Diabetic and Retinal Vascular Eye Disease

Le, Hong-Gam; Shakoor, Akbar

doi:10.1016/j.mcna.2021.02.004

Cited by 15 publications

(9 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ophthalmic arteries, responsible for delivering critical sustenance to ocular components, including the retina and crystalline lens ( 36 ), primarily arise from the internal carotid. Carotid stenosis induced by diabetes may enhance the risk of thromboembolic phenomena and attenuated blood flow ( 37 ), consequently resulting in ischemic ocular diseases such as retinal artery occlusion and ischemic optic neuropathy ( 38 ). Analysis of microvascular changes on fundus images provides valuable information for cardiovascular pathologies ( 39 ).…”

Section: Discussionmentioning

confidence: 99%

A Siamese ResNeXt network for predicting carotid intimal thickness of patients with T2DM from fundus images

Gong,

Fu,

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

ObjectiveTo develop and validate an artificial intelligence diagnostic model based on fundus images for predicting Carotid Intima-Media Thickness (CIMT) in individuals with Type 2 Diabetes Mellitus (T2DM).MethodsIn total, 1236 patients with T2DM who had both retinal fundus images and CIMT ultrasound records within a single hospital stay were enrolled. Data were divided into normal and thickened groups and sent to eight deep learning models: convolutional neural networks of the eight models were all based on ResNet or ResNeXt. Their encoder and decoder modes are different, including the standard mode, the Parallel learning mode, and the Siamese mode. Except for the six unimodal networks, two multimodal networks based on ResNeXt under the Parallel learning mode or the Siamese mode were embedded with ages. Performance of eight models were compared via the confusion matrix, precision, recall, specificity, F1 value, and ROC curve, and recall was regarded as the main indicator. Besides, Grad-CAM was used to visualize the decisions made by Siamese ResNeXt network, which is the best performance.ResultsPerformance of various models demonstrated the following points: 1) the RexNeXt showed a notable improvement over the ResNet; 2) the structural Siamese networks, which extracted features parallelly and independently, exhibited slight performance enhancements compared to the traditional networks. Notably, the Siamese networks resulted in significant improvements; 3) the performance of classification declined if the age factor was embedded in the network. Taken together, the Siamese ResNeXt unimodal model performed best for its superior efficacy and robustness. This model achieved a recall rate of 88.0% and an AUC value of 90.88% in the validation subset. Additionally, heatmaps calculated by the Grad-CAM algorithm presented concentrated and orderly mappings around the optic disc vascular area in normal CIMT groups and dispersed, irregular patterns in thickened CIMT groups.ConclusionWe provided a Siamese ResNeXt neural network for predicting the carotid intimal thickness of patients with T2DM from fundus images and confirmed the correlation between fundus microvascular lesions and CIMT.

show abstract

Section: Discussionmentioning

confidence: 99%

A Siamese ResNeXt network for predicting carotid intimal thickness of patients with T2DM from fundus images

Gong,

Fu,

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

show abstract

“…Diabetic retinopathy (DR) is another microvascular complication of diabetes mellitus, and involves the activation of microglia [168,169]. A pilot study showed that the AIF1 serum levels positively correlated with hyperreflective intraretinal spots (HRS) in patients with both nonproliferative or proliferative DR, and correlated with serum levels of proinflammatory cytokines such as IL-1β, IL-6 or TNF-α [170].…”

Section: Metabolic Diseasementioning

confidence: 99%

AIF1: Function and Connection with Inflammatory Diseases

De Leon-Oliva,

Garcia-Montero,

Fraile-Martinez

et al. 2023

Biology

View full text Add to dashboard Cite

Macrophages are a type of immune cell distributed throughout all tissues of an organism. Allograft inflammatory factor 1 (AIF1) is a calcium-binding protein linked to the activation of macrophages. AIF1 is a key intracellular signaling molecule that participates in phagocytosis, membrane ruffling and F-actin polymerization. Moreover, it has several cell type-specific functions. AIF1 plays important roles in the development of several diseases: kidney disease, rheumatoid arthritis, cancer, cardiovascular diseases, metabolic diseases and neurological disorders, and in transplants. In this review, we present a comprehensive review of the known structure, functions and role of AIF1 in inflammatory diseases.

show abstract

“…Disturbances in the retinal blood flow are involved in the pathophysiology of the most frequent vision‐threatening diseases in the Western world (Le & Shakoor, 2021). A precondition for intervening on these diseases is knowledge about the regulation of retinal blood flow under normal conditions.…”

Section: Introductionmentioning

confidence: 99%

The vasoactive effects of bradykinin, vasoactive intestinal peptide, calcitonin gene‐related peptide and neuropeptide Y depend on the perivascular tissue in porcine retinal arterioles in vitro

Lykke,

Ernst,

Bek

2023

Acta Ophthalmologica

View full text Add to dashboard Cite

PurposeThe retina contains a number of vasoactive neuropeptides and corresponding receptors, but the role of these neuropeptides for tone regulation of retinal arterioles has not been studied in detail.MethodsPorcine arterioles with preserved perivascular retinal tissue were mounted in a wire myograph, and the tone was measured after the addition of increasing concentrations of bradykinin, vasoactive intestinal peptide (VIP), neuropeptide Y (NPY), substance P (SP), calcitonin gene‐related peptide (CGRP) and brain natriuretic peptide (BNP). The experiments were performed during inhibition of the synthesis of nitric oxide (NO), prostaglandins and dopamine and were repeated after removal of the perivascular retinal tissue.ResultsBradykinin, VIP and CGRP induced significant concentration‐dependent dilatation and NPY significant concentration‐dependent contraction of the arterioles in the presence of perivascular retinal tissue (p < 0.03 for all comparisons) but not on isolated arterioles. BNP and SP had no effect on vascular tone. The NOS inhibitor L‐NAME reduced bradykinin‐ and VIP‐induced relaxation (p < 0.001 for both comparisons), whereas none of the other inhibitors influenced the vasoactive effects of the studied neuropeptides.ConclusionThe effects of neuropeptides on the tone of retinal arterioles depend on the perivascular retinal tissue and may involve effects other than those mediated by nitric oxide, prostaglandins and adrenergic compounds. Investigation of the mechanisms underlying the vasoactive effect of neuropeptides may be important for understanding and treating retinal diseases where disturbances in retinal flow regulation are involved in the disease pathogenesis.

show abstract

Diabetic and Retinal Vascular Eye Disease

Cited by 15 publications

References 45 publications

A Siamese ResNeXt network for predicting carotid intimal thickness of patients with T2DM from fundus images

A Siamese ResNeXt network for predicting carotid intimal thickness of patients with T2DM from fundus images

AIF1: Function and Connection with Inflammatory Diseases

The vasoactive effects of bradykinin, vasoactive intestinal peptide, calcitonin gene‐related peptide and neuropeptide Y depend on the perivascular tissue in porcine retinal arterioles in vitro

Contact Info

Product

Resources

About