with MCI. We found the following items significantly associated with dementia compared with the normal group: a superficial (OR, 0.68 [0.54-0.86]) and deep (OR, 0.75 [0.57-0.99]) RCP, as well as the GCC (OR, 0.68 [0.54-0.85]). Compared to the MCI group, those with dementia had decreased GCC (OR, 0.75 [0.58-0.97]).

CONCLUSIONS

Decreased deep RCP density was associated with MCI. Decreased superficial and deep RCP and the thin GCC were correlated with dementia. These implied that the retinal microvasculature may develop into a promising non-invasive imaging marker to predict severity of cognitive impairment.

Structural and Functional Retinal Changes in Patients with Mild Cognitive Impairment with and without Diabetes

Our objective is to analyze retinal changes using optical coherence tomography angiography (OCT-A) in patients with mild cognitive impairment (MCI) to characterize structural and vascular alterations. This cross-sectional study involved 117 eyes: 39 eyes from patients with MCI plus diabetes (DM-MCI), 39 eyes from patients with MCI but no diabetes (MCI); and 39 healthy control eyes (C). All patients underwent a visual acuity measurement, a structural OCT, an OCT-A, and a neuropsychological examination. Our study showed a thinning of retinal nerve fiber layer thickness (RNFL) and a decrease in macular thickness when comparing the MCI-DM group to the C group (p = 0.008 and p = 0.016, respectively). In addition, an increase in arteriolar thickness (p = 0.016), a reduction in superficial capillary plexus density (p = 0.002), and a decrease in ganglion cell thickness (p = 0.027) were found when comparing the MCI-DM group with the MCI group. Diabetes may exacerbate retinal vascular changes when combined with mild cognitive impairment.

Intrinsic signal optoretinography revealing AD-induced retinal photoreceptor hyperexcitability before a detectable morphological abnormality

Neuronal hyperexcitability promises an early biomarker of Alzheimer's disease (AD). However, in vivo detection of neuronal hyperexcitability in the brain is technically challenging. The retina, one part of the central nervous system, presents a unique window for noninvasive monitoring of the brain function. This study aims to test the feasibility of using intrinsic signal optoretinography (ORG) for mapping retinal hyperexcitability associated with early-stage AD. Custom-designed optical coherence tomography (OCT) was employed for both morphological measurement and functional ORG of wild-type mice and 3xTg-AD mice. Comparative analysis revealed AD-induced retinal photoreceptor hyperexcitability prior to detectable structural degeneration.

Optical Coherence Tomography Assessment of Macular Thickness in Alzheimer's Dementia with Different Neuropsychological Severities

This retrospective case-control study aimed to investigate associations between disease severity of Alzheimer's dementia (AD) and macular thickness. Data of patients with AD who were under medication (n = 192) between 2013 and 2020, as well as an age- and sex-matched control group (n = 200) with normal cognitive function, were included. AD patients were divided into subgroups according to scores of the Mini-Mental State Examination (MMSE) and Clinical Dementia Rating (CDR). Macular thickness was analyzed via the Early Treatment Diabetic Retinopathy Study (ETDRS) grid map. AD patients had significant reductions in full macula layers, including inner circle, outer inferior area, and outer nasal area of the macula. Similar retinal thinning was noted in ganglion cells and inner plexiform layers. Advanced AD patients (MMSE score < 18 or CDR ≥ 1) showed more advanced reduction of macular thickness than the AD group (CDR = 0.5 or MMSE ≥ 18), indicating that severe cognitive impairment was associated with thinner macular thickness. Advanced AD is associated with significant macula thinning in full retina and inner plexiform layers, especially at the inner circle of the macula. Macular thickness may be a useful biomarker of AD disease severity. Retinal imaging may be a non-invasive, low-cost surrogate for AD.

Relationships between quantitative retinal microvascular characteristics and cognitive function based on automated artificial intelligence measurements

Introduction: The purpose of this study is to assess the relationship between retinal vascular characteristics and cognitive function using artificial intelligence techniques to obtain fully automated quantitative measurements of retinal vascular morphological parameters. Methods: A deep learning-based semantic segmentation network ResNet101-UNet was used to construct a vascular segmentation model for fully automated quantitative measurement of retinal vascular parameters on fundus photographs. Retinal photographs centered on the optic disc of 3107 participants (aged 50-93 years) from the Beijing Eye Study 2011, a population-based cross-sectional study, were analyzed. The main parameters included the retinal vascular branching angle, vascular fractal dimension, vascular diameter, vascular tortuosity, and vascular density. Cognitive function was assessed using the Mini-Mental State Examination (MMSE). Results: The results showed that the mean MMSE score was 26.34 ± 3.64 (median: 27; range: 2-30). Among the participants, 414 (13.3%) were classified as having cognitive impairment (MMSE score < 24), 296 (9.5%) were classified as mild cognitive impairment (MMSE: 19-23), 98 (3.2%) were classified as moderate cognitive impairment (MMSE: 10-18), and 20 (0.6%) were classified as severe cognitive impairment (MMSE < 10). Compared with the normal cognitive function group, the retinal venular average diameter was significantly larger (p = 0.013), and the retinal vascular fractal dimension and vascular density were significantly smaller (both p < 0.001) in the mild cognitive impairment group. The retinal arteriole-to-venular ratio (p = 0.003) and vascular fractal dimension (p = 0.033) were significantly decreased in the severe cognitive impairment group compared to the mild cognitive impairment group. In the multivariate analysis, better cognition (i.e., higher MMSE score) was significantly associated with higher retinal vascular fractal dimension (b = 0.134, p = 0.043) and higher retinal vascular density (b = 0.152, p = 0.023) after adjustment for age, best corrected visual acuity (BCVA) (logMAR) and education level. Discussion: In conclusion, our findings derived from an artificial intelligence-based fully automated retinal vascular parameter measurement method showed that several retinal vascular morphological parameters were correlated with cognitive impairment. The decrease in retinal vascular fractal dimension and decreased vascular density may serve as candidate biomarkers for early identification of cognitive impairment. The observed reduction in the retinal arteriole-to-venular ratio occurs in the late stages of cognitive impairment.

Vitreous Humor Biomarkers Reflect Pathological Changes in the Brain for Alzheimer's Disease and Chronic Traumatic Encephalopathy

BACKGROUND

Patients with eye disease have an increased risk for developing neurodegenerative disease. Neurodegenerative proteins can be measured in the eye; however, correlations between biomarker levels in eye fluid and neuropathological diagnoses have not been established.

OBJECTIVE

This exploratory, retrospective study examined vitreous humor from 41 postmortem eyes and brain tissue with neuropathological diagnoses of Alzheimer's disease (AD, n = 7), chronic traumatic encephalopathy (CTE, n = 15), both AD + CTE (n = 10), and without significant neuropathology (controls, n = 9).

METHODS

Protein biomarkers i.e., amyloid-β (Aβ 40,42), total tau (tTau), phosphorylated tau (pTau181,231), neurofilament light chain (NfL), and eotaxin-1 were quantitatively measured by immunoassay. Non-parametric tests were used to compare vitreous biomarker levels between groups. Spearman's rank correlation tests were used to correlate biomarker levels in vitreous and cortical tissue. The level of significance was set to α= 0.10.

RESULTS

In pairwise comparisons, tTau levels were significantly increased in AD and CTE groups versus controls (p = 0.08 for both) as well as AD versus AD+CTE group and CTE versus AD+CTE group (p = 0.049 for both). Vitreous NfL levels were significantly increased in low CTE (Stage I/II) versus no CTE (p = 0.096) and in low CTE versus high CTE stage (p = 0.03). Vitreous and cortical tissue levels of pTau 231 (p = 0.02, r = 0.38) and t-Tau (p = 0.04, r = -0.34) were significantly correlated.

CONCLUSION

The postmortem vitreous humor biomarker levels significantly correlate with AD and CTE pathology in corresponding brains, while vitreous NfL was correlated with the CTE staging. This exploratory study indicates that biomarkers in the vitreous humor may serve as a proxy for neuropathological disease.

Vitamin K and the Visual System-A Narrative Review

Vitamin K occupies a unique and often obscured place among its fellow fat-soluble vitamins. Evidence is mounting, however, that vitamin K (VK) may play an important role in the visual system apart from the hepatic carboxylation of hemostatic-related proteins. However, to our knowledge, no review covering the topic has appeared in the medical literature. Recent studies have confirmed that matrix Gla protein (MGP), a vitamin K-dependent protein (VKDP), is essential for the regulation of intraocular pressure in mice. The PREDIMED (Prevención con Dieta Mediterránea) study, a randomized trial involving 5860 adults at risk for cardiovascular disease, demonstrated a 29% reduction in the risk of cataract surgery in participants with the highest tertile of dietary vitamin K1 (PK) intake compared with those with the lowest tertile. However, the specific requirements of the eye and visual system (EVS) for VK, and what might constitute an optimized VK status, is currently unknown and largely unexplored. It is, therefore, the intention of this narrative review to provide an introduction concerning VK and the visual system, review ocular VK biology, and provide some historical context for recent discoveries. Potential opportunities and gaps in current research efforts will be touched upon in the hope of raising awareness and encouraging continued VK-related investigations in this important and highly specialized sensory system.

Childhood Social Isolation as a Predictor of Retinal Neuronal Thickness in Middle Age: A Lifecourse Birth Cohort Study

OBJECTIVE

We investigated whether childhood social isolation was associated with retinal neural layer changes in adulthood, and whether this association was independent of other childhood or adulthood risk factors, including adult social isolation.

METHODS

Participants were members of the Dunedin Multidisciplinary Health and Development Study, a longitudinal population-based birth cohort from Aotearoa New Zealand ( n = 1037), born 1972 to 1973 and followed until age 45 years, with 94% of the living cohort still participating. Social isolation was recorded prospectively at ages 5, 7, 9, and 11 years, from teacher and parent report. Retinal nerve fiber layer (RNFL) and ganglion cell-inner plexiform layer thicknesses were measured via optical coherence tomography at age 45 years.

RESULTS

Childhood social isolation was associated with thinner average RNFL ( B = -0.739, p = .02), nasal RNFL ( B = -1.118, p = .005), and inferior RNFL ( B = -1.524, p = .007), although only nasal RNFL remained significant after adjustment. These associations were not fully explained by other psychosocial or physical health risk factors in childhood or adulthood, nor were they mediated by adult loneliness or social support.

CONCLUSIONS

Childhood social isolation was an independent predictor of RNFL thickness in middle age. Highlighting prospective links between childhood psychosocial adversity and retinal neuronal measures will help to inform future research into the utility of retinal neuronal thickness as a biomarker for neurodegeneration.

Risk of Subsequent Dementia or Alzheimer Disease Among Patients With Age-Related Macular Degeneration: A Systematic Review and Meta-analysis

PURPOSE

Alzheimer disease (AD), a common form of dementia, shares several clinical and pathologic features with age-related macular degeneration (AMD). Epidemiologic reports on the association of AMD with subsequent dementia or AD are inconsistent.

DESIGN

Systematic review and meta-analysis.

METHODS

The Meta-analysis of Observational Studies in Epidemiology reporting guidelines were applied. The Newcastle-Ottawa Scale was used to evaluate the risk of bias in the included cohort studies that examined the association of AMD with subsequent dementia or AD. We estimated the pooled hazard ratios (HRs) of dementia or AD using random effects model meta-analysis and subgroup analysis on different follow-up periods, AMD subtype, gender, age, study design, and methods to ascertain dementia or AD.

RESULTS

A total of 8 223 581 participants were included in 8 studies published during 2000-2021. The meta-analysis showed that AMD was significantly associated with subsequent dementia (pooled HR 1.22, 95% CI 1.01-1.47) or AD (pooled HR 1.21, 95% CI 1.03-1.43). Our secondary analysis revealed that the association was more noticeable in dry AMD than wet AMD.

CONCLUSIONS

Patients with AMD have higher risks of developing dementia or AD, and therefore identifying related comorbidities and retinal biomarkers is much warranted for older adults with AMD in ophthalmologic practice.

The correlation of retinal neurodegeneration and brain degeneration in patients with Alzheimer's disease using optical coherence tomography angiography and MRI

Introduction

Pathological changes in Alzheimer's disease can cause retina and optic nerve degeneration. The retinal changes are correlated with cognitive function. This study aimed to explore the relationship of retinal differences with neuroimaging in patients with Alzheimer's disease, analyze the association of cognitive function with retinal structure and vascular density, and identify potential additional biomarkers for early diagnosis of Alzheimer's disease.

Method

We performed magnetic resonance imaging (MRI) scans and neuropsychological assessments in 28 patients with mild Alzheimer's disease and 28 healthy controls. Retinal structure and vascular density were evaluated by optical coherence tomography angiography (OCTA). Furthermore, we analyzed the correlation between neuroimaging and OCTA parameters in patients with mild Alzheimer's disease with adjustment for age, gender, years of education, and hypertension.

Results

In patients with mild Alzheimer's disease, OCTA-detected retinal parameters were not significantly correlated with MRI-detected neuroimaging parameters after Bonferroni correction for multiple testing. Under multivariable analysis controlled for age, gender, years of education, and hypertension, the S-Hemi (0-3) sector of macular thickness was significantly associated with Mini-cog (β = 0.583, P = 0.002) with Bonferroni-corrected threshold at P < 0.003.

Conclusion

Our findings suggested decreased macular thickness might be associated with cognitive function in mild AD patients. However, the differences in retinal parameters didn't correspond to MRI-detected parameters in this study. Whether OCTA can be used as a new detection method mirroring MRI for evaluating the effect of neuronal degeneration in patients with mild Alzheimer's disease still needs to be investigated by more rigorous and larger studies in the future.

Application of Structural Retinal Biomarkers to Detect Cognitive Impairment in a Primary Care Setting

Background

Despite the diagnostic accuracy of advanced neurodiagnostic procedures, the detection of Alzheimer's disease (AD) remains poor in primary care. There is an urgent need for screening tools to aid in the detection of early AD.

Objective

This study examines the predictive ability of structural retinal biomarkers in detecting cognitive impairment in a primary care setting.

Methods

Participants were recruited from Alzheimer's Disease in Primary Care (ADPC) study. As part of the ADPC Retinal Biomarker Study (ADPC RBS), visual acuity, an ocular history questionnaire, eye pressure, optical coherence tomography (OCT) imaging, and fundus imaging was performed.

Results

Data were examined on n = 91 participants. The top biomarkers for predicting cognitive impairment included the inferior quadrant of the outer retinal layers, all four quadrants of the peripapillary retinal nerve fiber layer, and the inferior quadrant of the macular retinal nerve fiber layer.

Conclusion

The current data provides strong support for continued investigation into structural retinal biomarkers, particularly the retinal nerve fiber layer, as screening tools for AD.

Retinal Examinations Provides Early Warning of Alzheimer's Disease

Patients with Alzheimer's disease have difficulty maintaining independent living abilities as the disease progresses, causing an increased burden of care on family caregivers and the healthcare system and related financial strain. This patient group is expected to continue to expand as life expectancy climbs. Current diagnostics for Alzheimer's disease are complex, unaffordable, and invasive without regard to diagnosis quality at early stages, which urgently calls for more technical improvements for diagnosis specificity. Optical coherence tomography or tomographic angiography has been shown to identify retinal thickness loss and lower vascular density present earlier than symptom onset in these patients. The retina is an extension of the central nervous system and shares anatomic and functional similarities with the brain. Ophthalmological examinations can be an efficient tool to offer a window into cerebral pathology with the merit of easy operation. In this review, we summarized the latest observations on retinal pathology in Alzheimer's disease and discussed the feasibility of retinal imaging in diagnostic prediction, as well as limitations in current retinal examinations for Alzheimer's disease diagnosis.

Correlation between retinal vessel rarefaction and psychometric measures in an older Southern Italian population

Objective

To explore the linear association between inner retinal layers thickness and macular capillary density compared to variations of global cognition evaluated by psychometric measures in a cohort of Mediterranean subjects aged 65+ years.

Materials and methods

We performed a cross-sectional analysis of 574 participants aged 65 years+ drawn from a population-based Southern Italian study. All subjects underwent neurological evaluations, including global cognitive screening, the Mini-Mental State Examination (MMSE) and frontal assessment battery (FAB), together with an ophthalmic examination including optical coherence tomography (OCT) and OCT-Angiography. We assessed the average thickness of the ganglion cell complex (GCC) and the retinal nerve fiber layer (RNFL), the foveal avascular zone area, and vascular density (VD) of superficial (SVD) and deep (DVD) capillary plexi at the foveal and parafoveal area. Linear regression was applied to assess associations of ocular measurements with MMSE and FAB scores.

Results

In the linear regression model, foveal DVD (beta = 0.01, 95% CI:0.004–0.052), whole DVD (beta = 0.04, 95% CI:0.02–0.08), and whole SVD (beta = 0.04, 95% CI:0.02–0.07) showed a positive association with MMSE. In addition, foveal SVD (beta = 0.01, 95% CI:0.003–0.05) and whole SVD (beta = 0.03, 95% CI:0.004–0.08) were positively associated with the FAB score. We found no further significant association between the MMSE score or the FAB score and the average thickness of the GCC and RNFL, and FAZ area.

Conclusion

A direct linear association between the VD of the macular capillary plexi with global and frontal cognitive functions was observed in elderly subjects.

Advances in Optical Coherence Tomography Imaging Technology and Techniques for Choroidal and Retinal Disorders

Optical coherence tomography (OCT) imaging has played a pivotal role in the field of retina. This light-based, non-invasive imaging modality provides high-quality, cross-sectional analysis of the retina and has revolutionized the diagnosis and management of retinal and choroidal diseases. Since its introduction in the early 1990s, OCT technology has continued to advance to provide quicker acquisition times and higher resolution. In this manuscript, we discuss some of the most recent advances in OCT technology and techniques for choroidal and retinal diseases. The emerging innovations discussed include wide-field OCT, adaptive optics OCT, polarization sensitive OCT, full-field OCT, hand-held OCT, intraoperative OCT, at-home OCT, and more. The applications of these rising OCT systems and techniques will allow for a closer monitoring of chorioretinal diseases and treatment response, more robust analysis in basic science research, and further insights into surgical management. In addition, these innovations to optimize visualization of the choroid and retina offer a promising future for advancing our understanding of the pathophysiology of chorioretinal diseases.

A lightweight deep learning model for automatic segmentation and analysis of ophthalmic images

Detection, diagnosis, and treatment of ophthalmic diseases depend on extraction of information (features and/or their dimensions) from the images. Deep learning (DL) model are crucial for the automation of it. Here, we report on the development of a lightweight DL model, which can precisely segment/detect the required features automatically. The model utilizes dimensionality reduction of image to extract important features, and channel contraction to allow only the required high-level features necessary for reconstruction of segmented feature image. Performance of present model in detection of glaucoma from optical coherence tomography angiography (OCTA) images of retina is high (area under the receiver-operator characteristic curve AUC ~ 0.81). Bland–Altman analysis gave exceptionally low bias (~ 0.00185), and high Pearson’s correlation coefficient (p = 0.9969) between the parameters determined from manual and DL based segmentation. On the same dataset, bias is an order of magnitude higher (~ 0.0694, p = 0.8534) for commercial software. Present model is 10 times lighter than Unet (popular for biomedical image segmentation) and have a better segmentation accuracy and model training reproducibility (based on the analysis of 3670 OCTA images). High dice similarity coefficient (D) for variety of ophthalmic images suggested it’s wider scope in precise segmentation of images even from other fields. Our concept of channel narrowing is not only important for the segmentation problems, but it can also reduce number of parameters significantly in object classification models. Enhanced disease diagnostic accuracy can be achieved for the resource limited devices (such as mobile phone, Nvidia’s Jetson, Raspberry pi) used in self-monitoring, and tele-screening (memory size of trained model ~ 35 MB).

The electroretinogram b-wave amplitude: a differential physiological measure for Attention Deficit Hyperactivity Disorder and Autism Spectrum Disorder

Background

Attention Deficit Hyperactivity Disorder (ADHD) is the most prevalent childhood neurodevelopmental disorder. It shares some genetic risk with Autism Spectrum Disorder (ASD), and the conditions often occur together. Both are potentially associated with abnormal glutamate and GABA neurotransmission, which can be modelled by measuring the synaptic activity in the retina with an electroretinogram (ERG). Reduction of retinal responses in ASD has been reported, but little is known about retinal activity in ADHD. In this study, we compared the light-adapted ERGs of individuals with ADHD, ASD and controls to investigate whether retinal responses differ between these neurodevelopmental conditions.

Methods

Full field light-adapted ERGs were recorded from 15 ADHD, 57 ASD (without ADHD) and 59 control participants, aged from 5.4 to 27.3 years old. A Troland protocol was used with a random series of nine flash strengths from −0.367 to 1.204 log photopic cd.s.m⁻². The time-to-peak and amplitude of the a- and b-waves and the parameters of the Photopic Negative Response (PhNR) were compared amongst the three groups of participants, using generalised estimating equations.

Results

Statistically significant elevations of the ERG b-wave amplitudes, PhNR responses and faster timings of the b-wave time-to-peak were found in those with ADHD compared with both the control and ASD groups. The greatest elevation in the b-wave amplitudes associated with ADHD were observed at 1.204 log phot cd.s.m⁻² flash strength (p < .0001), at which the b-wave amplitude in ASD was significantly lower than that in the controls. Using this measure, ADHD could be distinguished from ASD with an area under the curve of 0.88.

Conclusions

The ERG b-wave amplitude appears to be a distinctive differential feature for both ADHD and ASD, which produced a reversed pattern of b-wave responses. These findings imply imbalances between glutamate and GABA neurotransmission which primarily regulate the b-wave formation. Abnormalities in the b-wave amplitude could provisionally serve as a biomarker for both neurodevelopmental conditions.

Supplementary Information

The online version contains supplementary material available at 10.1186/s11689-022-09440-2.

Biomarkers for Alzheimer's Disease in the Current State: A Narrative Review

Alzheimer’s disease (AD) has become a problem, owing to its high prevalence in an aging society with no treatment available after onset. However, early diagnosis is essential for preventive intervention to delay disease onset due to its slow progression. The current AD diagnostic methods are typically invasive and expensive, limiting their potential for widespread use. Thus, the development of biomarkers in available biofluids, such as blood, urine, and saliva, which enables low or non-invasive, reasonable, and objective evaluation of AD status, is an urgent task. Here, we reviewed studies that examined biomarker candidates for the early detection of AD. Some of the candidates showed potential biomarkers, but further validation studies are needed. We also reviewed studies for non-invasive biomarkers of AD. Given the complexity of the AD continuum, multiple biomarkers with machine-learning-classification methods have been recently used to enhance diagnostic accuracy and characterize individual AD phenotypes. Artificial intelligence and new body fluid-based biomarkers, in combination with other risk factors, will provide a novel solution that may revolutionize the early diagnosis of AD.

Fluid Biomarkers in Alzheimer’s Disease and Other Neurodegenerative Disorders: Toward Integrative Diagnostic Frameworks and Tailored Treatments

The diagnosis of neurodegenerative diseases (NDDs) represents an increasing social burden, with the unsolved issue of disease-modifying therapies (DMTs). The failure of clinical trials treating Alzheimer′s Disease (AD) so far highlighted the need for a different approach in drug design and patient selection. Identifying subjects in the prodromal or early symptomatic phase is critical to slow down neurodegeneration, but the implementation of screening programs with this aim will have an ethical and social aftermath. Novel minimally invasive candidate biomarkers (derived from blood, saliva, olfactory brush) or classical cerebrospinal fluid (CSF) biomarkers have been developed in research settings to stratify patients with NDDs. Misfolded protein accumulation, neuroinflammation, and synaptic loss are the pathophysiological hallmarks detected by these biomarkers to refine diagnosis, prognosis, and target engagement of drugs in clinical trials. We reviewed fluid biomarkers of NDDs, considering their potential role as screening, diagnostic, or prognostic tool, and their present-day use in clinical trials (phase II and III). A special focus will be dedicated to novel techniques for the detection of misfolded proteins. Eventually, an applicative diagnostic algorithm will be proposed to translate the research data in clinical practice and select prodromal or early patients to be enrolled in the appropriate DMTs trials for NDDs.

Towards standardizing retinal optical coherence tomography angiography: a review

The visualization and assessment of retinal microvasculature are important in the study, diagnosis, monitoring, and guidance of treatment of ocular and systemic diseases. With the introduction of optical coherence tomography angiography (OCTA), it has become possible to visualize the retinal microvasculature volumetrically and without a contrast agent. Many lab-based and commercial clinical instruments, imaging protocols and data analysis methods and metrics, have been applied, often inconsistently, resulting in a confusing picture that represents a major barrier to progress in applying OCTA to reduce the burden of disease. Open data and software sharing, and cross-comparison and pooling of data from different studies are rare. These inabilities have impeded building the large databases of annotated OCTA images of healthy and diseased retinas that are necessary to study and define characteristics of specific conditions. This paper addresses the steps needed to standardize OCTA imaging of the human retina to address these limitations. Through review of the OCTA literature, we identify issues and inconsistencies and propose minimum standards for imaging protocols, data analysis methods, metrics, reporting of findings, and clinical practice and, where this is not possible, we identify areas that require further investigation. We hope that this paper will encourage the unification of imaging protocols in OCTA, promote transparency in the process of data collection, analysis, and reporting, and facilitate increasing the impact of OCTA on retinal healthcare delivery and life science investigations.

Hearing Loss and Cognition: What We Know and Where We Need to Go

Although a causal association remains to be determined, epidemiologic evidence suggests an association between hearing loss and increased risk of dementia. If we determine the association is causal, opportunity for targeted intervention for hearing loss may play a fundamental role in dementia prevention. In this discussion, we summarize current research on the association between hearing loss and dementia and review potential casual mechanisms behind the association (e.g., sensory-deprivation hypothesis, information-degradation hypothesis, common cause). We emphasize key areas of research which might best inform our investigation of this potential casual association. These selected research priorities include examination of the causal mechanism, measurement of co-existing hearing loss and cognitive impairment and determination of any bias in testing, potential for managing hearing loss for prevention of dementia and cognitive decline, or the potential to reduce dementia-related symptoms through the management of hearing loss. Addressing these research gaps and how results are then translated for clinical use may prove paramount for dementia prevention, management, and overall health of older adults.

Subcortical and Cerebellar Neural Correlates of Prodromal Alzheimer’s Disease with Prolonged Sleep Latency

Background: Despite the important associations among sleep, Alzheimer’s disease (AD), subcortical structures, and the cerebellum, structural and functional magnetic resonance imaging (MRI) with regard to these regions and sleep on patients in AD trajectory are scarce. Objective: This study aimed to evaluate the influence of prolonged sleep latency on the structural and functional alterations in the subcortical and cerebellar neural correlates in amyloid-β positive amnestic mild cognitive impairment patients (Aβ+aMCI). Methods: A total of 60 patients with aMCI who were identified as amyloid positive ([18F] flutemetamol+) were recruited in the study, 24 patients with normal sleep latency (aMCI-n) and 36 patients prolonged sleep latency (aMCI-p). Cortical thickness and volumes between the two groups were compared. Volumetric analyses were implemented on the brainstem, thalamus, and hippocampus. Subcortical and cerebellar resting state functional connectivity (FC) differences were measured between the both groups through seed-to-voxel analysis. Additionally, group x Aβ interactive effects on FC values were tested with a general linear model. Result: There was a significantly decreased brainstem volume in aMCI-p subjects. We observed a significant reduction of the locus coeruleus (LC) FC with frontal, temporal, insular cortices, hippocampus, and left thalamic FC with occipital cortex. Moreover, the LC FC with occipital cortex and left hippocampal FC with frontal cortex were increased in aMCI-p subjects. In addition, there was a statistically significant group by regional standardized uptake value ratio interactions discovered in cerebro-cerebellar networks. Conclusion: The aforementioned findings suggest that prolonged sleep latency may be a detrimental factor in compromising structural and functional correlates of subcortical structures and the cerebellum, which may accelerate AD pathophysiology.

Deficits in color detection in patients with Alzheimer disease

Deficits in color vision and related retinal changes hold promise as early screening biomarkers in patients with Alzheimer’s disease. This study aimed to determine a cut-off score that can screen for Alzheimer’s dementia using a novel color vision threshold test named the red, green, and blue (RGB) modified color vision plate test (RGB-vision plate). We developed the RGB-vision plate consisting of 30 plates in which the red and green hues of Ishihara Plate No.22 were sequentially adjusted. A total of 108 older people participated in the mini-mental state examination (MMSE), Ishihara plate, and RGB-vision plate. For the analyses, the participants were divided into two groups: Alzheimer’s dementia (n = 42) and healthy controls (n = 38). K-means cluster analysis and ROC curve analysis were performed to identify the most appropriate cut-off score. As a result, the cut-off screening score for Alzheimer’s dementia on the RGB-vision plate was set at 25, with an area under the curve of 0.773 (p<0.001). Moreover, there was a negative correlation between the RGB-vision plate thresholds and MMSE scores (r = -0.36, p = 0.02). In conclusion, patients with Alzheimer’s dementia had a deficit in color vision. The RGB-vision plate is a potential early biomarker that may adequately detect Alzheimer’s dementia.

Enhanced medical diagnosis for dOCTors: a perspective of optical coherence tomography

SIGNIFICANCE

After three decades, more than 75,000 publications, tens of companies being involved in its commercialization, and a global market perspective of about USD 1.5 billion in 2023, optical coherence tomography (OCT) has become one of the fastest successfully translated imaging techniques with substantial clinical and economic impacts and acceptance.

AIM

Our perspective focuses on disruptive forward-looking innovations and key technologies to further boost OCT performance and therefore enable significantly enhanced medical diagnosis.

APPROACH

A comprehensive review of state-of-the-art accomplishments in OCT has been performed.

RESULTS

The most disruptive future OCT innovations include imaging resolution and speed (single-beam raster scanning versus parallelization) improvement, new implementations for dual modality or even multimodality systems, and using endogenous or exogenous contrast in these hybrid OCT systems targeting molecular and metabolic imaging. Aside from OCT angiography, no other functional or contrast enhancing OCT extension has accomplished comparable clinical and commercial impacts. Some more recently developed extensions, e.g., optical coherence elastography, dynamic contrast OCT, optoretinography, and artificial intelligence enhanced OCT are also considered with high potential for the future. In addition, OCT miniaturization for portable, compact, handheld, and/or cost-effective capsule-based OCT applications, home-OCT, and self-OCT systems based on micro-optic assemblies or photonic integrated circuits will revolutionize new applications and availability in the near future. Finally, clinical translation of OCT including medical device regulatory challenges will continue to be absolutely essential.

CONCLUSIONS

With its exquisite non-invasive, micrometer resolution depth sectioning capability, OCT has especially revolutionized ophthalmic diagnosis and hence is the fastest adopted imaging technology in the history of ophthalmology. Nonetheless, OCT has not been completely exploited and has substantial growth potential-in academics as well as in industry. This applies not only to the ophthalmic application field, but also especially to the original motivation of OCT to enable optical biopsy, i.e., the in situ imaging of tissue microstructure with a resolution approaching that of histology but without the need for tissue excision.

Sensing Using Light: A Key Area of Sensors

This invited featured paper offers a Doctrinal Conception of sensing using Light (SuL) as an "umbrella" in which any sensing approach using Light Sciences and Technologies can be easily included. The key requirements of a sensing system will be quickly introduced by using a bottom-up methodology. Thanks to this, it will be possible to get a general conception of a sensor using Light techniques and know some related issues, such as its main constituted parts and types. The case in which smartness is conferred to the device is also considered. A quick "flight" over 10 significant cases using different principles, techniques, and technologies to detect diverse measurands in various sector applications is offered to illustrate this general concept. After reading this paper, any sensing approach using Light Sciences and Technologies may be easily included under the umbrella: sensing using Light or photonic sensors (PS).

Glaucoma Is Not Associated With Alzheimer's Disease or Dementia: A Meta-Analysis of Cohort Studies

Background: Previous studies evaluating the relationships of glaucoma with Alzheimer's disease (AD) and dementia showed inconsistent results. We performed a meta-analysis of cohort studies to evaluate the association between glaucoma with incidence of AD, all-cause dementia, and non-AD dementia. Methods: Cohort studies which evaluated the association between glaucoma with incidence of AD, all-cause dementia, and non-AD dementia in adult population with multivariate analyses were identified by systematic search of PubMed, Embase, and Cochrane's Library databases. A random-effects model incorporating the potential intra-study heterogeneity was used for the meta-analysis. Results: Eleven cohort studies including 4,645,925 participants were included. Results showed that compared to those without glaucoma at baseline, adult patients with glaucoma was not independently associated with increased incidence of AD [adjusted risk ratio (RR): 1.03, 95% confidence interval (CI): 0.93-1.05, P = 0.55; I ² = 83%], all-cause dementia (adjusted RR: 1.08, 95% CI: 0.97-1.19, P = 0.15; I ² = 79%), or non-AD dementia (adjusted RR: 1.05 95% CI: 0.91-1.21, P = 0.49; I ² = 82%). Sensitivity analyses by excluding one study at a time did not significantly affect the results of the meta-analyses. Moreover, subgroup analyses showed consistent results in meta-analysis of prospective or retrospective cohort studies, and in meta-analysis of patients with primary open-angle glaucoma or primary angle-closure glaucoma (P-values for subgroup difference all > 0.05). Conclusions: Current evidence from cohort studies did not support that glaucoma is an independent risk factor of AD, all-cause dementia, or non-AD dementia in adult population.

Detection of retinal changes with optical coherence tomography angiography in mild cognitive impairment and Alzheimer's disease patients: A meta-analysis

Objective

To assess retinal microvascular network impairments in the eyes of mild cognitive impairment (MCI) and Alzheimer’s disease (AD) patients with optical coherence tomography angiography (OCTA).

Design

Systematic review and meta-analysis.

Methods

A literature search was conducted in the PubMed and EMBASE databases to identify relevant studies detecting retinal microvascular attenuation among AD, MCI patients and cognitively healthy controls (HCs) by OCTA. Data were extracted by Review Manager V.5.4 and Stata V.14.0.

Results

Eight investigations were included in this meta-analysis, with 150 AD patients, 195 MCI patients and 226 HCs were eligible for meta-analysis. Evidence based on these studies demonstrated that there was a significantly decreased vessel density (VD) of the Optovue group in superficial capillary plexus (SCP): WMD = -2.26, 95% CI: -3.98 to -0.55, p = 0.01; in deep capillary plexus (DCP): WMD = -3.40, 95% CI: -5.99 to -0.81, p = 0.01, VD of the Zeiss group in SCP:WMD = -0.91, 95% CI: -1.79 to -0.02, p = 0.05 and an enlarged fovea avascular zone (FAZ):WMD = 0.06, 95% CI: 0.01 to 0.11, P = 0.02 in OCTA measurements of MCI patients. Additionally, in OCTA measurements of AD patients, there was a significantly decreased VD in the SCP: WMD = -1.88, 95% CI: -2.7 to -1.07, p<0.00001. In contrast, there was no significant decrease in DCP nor enlargement of FAZ in AD patients.

Conclusion

Retinal microvascular alternations could be optimally screened in MCI patients detected by OCTA, which could be a warning sign of relative changes in the MCI before progressing to AD. Retinal microvasculature changes worth further investigation in larger scale clinical trials.

Homocysteine and Age-Related Central Nervous System Diseases: Role of Inflammation

Hyperhomocysteinemia (HHcy) is remarkably common among the aging population. The relation between HHcy and the development of neurodegenerative diseases, such as Alzheimer's disease (AD) and eye diseases, and age-related macular degeneration (AMD) and diabetic retinopathy (DR) in elderly people, has been established. Disruption of the blood barrier function of the brain and retina is one of the most important underlying mechanisms associated with HHcy-induced neurodegenerative and retinal disorders. Impairment of the barrier function triggers inflammatory events that worsen disease pathology. Studies have shown that AD patients also suffer from visual impairments. As an extension of the central nervous system, the retina has been suggested as a prominent site of AD pathology. This review highlights inflammation as a possible underlying mechanism of HHcy-induced barrier dysfunction and neurovascular injury in aging diseases accompanied by HHcy, focusing on AD.

Retinal Imaging Techniques Based on Machine Learning Models in Recognition and Prediction of Mild Cognitive Impairment

BACKGROUND AND PURPOSE

Mild Cognitive Impairment (MCI) is thought to be the signal of many progressive diseases but is easily ignored. Therefore, a simple and easy screening method for recognizing and predicting MCI is urgently needed. The study aimed to establish machine learning models of retinal vascular features to categorize and predict MCI.

PATIENTS AND METHODS

Subjects enrolled underwent cognitive function assessment and were divided into a normal group, an MCI group, and a dementia group, and fundus photography was performed. MATLAB 2019b was used for fundus image preprocessing and vascular segmentation. Via the Green channel, adaptive histogram equalization (AHE), image binarization, and median filtering, we obtained the original and segmentation retinal vessel images. Afterwards, the histogram of oriented gradient (HOG) was used for image feature extraction. Support vector machine (SVM) and extreme learning machine (ELM) were selected for training models in the fundus original images and fundus vascular segmentation images, respectively. Among the three cognitive groups, sensitivity, specificity, the receiver operating characteristic (ROC) curves, and the area under the curve (AUC) were used to evaluate and compare the predictive performance of the two models in the fundus original and vascular segmentation images, respectively.

RESULTS

A total of 86 eligible subjects were enrolled in the study. After a clinical cognitive assessment, the participants were divided into the normal group (N = 38), the MCI group (N = 26), and the dementia group (N = 22). A total of 332 qualified fundus images were adopted after screening. Comparing the models among the three groups showed that the SVM model had more advantages than the ELM model in the fundus original images and vascular segmentation images. Meanwhile, we found that the original images performed better than the segmentation images in the same prediction model. Among the three groups, the SVM model of the fundus original images had the best performance.

CONCLUSION

The establishment of a predictive model based on vascular-related feature extraction from fundus images has high recognition and prediction abilities for cognitive function and can be used as a screening method for MCI.

CLINICAL TRIAL REGISTRATION

ChiCTR.org.cn (ChiCTR1900027404), Registered on Nov 12, 2019.