Artificial intelligence velocimetry and microaneurysm-on-a-chip for three-dimensional analysis of blood flow in physiology and disease

Proceedings of the National Academy of Sciences, Journal Year: 2021, Volume and Issue: 118(13)

Published: March 24, 2021

Significance Microfluidics is an important in vitro platform to gain insights into mechanics of blood flow and mechanisms pathophysiology human diseases. Extraction 3D fields microfluidics with dense cell suspensions remains a formidable challenge. We present artificial-intelligence velocimetry (AIV) as general determine microaneurysm-on-a-chip simulate microaneurysms patients diabetic retinopathy. AIV built on physics-informed neural networks that integrate seamlessly 2D images from microfluidic experiments or vivo observations physical laws estimate full velocity stress fields. could be integrated imaging technologies automatically infer key hemodynamic metrics biomedical images.

Language: Английский

---

Interplay between aging and other factors of the pathogenesis of age-related macular degeneration

Ageing Research Reviews, Journal Year: 2022, Volume and Issue: 81, P. 101735 - 101735

Published: Sept. 13, 2022

Age-related macular degeneration (AMD) is a complex eye disease with the retina as target tissue and aging per definition most serious risk factor. However, contains over 60 kinds of cells that form different structures, including neuroretina retinal pigment epithelium (RPE) which can age at rates. Other established or putative AMD factors differentially affect RPE differently interplay these structures. The occurrence β-amyloid plaques increased levels cholesterol in retinas suggest may be syndrome accelerated brain aging. Therefore, question about real meaning justified. In this review we present update information on how some aspects pathogenesis, such oxidative stress, amyloid beta formation, circadian rhythm, metabolic cellular senescence. Also, show specific for photoreceptors, microglia well Bruch's membrane choroid. process As an accurate quantification biological important stratification early intervention age-related diseases, determination microglial helpful precise diagnosis treatment largely untreatable disease.

Language: Английский

---

Oculomics: A Crusade Against the Four Horsemen of Chronic Disease

Ophthalmology and Therapy, Journal Year: 2024, Volume and Issue: 13(6), P. 1427 - 1451

Published: April 17, 2024

Chronic, non-communicable diseases present a major barrier to living long and healthy life. In many cases, early diagnosis can facilitate prevention, monitoring, treatment efforts, improving patient outcomes. There is therefore critical need make screening techniques as accessible, unintimidating, cost-effective possible. The association between ocular biomarkers systemic health disease (oculomics) presents an attractive opportunity for detection of diseases, ophthalmic are often relatively low-cost, fast, non-invasive. this review, we highlight the key associations structural in eye four globally leading causes morbidity mortality: cardiovascular disease, cancer, neurodegenerative metabolic disease. We observe that particularly promising target oculomics, with detected multiple structures. Cardiovascular choroid, retinal vasculature, nerve fiber layer, eyelid, tear fluid, lens, vasculature. contrast, only fluid emerged cancer. retina rich source oculomics data, analysis which has been enhanced by artificial intelligence-based tools. Although not all disease-specific, limiting their current diagnostic utility, future research will likely benefit from combining data various structures improve specificity, well active design, development, optimization instruments specific signatures, thus facilitating differential diagnoses. Long-term stop people lives. help prevent, monitor, treat patients' health. order diagnose tools easy patients access, painless, low-cost. may provide solution. discuss link changes types long-term that, together, kill most population: (1) (affecting heart and/or blood). (2) Cancer (abnormal growth cells). (3) Neurodegenerative brain nervous system). (4) Metabolic (problems storing, accessing, using body's fuel). show leaves tell-tale signs lots different parts eye. Signs mostly found back eye, cancer be fluid. seen them tell us what is. believe understand more about how detect it if combine information within develop new these

Language: Английский

---

Artificial Intelligence in Predicting Systemic Parameters and Diseases From Ophthalmic Imaging

Frontiers in Digital Health, Journal Year: 2022, Volume and Issue: 4

Published: May 26, 2022

Artificial Intelligence (AI) analytics has been used to predict, classify, and aid clinical management of multiple eye diseases. Its robust performances have prompted researchers expand the use AI into predicting systemic, non-ocular diseases parameters based on ocular images. Herein, we discuss reasons why is well-suited for systemic applications, review applications deep learning ophthalmic images in prediction demographic parameters, body composition factors, cardiovascular, hematological, neurodegenerative, metabolic, renal, hepatobiliary systems. Three main imaging modalities are included—retinal fundus photographs, optical coherence tomographs external We examine range factors studied from current literature areas future research, while acknowledging limitations systems

Language: Английский

---

Direct Retinal Imaging for Shock Resuscitation in Critical Ill Adults II (D-RISC II)

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 31, 2025

Abstract Background Shock involves microcirculatory dysfunction that is not suitably captured well by measurements of large vessels, such as systemic blood pressure. The outer retinal microcirculation (the choroid) can be measured non-invasively and may reflect in other organs. We tested the feasibility measuring choroid an intensive care setting explored associations between choroidal severity disease. Methods performed optical coherence tomography on patients admitted to treatment unit, repeated imaging once 12-72 hours later. anatomy using automated image segmentation, compared this routine clinical data, described change over time. Results Of fifteen recruited, 80% (12) had successful baseline 40% (6) these follow-up within care. At baseline, with thicker choroids larger vascularity cumulative fluid balance, lower disease (Acute Physiology Chronic Health Evaluation II) score, haematocrit, albumin. A measurable suprachoroidal space was seen 75% (9) size tended heart rates. There substantial intraindividual variation Comment Measuring feasible critical illness. Exploratory variables suggest provide information about microvascular function major Size perfusion pressure or vascular leak response inflammation.

Language: Английский

---

Method for measuring retinal capillary blood flow velocity by encoded OCTA

Chinese Optics Letters, Journal Year: 2025, Volume and Issue: 23(4), P. 041701 - 041701

Published: Jan. 1, 2025

Language: Английский

---

EfficientNetB0-Based End-to-End Diagnostic System for Diabetic Retinopathy Grading and Macular Edema Detection

Diabetes Metabolic Syndrome and Obesity, Journal Year: 2025, Volume and Issue: Volume 18, P. 1311 - 1321

Published: April 1, 2025

This study aims to develop and validate a deep learning-based automated diagnostic system that utilizes fluorescein angiography (FFA) images for the rapid accurate diagnosis of diabetic retinopathy (DR) its complications. We collected 19,031 FFA from 2753 patients between June 2017 March 2024 construct evaluate our analytical framework. The were preprocessed annotated training validating learning model. employed two-stage system: first stage used EfficientNetB0 five-class classification task differentiate normal retinal conditions, various stages DR, post-laser treatment status; second focused on classified as abnormal in stage, further detecting presence macular edema (DME). Model performance was evaluated using multiple metrics, including accuracy, AUC, precision, recall, F1-score, Cohen's kappa coefficient. In model achieved an accuracy 0.7036 AUC 0.9062 test set, demonstrating high discriminative ability. 0.7258 0.7530, performing well. Additionally, through Grad-CAM (gradient-weighted class activation mapping), we visualized most influential image regions model's decision-making process, enhancing interpretability. successfully developed end-to-end DR based not only automates grading but also detects DME, significantly reducing time required interpretation by clinicians providing effective tool improve efficiency diagnosis.

Language: Английский

---

Retinal Microvascular Changes in COVID-19 Bilateral Pneumonia Based on Optical Coherence Tomography Angiography

Journal of Clinical Medicine, Journal Year: 2022, Volume and Issue: 11(13), P. 3621 - 3621

Published: June 23, 2022

The purpose of this study was to evaluate retinal and choroidal microvascular alterations with optical coherence tomography angiography (OCTA) in COVID-19 patients hospitalized because bilateral pneumonia caused by SARS-CoV-2. vessel density (VD) foveal avascular zone (FAZ) 63 SARS-CoV-2 who had positive polymerase chain reaction (PCR) tests recovered after receiving treatment 45 healthy age- gender-matched controls were evaluated compared using OCTA the superficial capillary plexus (SCP) deep (DCP). VD also estimated both groups choriocapillaris (CC). In patients, there a statistically significant difference between control group (FAZs) (FAZd) (p = 0.000). significantly lower area 0.046). There no changes superior, inferior, nasal, temporal quadrants plexus, or choriocapillaris. not plexus. may affect vasculature, causing ischemia, enlargement FAZ, lowering area. Routine ophthalmic examination infection should be considered course post-infectious rehabilitation.

Language: Английский

---

Glaucoma Classification using Light Vision Transformer

EAI Endorsed Transactions on Pervasive Health and Technology, Journal Year: 2023, Volume and Issue: 9

Published: Sept. 21, 2023

INTRODUCTION: Nowadays one of the primary causes permanent blindness is glaucoma. Due to trade-offs, it makes in terms portability, size, and cost, fundus imaging most widely used glaucoma screening technique. OBJECTIVES:To boost accuracy,focusing on less execution time, resources consumption, we have proposed a vision transformer-based model with data pre-processing techniques which fix classification problems. METHODS: Convolution “local” technique by CNNs that restricted limited area around an image. Self-attention, Vision Transformers, “global” action since gathers from whole This possible for ViT successfully collect far-off semantic relevance Several optimizers, including Adamax, SGD, RMSprop, Adadelta, Adafactor, Nadam, Adagrad, were studied this paper. We trained tested Transformer IEEE Fundus image dataset having 1750 Healthy Glaucoma images. Additionally, was preprocessed using resizing, auto-rotation, auto-adjust contrast adaptive equalization. RESULTS: Results also show Nadam Optimizer increased accuracy up 97% equalized preprocessing followed auto rotate resizing operations. CONCLUSION: The experimental findings shows transformer based spurred revolution computer reduced time training classification.

Language: Английский

---

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

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

---