Retinal vascular fractal dimension and cerebral blood flow, a pilot study

Association of fractal dimension and other retinal vascular network parameters with cognitive performance and neuroimaging biomarkers: The Multi-Ethnic Study of Atherosclerosis (MESA)

INTRODUCTION

Retinal vascular network changes may reflect the integrity of the cerebral microcirculation, and may be associated with cognitive impairment.

METHODS

Associations of retinal vascular measures with cognitive function and MRI biomarkers were examined amongst Multi-Ethnic Study of Atherosclerosis (MESA) participants in North Carolina who had gradable retinal photographs at Exams 2 (2002 to 2004, n = 313) and 5 (2010 to 2012, n = 306), and detailed cognitive testing and MRI at Exam 6 (2016 to 2018).

RESULTS

After adjustment for covariates and multiple comparisons, greater arteriolar fractal dimension (FD) at Exam 2 was associated with less isotropic free water of gray matter regions (β = -0.0005, SE = 0.0024, p = 0.01) at Exam 6, while greater arteriolar FD at Exam 5 was associated with greater gray matter cortical volume (in mm3 , β = 5458, SE = 20.17, p = 0.04) at Exam 6.

CONCLUSION

Greater arteriolar FD, reflecting greater complexity of the branching pattern of the retinal arteries, is associated with MRI biomarkers indicative of less neuroinflammation and neurodegeneration.

Ocular biomarkers of cognitive decline based on deep-learning retinal vessel segmentation

BACKGROUND

The current literature shows a strong relationship between retinal neuronal and vascular alterations in dementia. The purpose of the study was to use NFN+ deep learning models to analyze retinal vessel characteristics for cognitive impairment (CI) recognition.

METHODS

We included 908 participants from a community-based cohort followed for over 15 years (the prospective KaiLuan Study) who underwent brain magnetic resonance imaging (MRI) and fundus photography between 2021 and 2022. The cohort consisted of both cognitively healthy individuals (N = 417) and those with cognitive impairment (N = 491). We employed the NFN+ deep learning framework for retinal vessel segmentation and measurement. Associations between Retinal microvascular parameters (RMPs: central retinal arteriolar / venular equivalents, arteriole to venular ratio, fractal dimension) and CI were assessed by Pearson correlation. P < 0.05 was considered statistically significant. The correlation between the CI and RMPs were explored, then the correlation coefficients between CI and RMPs were analyzed. Random Forest nonlinear classification model was used to predict whether one having cognitive decline or not. The assessment criterion was the AUC value derived from the working characteristic curve.

RESULTS

The fractal dimension (FD) and global vein width were significantly correlated with the CI (P < 0.05). Age (0.193), BMI (0.154), global vein width (0.106), retinal vessel FD (0.099), and CRAE (0.098) were the variables in this model that were ranked in order of feature importance. The AUC values of the model were 0.799.

CONCLUSIONS

Establishment of a predictive model based on the extraction of vascular features from fundus images has a high recognizability and predictive power for cognitive function and can be used as a screening method for CI.

Fractal Analysis of the Cerebrovascular System Pathophysiology

The cerebrovascular system is characterized by parameters such as arterial blood pressure (ABP), cerebral perfusion pressure (CPP), and cerebral blood flow velocity (CBFV). These are regulated by interconnected feedback loops resulting in a fluctuating and complex time course. They exhibit fractal characteristics such as (statistical) self-similarity and scale invariance which could be quantified by fractal measures. These include the coefficient of variation, the Hurst coefficient H, or the spectral exponent α in the time domain, as well as the spectral index ß in the frequency domain. Prior to quantification, the time series has to be classified as either stationary or nonstationary, which determines the appropriate fractal analysis and measure for a given signal class. CBFV was characterized as a nonstationary (fractal Brownian motion) signal with spectral index ß between 2.0 and 2.3. In the high-frequency range (>0.15 Hz), CBFV variability is mainly determined by the periodic ABP variability induced by heartbeat and respiration. However, most of the spectral power of CBFV is contained in the low-frequency range (<0.15 Hz), where cerebral autoregulation acts as a low-pass filter and where the fractal properties are found. Cerebral vasospasm, which is a complication of subarachnoid hemorrhage (SAH), is associated with an increase in ß denoting a less complex time course. A reduced fractal dimension of the retinal microvasculature has been observed in neurodegenerative disease and in stroke. According to the decomplexification theory of illness, such a diminished complexity could be explained by a restriction or even dropout of feedback loops caused by disease.

Automated Retinal Vessel Analysis Based on Fundus Photographs as a Predictor for Non-Ophthalmic Diseases-Evolution and Perspectives

The study of retinal vessels in relation to cardiovascular risk has a long history. The advent of a dedicated tool based on digital imaging, i.e., the retinal vessel analyzer, and also other software such as Integrative Vessel Analysis (IVAN), Singapore I Vessel Assessment (SIVA), and Vascular Assessment and Measurement Platform for Images of the Retina (VAMPIRE), has led to the accumulation of a formidable body of evidence regarding the prognostic value of retinal vessel analysis (RVA) for cardiovascular and cerebrovascular disease (including arterial hypertension in children). There is also the potential to monitor the response of retinal vessels to therapies such as physical activity or bariatric surgery. The dynamic vessel analyzer (DVA) remains a unique way of studying neurovascular coupling, helping to understand the pathogenesis of cerebrovascular and neurodegenerative conditions and also being complementary to techniques that measure macrovascular dysfunction. Beyond cardiovascular disease, retinal vessel analysis has shown associations with and prognostic value for neurological conditions, inflammation, kidney function, and respiratory disease. Artificial intelligence (AI) (represented by algorithms such as QUantitative Analysis of Retinal vessel Topology and siZe (QUARTZ), SIVA-DLS (SIVA-deep learning system), and many others) seems efficient in extracting information from fundus photographs, providing prognoses of various general conditions with unprecedented predictive value. The future challenges will be integrating RVA and other qualitative and quantitative risk factors in a unique, comprehensive prediction tool, certainly powered by AI, while building the much-needed acceptance for such an approach inside the medical community and reducing the "black box" effect, possibly by means of saliency maps.

White matter microstructural integrity is associated with retinal vascular caliber in adolescents with bipolar disorder

OBJECTIVE

Reduced white matter integrity is observed in bipolar disorder (BD), and is associated with cardiovascular risk in adults. This topic is underexplored in youth, and in BD, where novel microvascular measures may help to inform understanding of the vascular-brain connection. We therefore examined the association of retinal vascular caliber with white matter integrity in a cross-sectional sample of adolescents with and without BD.

METHODS

Eighty-four adolescents (n = 42 BD, n = 42 controls) completed retinal imaging, yielding arteriolar and venular caliber. Diffusion tensor imaging measured white matter fractional anisotropy (FA). Multiple linear regression tested associations between retinal vascular caliber and FA in regions-of-interest; corpus callosum, anterior thalamic radiation, uncinate fasciculus, and superior longitudinal fasciculus. Complementary voxel-wise analyses were performed.

RESULTS

Arteriolar caliber was elevated in adolescents with BD relative to controls (F(1,79) = 6.15, p = 0.02, η2p = 0.07). In the overall sample, higher venular caliber was significantly associated with lower corpus callosum FA (β = -0.24, puncorrected = 0.04). In voxel-wise analyses, higher arteriolar caliber was significantly associated with lower corpus callosum and forceps minor FA in the overall sample (β = -0.46, p = 0.03). A significant diagnosis-by-venular caliber interaction on FA was noted in 5 clusters including the right retrolenticular internal capsule (β = 0.72, p = 0.03), corticospinal tract (β = 0.72, p = 0.04), and anterior corona radiata (β = 0.63, p = 0.04). In each instance, venular caliber was more positively associated with FA in BD vs. controls.

CONCLUSION

Retinal microvascular measures are associated with white matter integrity in BD, particularly in the corpus callosum. This study was proof-of-concept, designed to guide future studies focused on the vascular-brain interface in BD.

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.

Fractal analysis of healthy and diseased vasculature in pediatric Moyamoya disease

BACKGROUND AND PURPOSE

Fractal dimension is an objective metric for the notion of structural complexity. We sought to investigate differences in structural complexity between healthy and affected territories of cerebral vasculature in moyamoya, as well as associated scalp vasculature and native transdural collaterals in patients with moyamoya by comparing their respective fractal dimensions.

METHODS

Our cohort consisted of 15 transdural collaterals from 12 patients with unilateral anterior circulation moyamoya. Frames of distal arterial vasculature from internal and external carotid angiograms were selected then automatically segmented and also manually annotated by a cerebrovascular surgeon. In the affected hemisphere, the region with transdural collateral supply was compared to the contralateral region. The resulting skeletonized angiograms were analyzed for their fractal dimensions.

RESULTS

We found the average fractal dimension (Df) of the moyamoya-side ICA was 1.82 with slightly different means for the anteroposterial (AP) and lateral views (mean  =  1.82; mean  =  1.81). The overall mean for healthy cerebral vasculature was also found to be 1.82 (AP: mean  =  1.83; lateral: mean  =  1.81). Mean Df of native transdural collaterals was found to be 1.82 (AP: mean  =  1.83; lateral: mean  =  1.81). The mean Df difference between autosegmented and manually segmented images was 0.013.

CONCLUSION

In accordance with the clinical understanding of moyamoya disease, the distal arterial structural complexity is not affected in moyamoya, and is maintained by transdural collaterals formed by vasculogenesis. Autosegmentation of cerebral vasculature is also shown to be accurate when compared to manual segmentation.

Optic disc and retinal vascular features in first 6 years of Chinese children

Purpose

Retinal microvasculature plays an important role in children's fundus lesions and even in their later life. However, little was known on the features of normal retina in early life. The purpose of this study was to explore the normal retinal features in the first 6 years of life and provide information for future research.

Methods

Children, aged from birth to 6 years old and diagnosed with various unilateral ocular diseases were included. Venous phase fundus fluorescein angiography images with the optic disc at the center were collected. Based on the ResUNet convolutional neural network, optic disc and retinal vascular features in the posterior retina were computed automatically.

Results

A total of 146 normal eyes of 146 children were included. Among different age groups, no changes were shown in the optic disc diameter (y = -0.00002x + 1.362, R² = 0.025, p = 0.058). Retinal vessel density and fractal dimension are linearly and strongly correlated (r = 0.979, p < 0.001). Older children had smaller value of fractal dimension (y = -0.000026x + 1.549, R²= 0.075, p = 0.001) and narrower vascular caliber if they were less than 3 years old (y = -0.008x + 84.861, R²= 0.205, p < 0.001). No differences were in the density (y = -0.000007x + 0.134, R²= 0.023, p = 0.067) and the curvature of retinal vessels (lnC = -0.00001x - 4.657, R²= 0.001, p = 0.667).

Conclusions

Age and gender did not impact the optic disc diameter, vessel density, and vessel curvature significantly in this group of children. Trends of decreased vessel caliber in the first 3 years of life and decreased vessel complexity with age were observed. The structural characteristics provide information for future research to better understand the developmental origin of the healthy and diseased retina.

Neurovascular correlates of retinal microvascular caliber in adolescent bipolar disorder

BACKGROUND

The connection between vascular and brain metrics is well-studied in older adults, but neglected in youth and in psychiatric populations at increased cardiovascular risk. We therefore examined the association of retinal vascular caliber with cerebral blood flow (CBF) in adolescents with and without bipolar disorder (BD).

METHODS

Ninety-four adolescents (n = 48 BD, n = 46 controls) completed retinal fundus imaging, yielding estimates of arteriolar and venular diameter. Arterial spin labelling MRI was performed to measure CBF. We tested for associations between retinal vascular caliber and CBF in regions of interest; anterior cingulate cortex (ACC), middle frontal gyrus, and hippocampus in BD and controls separately. Complementary voxel-wise analyses were also performed.

RESULTS

In the BD group, higher arteriovenous ratio (AVR) was associated with greater ACC CBF (β = 0.34, p_uncorrected = 0.02), after controlling for age, sex, and BMI, however this finding did not survive correction for multiple comparisons. The control group did not show any associations (β = 0.13, p_uncorrected = 0.40). Voxel-wise analyses within the BD group detected a significant positive association between AVR and regional CBF in two distinct clusters: i) left hippocampus (p < 0.0001); ii) right middle temporal gyrus (p = 0.04).

LIMITATIONS

Limited sample size; young, medically healthy sample limits signal detection; cross-sectional design.

CONCLUSION

This study reveals that higher AVR is associated with higher regional CBF in adolescents with BD. Present findings advance understanding of potential neurofunctional mechanisms linking retinal vascular caliber with psychiatric diagnoses. This proof-of-concept study was designed to generate initial insights to guide future studies focusing on the vascular-brain connection in youth and in psychiatry.

Reduced cerebral vascular fractal dimension among asymptomatic individuals as a potential biomarker for cerebral small vessel disease

Cerebral small vessel disease is a neurological disease frequently found in the elderly and detected on neuroimaging, often as an incidental finding. White matter hyperintensity is one of the most commonly reported neuroimaging markers of CSVD and is linked with an increased risk of future stroke and vascular dementia. Recent attention has focused on the search of CSVD biomarkers. The objective of this study is to explore the potential of fractal dimension as a vascular neuroimaging marker in asymptomatic CSVD with low WMH burden. D_f is an index that measures the complexity of a self-similar and irregular structure such as circle of Willis and its tributaries. This exploratory cross-sectional study involved 22 neurologically asymptomatic adult subjects (42 ± 12 years old; 68% female) with low to moderate 10-year cardiovascular disease risk prediction score (QRISK2 score) who underwent magnetic resonance imaging/angiography (MRI/MRA) brain scan. Based on the MRI findings, subjects were divided into two groups: subjects with low WMH burden and no WMH burden, (WMH⁺; n = 8) and (WMH⁻; n = 14) respectively. Maximum intensity projection image was constructed from the 3D time-of-flight (TOF) MRA. The complexity of the CoW and its tributaries observed in the MIP image was characterised using D_f. The D_f of the CoW and its tributaries, i.e., D_f (w) was significantly lower in the WMH⁺ group (1.5172 ± 0.0248) as compared to WMH⁻ (1.5653 ± 0.0304, p = 0.001). There was a significant inverse relationship between the QRISK2 risk score and D_f (w), (r_s = − .656, p = 0.001). D_f (w) is a promising, non-invasive vascular neuroimaging marker for asymptomatic CSVD with WMH. Further study with multi-centre and long-term follow-up is warranted to explore its potential as a biomarker in CSVD and correlation with clinical sequalae of CSVD.

Retinal vessel multifractals predict pial collateral status in patients with acute ischemic stroke

OBJECTIVES

Pial collateral blood flow is a major determinant of the outcomes of acute ischemic stroke. This study was undertaken to determine whether retinal vessel metrics can predict the pial collateral status and stroke outcomes in patients.

METHODS

Thirty-five patients with acute stroke secondary to middle cerebral artery (MCA) occlusion underwent grading of their pial collateral status from computed tomography angiography and retinal vessel analysis from retinal fundus images.

RESULTS

The NIHSS (14.7 ± 5.5 vs 10.1 ± 5.8, p = 0.026) and mRS (2.9 ± 1.6 vs 1.9 ± 1.3, p = 0.048) scores were higher at admission in patients with poor compared to good pial collaterals. Retinal vessel multifractals: D0 (1.673±0.028vs1.652±0.025, p = 0.028), D1 (1.609±0.027vs1.590±0.025, p = 0.044) and f(α)max (1.674±0.027vs1.652±0.024, p = 0.019) were higher in patients with poor compared to good pial collaterals. Furthermore, support vector machine learning achieved a fair sensitivity (0.743) and specificity (0.707) for differentiating patients with poor from good pial collaterals. Age (p = 0.702), BMI (p = 0.422), total cholesterol (p = 0.842), triglycerides (p = 0.673), LDL (p = 0.952), HDL (p = 0.366), systolic blood pressure (p = 0.727), HbA1c (p = 0.261) and standard retinal metrics including CRAE (p = 0.084), CRVE (p = 0.946), AVR (p = 0.148), tortuosity index (p = 0.790), monofractal Df (p = 0.576), lacunarity (p = 0.531), curve asymmetry (p = 0.679) and singularity length (p = 0.937) did not differ between patients with poor compared to good pial collaterals.

CONCLUSIONS

This is the first translational study to show increased retinal vessel multifractal dimensions in patients with acute ischemic stroke and poor pial collaterals. A retinal vessel classifier was developed to differentiate between patients with poor and good pial collaterals and may allow rapid non-invasive identification of patients with poor pial collaterals.

Quantitative Analysis of Retinal Vasculature in Rhegmatogenous Retinal Detachment Based on Ultra-Widefield Fundus Imaging

Purpose

To quantitatively analyze retinal vascular morphological features, such as vascular density, caliber, and tortuosity, in rhegmatogenous retinal detachment (RRD).

Methods

A total of 244 patients with RRD and 400 healthy controls (HC) were included. Retinal fundus images were collected using OPTOS PLC Daytona P200T. Retinal images were divided into RRD and non-RRD regions of interest (ROIs). All visible retinal fundus vessels were then extracted mainly based on edge detection within ROI to form the whole-vascular image. Retinal vasculature parameters, such as vascular density, caliber, and tortuosity, were calculated.

Results

For the absolute density, the mean rank (MR) value of normal controls was significantly higher than that in non-RRD (p < 0.001). A consistent tendency of significant vascular density was increased from non-RRD to RRD (p < 0.001). The average and median diameters of normal controls were both significantly larger than RRD (p < 0.001). The average and median diameters were also appeared significantly thinner in non-RRD. Unweighted and width-inversely-weighted vascular tortuosity in RRD and non-RRD comparison exhibited non-significant differences. All types of tortuosity calculated from HC were significantly larger (p < 0.001) in values compared to RRD. All types of tortuosity values of HC were significantly higher than non-RRD. Compared with non-RRD, RRD was significantly larger in area-weighted, length-weighted, and width-weighted vascular tortuosity.

Conclusions

This study showed that RRD affects both the quantity and morphology of retinal vasculature, such as RRD and non-RRD areas. Smaller average and medium vascular diameters and tortuosity values were found in RRD. However, the absolute vascular density, the average and median diameter, and tortuosity values were also reduced in non-RRD although the retina is still attached. This work indicates that RRD may affect the retinal vasculature beyond the detached retina.

Visual Impairments Are Associated With Retinal Microvascular Density in Patients With Parkinson's Disease

Objective

This study aimed to evaluate retinal microvascular density in patients with Parkinson’s disease (PD) and its correlation with visual impairment.

Methods

This cross-sectional study included 24 eyes of 24 patients with PD and 23 eyes of 23 healthy controls. All participants underwent ophthalmic examination, visual evoked potential (VEP) test, 25-item National Eye Institute Visual Function Questionnaire (NEI VFQ-25), and optical coherence tomography angiography (OCTA) examination. The correlation between retinal microvascular density and visual parameter was evaluated using Spearman correlation analysis, and the area under receiver operating characteristic curve (AUROC) was calculated.

Results

Parkinson’s disease patients had prolonged P100 latency (P = 0.041), worse vision-related quality of life (composite score and 3 of 12 subscales in NEI VFQ-25), and decreased vessel density (VD) in all sectors of 3-mm-diameter region (all P < 0.05) compared with healthy controls. There were no statistical differences in the ganglion cell-inner plexiform layer (GCIPL) thickness and retinal nerve fiber layer (RNFL) thickness between the two groups. A negative correlation was found between P100 latency and nasal and superior sectors of macular VD in a 3-mm-diameter region (r = −0.328, P = 0.030; r = −0.302, and P = 0.047, respectively). Macular VD in a 3-mm-diameter region showed diagnostic capacities to distinguish PD patients from healthy controls (AUROCs, ranging from 0.655 to 0.723).

Conclusion

This study demonstrated that decreased retinal microvascular density was correlated with visual impairment in PD patients. Retinal microvasculature change may occur earlier than visual decline and retinal structure change and has the potential to be a promising diagnostic marker for early PD.

Development of Novel Fractal Method for Characterizing the Distribution of Blood Flow in Multi-Scale Vascular Tree

Blood perfusion is an important index for the function of the cardiovascular system and it can be indicated by the blood flow distribution in the vascular tree. As the blood flow in a vascular tree varies in a large range of scales and fractal analysis owns the ability to describe multi-scale properties, it is reasonable to apply fractal analysis to depict the blood flow distribution. The objective of this study is to establish fractal methods for analyzing the blood flow distribution which can be applied to real vascular trees. For this purpose, the modified methods in fractal geometry were applied and a special strategy was raised to make sure that these methods are applicable to an arbitrary vascular tree. The validation of the proposed methods on real arterial trees verified the ability of the produced parameters (fractal dimension and multifractal spectrum) in distinguishing the blood flow distribution under different physiological states. Furthermore, the physiological significance of the fractal parameters was investigated in two situations. For the first situation, the vascular tree was set as a perfect binary tree and the blood flow distribution was adjusted by the split ratio. As the split ratio of the vascular tree decreases, the fractal dimension decreases and the multifractal spectrum expands. The results indicate that both fractal parameters can quantify the degree of blood flow heterogeneity. While for the second situation, artificial vascular trees with different structures were constructed and the hemodynamics in these vascular trees was simulated. The results suggest that both the vascular structure and the blood flow distribution affect the fractal parameters for blood flow. The fractal dimension declares the integrated information about the heterogeneity of vascular structure and blood flow distribution. In contrast, the multifractal spectrum identifies the heterogeneity features in blood flow distribution or vascular structure by its width and height. The results verified that the proposed methods are capable of depicting the multi-scale features of the blood flow distribution in the vascular tree and further are potential for investigating vascular physiology.

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.