Changes of retinal structure and function in patients with internal carotid artery stenosis

Screening of Moyamoya Disease From Retinal Photographs: Development and Validation of Deep Learning Algorithms

BACKGROUND

Moyamoya disease (MMD) is a rare and complex pathological condition characterized by an abnormal collateral circulation network in the basal brain. The diagnosis of MMD and its progression is unpredictable and influenced by many factors. MMD can affect the blood vessels supplying the eyes, resulting in a range of ocular symptoms. In this study, we developed a deep learning model using real-world data to assist a diagnosis and determine the stage of the disease using retinal photographs.

METHODS

This retrospective observational study conducted from August 2006 to March 2022 included 498 retinal photographs from 78 patients with MMD and 3835 photographs from 1649 healthy participants. Photographs were preprocessed, and an ResNeXt50 model was developed. Model performance was measured using receiver operating curves and their area under the receiver operating characteristic curve, accuracy, sensitivity, and F1-score. Heatmaps and progressive erasing plus progressive restoration were performed to validate the faithfulness.

RESULTS

Overall, 322 retinal photographs from 67 patients with MMD and 3752 retinal photographs from 1616 healthy participants were used to develop a screening and stage prediction model for MMD. The average age of the patients with MMD was 44.1 years, and the average follow-up time was 115 months. Stage 3 photographs were the most prevalent, followed by stages 4, 5, 2, 1, and 6 and healthy. The MMD screening model had an average area under the receiver operating characteristic curve of 94.6%, with 89.8% sensitivity and 90.4% specificity at the best cutoff point. MMD stage prediction models had an area under the receiver operating characteristic curve of 78% or higher, with stage 3 performing the best at 93.6%. Heatmap identified the vascular region of the fundus as important for prediction, and progressive erasing plus progressive restoration result shows an area under the receiver operating characteristic curve of 70% only with 50% of the important regions.

CONCLUSIONS

This study demonstrated that retinal photographs could be used as potential biomarkers for screening and staging of MMD and the disease stage could be classified by a deep learning algorithm.

Retinal Microvascular Changes in Internal Carotid Artery Stenosis

Purpose: We aimed to analyze retinal microvascular parameters, measured by optical coherence tomography angiography in patients with internal carotid artery stenosis compared to healthy individuals. Materials and Methods: A total of 41 eyes from 30 patients who had varying degrees of carotid stenosis, and 42 eyes from 42 healthy controls, were enrolled in this study. Depending on the degree of stenosis evaluated by Doppler ultrasonographic imaging, the patient group was further subclassified into mild, moderate, and severe carotid artery stenosis. Superficial and deep capillary plexus vessel densities, radial peripapillary capillary vessel density, foveal avascular zone, and flow densities in the choriocapillaris and outer retina were evaluated by optical coherence tomography angiography. Results: The superficial and deep capillary plexus vessel densities were significantly reduced among the groups, only sparing the foveal region. The mean superficial plexus vessel density was 45.67 ± 4.65 and 50.09 ± 4.05 for the patient and control group, respectively (p = 0.000). The mean deep capillary plexus density was 46.33% ± 7.31% and 53.27% ± 6.31% for the patient and control group, respectively (p = 0.000). The mean superficial and deep capillary vessel densities in the foveal region did not show any statistical difference between the patient and control groups (p = 0.333 for the superficial and p = 0.195 for the deep plexus vessel density). Radial peripapillary capillary vessel density was decreased in the patient group (p = 0.004). The foveal avascular zone area was wider in the patient group but this difference did not show a significant difference (p = 0.385). Conclusions: Retinal microvascular changes are a prominent outcome of internal carotid disease, and even mild stenosis can lead to alterations in the retinal microvascular bed which could be detected by OCTA. By early detection of microvascular changes in the retina in this patient group, we might speculate the overall vascular condition.

Length of Carotid Plaque Impacts Retinal Microvascular Densities of Carotid Artery Stenosis Patients

Purpose

We explored the retinal microvascular changes in carotid artery stenosis (CAS) and their relationship with carotid plaque morphology.

Methods

All participants were diagnosed with carotid artery stenosis by a neurologist. Participants underwent digital subtraction angiography (DSA) and optical coherence tomography angiography (OCTA) imaging. The degree and length of carotid plaque were obtained from the DSA tool. OCTA tool measured the densities in the superficial vascular complex (SVC) and deep vascular complex (DVC).

Results

One hundred seventeen patients with CAS patients were included in our data analysis. Eyes with ipsilateral stenosis had reduced retinal microvascular densities when compared to contralateral eyes in patients with CAS (P = 0.016 for SVC, and P = 0.004 for DVC). Microvascular densities correlated with the length of carotid plaque (P = 0.015 for SVC, and P = 0.022 for DVC) in our CAS cohort, although they did not correlate with the degree of carotid plaque (P = 0.264 for SVC, and P = 0.298 for DVC). However, when stratified into moderate and severe subgroups, the degree of carotid plaque correlated with microvascular densities in patients with severe stenosis (P = 0.045 for SVC, and P = 0.038 for DVC).

Conclusions

Our study suggests that OCTA can noninvasively detect retinal microvascular changes in patients with CAS and that these changes correlated with the length of the stenosis, but future studies are required to confirm these findings.

Translational Relevance

Noninvasive and rapid acquisition of the OCTA image might have the potential to be used as a screening tool to detect microvascular changes in carotid artery stenosis.

Comparison of Ophthalmic Artery Morphological Characteristics and Retinal Vessel Diameter for Identifying Ocular Ischemic Syndrome

Purpose

To investigate the morphological characteristics of the ophthalmic artery (OA) and retinal vessels in ocular ischemic syndrome (OIS) and to compare their ability to identify OIS.

Methods

This cross-sectional observational study included 21 patients with unilateral OIS and 17 controls matched for age, sex, degree of internal carotid artery (ICA) stenosis, and cerebral collateral patency. This study used a three-dimensional reconstruction based on computed tomographic angiography to measure the morphological characteristics of the OA and the ICA. Quantitative measurements of retinal vessel diameter were performed using the Integrative Vessel Analysis software. Receiver operating characteristic (ROC) curve analysis was performed to assess the ability of the OA diameter and the central retinal artery equivalent (CRAE) to identify OIS.

Results

The diameter of the OA (odds ratio = 0.001; P = 0.001) and the CRAE (odds ratio = 0.951; P = 0.028) were significantly associated with the presence of OIS after adjusting for age, sex, and the degree of the ICA stenosis. The areas under the curve for the OA diameter and the CRAE were, respectively, 0.871 (P < 0.001) and 0.744 (P = 0.017) according to the ROC curves analysis.

Conclusions

The OA diameter measurement identified OIS better than CRAE measurement. The OA may reflect the changes in ocular blood supply in patients with OIS earlier than retinal vessels. The OA of eyes with OIS may undergo arterial wall remodeling, leading to a decrease in OA diameter and further reduction in blood flow.

A narrative review of retinal vascular parameters and the applications (Part II): Diagnosis in stroke

The retina, as an external extension of the diencephalon, can be directly, noninvasively observed by ocular fundus photography. Therefore, it offers a convenient and feasible mode to study nervous system diseases. Caliber, tortuosity, and fractal dimension, as three commonly used retinal vascular parameters, are not only the reflection of structural changes in the retinal microcirculation but also capture the branching pattern or density changes of the retinal microvascular network. Therefore, it contributes to better reflecting the subclinical pathological changes (e.g., lacunar stroke and small cerebral vascular disease) and predicting the risk of incident stroke and recurrent stroke.

Quantitative assessment of retinal vessel density and thickness changes in internal carotid artery stenosis patients using optical coherence tomography angiography

OBJECTIVE

To quantitatively assess the retinal features of patients with different degrees of internal carotid artery stenosis (ICAS), particularly mild ICAS patients, utilizing optical coherence tomography angiography (OCTA).

METHODS

Thirty-two mild ICAS patients (mild ICAS group), 34 moderate to severe ICAS patients (nonmild ICAS group), and 40 controls were enrolled in this study. Retinal vessel density was quantitatively measured by OCTA, including radial peripapillary capillary vessel density (RPC-VD), superficial and deep capillary plexus vessel density (SCP/DCP-VD). Structural parameters were collected from optical coherence tomography (OCT), including retinal thickness and subfoveal choroidal thickness (SFCT). Furthermore, LASSO-penalized logistic regression was used to construct the diagnostic model based on retinal parameters. ROC curves and nomogram plots were used to assess the diagnostic ability of this model for ICAS.

RESULTS

The macular SCP-VD of mild ICAS patients was significantly lower than that of controls and lower than that of nonmild ICAS patients (all p < 0.05). However, there was no difference among the three groups in terms of DCP-VD (p > 0.05). RPC-VD could effectively discriminate between the mild ICAS group and the nonmild ICAS group (p = 0.005). For structural OCT, only the SFCT decreased as the ICAS degree increased (p < 0.05). Diagnostic scores based on retinal parameters showed a strong diagnostic capability for mild ICAS (AUC = 0.8656).

CONCLUSION

Mild ICAS patients exhibited distinct retinal features compared to nonmild ICAS patients and control subjects. OCTA potentially represents a promising method for the early detection of ICAS patients and the noninvasive surveillance of haemodynamic changes in those patients.