Optical coherence tomography angiography analysis methods: a systematic review and meta-analysis DOI Creative Commons

Ella Courtie,

James Robert Moore Kirkpatrick,

Matthew Taylor

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: April 26, 2024

Abstract Optical coherence tomography angiography (OCTA) is widely used for non-invasive retinal vascular imaging, but the OCTA methods to assess perfusion vary. We evaluated different between studies. MEDLINE and Embase were searched from 2014 August 2021. included prospective studies including ≥ 50 participants using in either global or systemic disorders. Risk of bias was assessed National Institute Health quality assessment tool observational cohort cross-sectional Heterogeneity data by Q statistics, Chi-square test, I 2 index. Of 5974 identified, 191 this evaluation. The selected employed seven devices, six macula volume dimensions, four subregions, nine analyses, five vessel layer definitions, totalling 197 distinct assessing over 7000 possible combinations. Meta-analysis performed on 88 reporting density foveal avascular zone area, showing lower patients with diabetes mellitus than healthy controls, high heterogeneity. lowest reported effects strongest superficial capillary plexus assessments. Systematic review revealed massive heterogeneity perfusion, supporting calls standardisation methodology.

Language: Английский

Screening and evaluation of antioxidants for retinal pigment epithelial cell protection: L-ergothioneine as a novel therapeutic candidate through NRF2 activation DOI

Sijie Gu,

Siqi Wu,

Zesong Lin

et al.

Experimental Eye Research, Journal Year: 2024, Volume and Issue: 242, P. 109862 - 109862

Published: March 13, 2024

Language: Английский

Citations

3
A Siamese ResNeXt network for predicting carotid intimal thickness of patients with T2DM from fundus images DOI Creative Commons

AJuan Gong,

Wanjin Fu, Heng Li

et al.

Frontiers in Endocrinology, Journal Year: 2024, Volume and Issue: 15

Published: March 14, 2024

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

Language: Английский

Citations

3
Optical coherence tomography’s current clinical medical and dental applications: a review DOI Creative Commons
Saqib Ali, Saqlain Bin Syed Gilani,

Juzer Shabbir

et al.

F1000Research, Journal Year: 2021, Volume and Issue: 10, P. 310 - 310

Published: April 22, 2021

Optical coherence tomography (OCT) is a non-invasive investigative technique that used to obtain high-resolution three-dimensional (3D) images of biological structures. This method useful in diagnosing diseases specific organs like the eye, where direct biopsy cannot be conducted. Since its inception, significant advancements have been made technology. Apart from initial application ophthalmology for retinal imaging, substantial technological innovations OCT brought by research community enabled utilization beyond original scope and allowed many new clinical areas. review presents summary applications field medicine (ophthalmology, cardiology, otology, dermatology) dentistry (tissue detection caries, analysis dental polymer composite restorations, imaging root canals, diagnosis oral cancer). In addition, potential advantages disadvantages are also discussed.

Language: Английский

Citations

19
Predicting ischemic stroke risk from atrial fibrillation based on multi-spectral fundus images using deep learning DOI Creative Commons
Hui Li, Mengdi Gao, Haiqing Song

et al.

Frontiers in Cardiovascular Medicine, Journal Year: 2023, Volume and Issue: 10

Published: Aug. 1, 2023

Background Ischemic stroke (IS) is one of the most common serious secondary diseases atrial fibrillation (AF) within 1 year after its occurrence, both which have manifestations ischemia and hypoxia small vessels in early phase condition. The fundus a collection capillaries, while retina responds differently to light different wavelengths. Predicting risk IS occurring AF, based on subtle differences images wavelengths, yet be explored. This study was conducted predict AF multi-spectrum using deep learning. Methods A total 150 participants without suffering from discharge 100 with persistent arrhythmia symptoms or history diagnosis last (defined as patients who would develop pathological generally prior brain) were recruited. Fundus at 548, 605, 810 nm wavelengths collected. Three classical neural network (DNN) models (Inception V3, ResNet50, SE50) trained. Sociodemographic selected routine clinical data obtained. Results accuracy all DNNs single-spectral multi-spectral combination three input reached above 78%. detection performance 605 spectral relatively more stable than other acquired higher area under curve (AUC) scores models. Conclusions probability could predicted learning, combinations improved DNNs. Acquiring advantageous for prevention cardiovascular cerebrovascular diseases. method this beneficial preliminary initiative exploration that are difficult onset time such IS.

Language: Английский

Citations

8
Applications of artificial intelligence-assisted retinal imaging in systemic diseases: A literature review DOI

AliM Al-Halafi

Saudi Journal of Ophthalmology, Journal Year: 2023, Volume and Issue: 37(3), P. 185 - 192

Published: July 1, 2023

Language: Английский

Citations

8
Optical Coherence Tomography Angiography Changes in Patients Diagnosed With Acute Coronary Syndrome: A Systematic Review and Meta-Analysis DOI Open Access

Anna Maria Sideri,

Dimitra Mitsopoulou, Stylianos Kandarakis

et al.

Cureus, Journal Year: 2024, Volume and Issue: unknown

Published: Feb. 13, 2024

We conducted a systematic review and meta-analysis to assess the association between optical coherence tomography angiography (OCTA) parameters acute coronary syndrome (ACS). Two independent reviewers searched electronic databases (MEDLINE (Medical Literature Analysis Retrieval System Online), Scopus, Embase (Excerpta Medica Database), Cochrane Library, ClinicalTrials.gov, World Health Organization International Clinical Trials Registry Platform) from inception until April 2023. According inclusion criteria of this review, eligible were observational studies, randomized control trials, registry/database studies that included eyes adult ACS patients assessed OCTA within macula. The pooled standardized mean differences (SMD) diagnosed with healthy controls confidence interval (CI) 95% calculated using Hartung-Knapp-Sidik-Jonkman random-effects method. heterogeneity was by I2 Cochran Q random effects model applied. Seven in our (n = 898), which three 341). SMD superficial vascular plexus (SVP), deep (DVP), foveal avascular zone (FAZ) -0.46 (95% CI: -0.94 0.01, p 0.05, 0%, studies), -0.10 -3.20 3.00, 0.75, 67%, two 0.43 -1.22 2.09, 0.38, 92%, respectively. Our findings suggest there are no metrics individuals.

Language: Английский

Citations

2
Modifications in Macular Perfusion and Neuronal Loss After Acute Traumatic Brain Injury DOI Creative Commons
Jenny L. Hepschke, Elinor Laws, Noor Haziq Saliman

et al.

Investigative Ophthalmology & Visual Science, Journal Year: 2023, Volume and Issue: 64(4), P. 35 - 35

Published: April 28, 2023

Traumatic brain injury (TBI) causes structural damage and functional impairment in the visual system, often with retinal ganglion cell (RGC) degeneration occurring without symptoms. RGC is associated reduced blood-flow, however, it not known whether reductions perfusion precede or are secondary to neurodegeneration.

Language: Английский

Citations

6
A dynamic multiscale model of cerebral blood flow and autoregulation in the microvasculature DOI Creative Commons
Ali Daher, Stephen J. Payne

Applied Mathematical Modelling, Journal Year: 2023, Volume and Issue: 123, P. 213 - 240

Published: July 3, 2023

Models of the micro-circulatory blood flow in brain can play a key role understanding variety cerebrovascular diseases that occur microvasculature. These conditions are often linked to structural modifications vessel network, alterations patterns, as well impairment autoregulatory response, all which pathological changes model should be able address if it were have any clinical value. Furthermore, results validated against MRI data, simulations need computationally feasible when used on networks scale an voxel. This requires some form upscaling approach bypasses for explicit architectural representation whole network while maintaining relevant anatomical connections. To this end, we developed hybrid multiscale and autoregulation traces dynamic flow, volume, pressure cortical microvasculature, where discrete topology penetrating vessels is preserved, these then appropriately coupled homogenised capillary bed by spatially distributing support function terminal endings. In contrast other models, here accounts physiological phenomena processes microvessels. We show how adaptive meshing scheme study employed ensure scale-invariant coupling formulation numerically accurate simulations, without compromising computational feasibility model. A statistically voxel generated, parameter values calibrated using Monte Carlo Filtering analysis physiologically informed. The found capture steep gradients been reported at interfaces. response upstream drop, recover cerebral exhibiting characteristic behaviour terms calibre biphasic response. Overall, offers high-quality characterisation microvasculature improved efficiency lays ground whole-brain simulations.

Language: Английский

Citations

6
Advancing systemic disease diagnosis through ophthalmic image‐based artificial intelligence DOI Creative Commons
Hanpei Miao,

Zixing Zou,

Jie Xu

et al.

MedComm – Future Medicine, Journal Year: 2024, Volume and Issue: 3(1)

Published: March 1, 2024

Abstract The eye serves as a unique window into systemic health, offering clinicians valuable opportunity for early detection and targeted treatment. Against this backdrop, advancements in artificial intelligence (AI) ophthalmic imaging are converging to pave the way more precise predictive diagnostics. This review aims elucidate transformative role of AI utilizing prediction diseases. We begin by introducing advantages tool detecting also provide an overview various techniques that have proven useful predicting ailments. Then, we summarize two research patterns analyzing ocular data, followed introduction current applications using images significantly increase diagnostic precision. Despite promise, challenges such data heterogeneity model interpretability persist, which covered review. conclude discussing future directions immense potential these AI‐enabled approaches hold revolutionizing healthcare. As technologies advance, their integration with offers promising avenues improving diagnosis, prediction, management diseases, thereby contributing evolving landscape integrated

Language: Английский

Citations

2
Review: Emerging Eye-Based Diagnostic Technologies for Traumatic Brain Injury DOI Creative Commons
Georgia Harris, Jonathan James Stanley Rickard, Gibran Butt

et al.

IEEE Reviews in Biomedical Engineering, Journal Year: 2022, Volume and Issue: 16, P. 530 - 559

Published: March 23, 2022

The study of ocular manifestations neurodegenerative disorders, Oculomics, is a growing field investigation for early diagnostics, enabling structural and chemical biomarkers to be monitored overtime predict prognosis. Traumatic brain injury (TBI) triggers cascade events harmful the brain, which can lead neurodegeneration. TBI, termed "silent epidemic" becoming leading cause death disability worldwide. There currently no effective diagnostic tool yet, early-intervention known considerably shorten hospital stays, improve outcomes, fasten neurological recovery lower mortality rates, highlighting unmet need techniques capable rapid accurate point-of-care implemented in earliest stages. This review focuses on latest advances main neuropathophysiological responses achievements shortfalls TBI methods. Validated emerging TBI-indicative are outlined linked neuro-disorders. Methods detecting categorised along with prospective physical sensing techniques. Particular attention drawn potential Raman spectroscopy as non-invasive molecular signatures projections laying platform first tangible path towards alternative technologies TBI.

Language: Английский

Citations

10