Retinal Imaging and Analysis

Comparison of Deep Learning Tools for Optic Nerve Axon Quantification Finds Limited Generalizability on Independent Validation

This study evaluates three deep learning models for optic nerve axon quantification on a novel rat dataset, finding reduced performance compared to published benchmarks.

Explainable AI-Driven Diagnosis Model for Early Glaucoma Detection Using Grey-Wolf Optimized Extreme Learning Machine Approach

This paper proposes an explainable AI model for early glaucoma detection using a grey-wolf optimized extreme learning machine approach, achieving high accuracy on standard datasets.

Transocular detection of premotor Parkinson's disease via retinal capillary neurovascular coupling through functional OCT angiography

This paper introduces fOCTA-rNVC, a functional OCT angiography method that detects premotor Parkinson's disease by measuring retinal capillary neurovascular coupling changes, achieving 100% accuracy with minimal midbrain dopaminergic neuron loss.

Dual-Field Microvascular Segmentation: Hemodynamically-Consistent Attention Learning for Retinal Vasculature Mapping

DFMS-Net improves retinal microvascular segmentation by integrating geometric and functional fields to enhance vessel continuity and hemodynamic plausibility.

Machine-learning-based automated Schlemms canal volumetric segmentation for optical coherence tomography

This paper introduces SC-LSS, an automated tool for volumetric segmentation of Schlemms Canal in OCT images, showing high agreement with manual segmentation and detecting changes in SC size under different intraocular pressure conditions.

Retinal vascular dysfunction in the Mthfr677C>T mouse model of cerebrovascular disease

The paper examines retinal vascular changes in Mthfr677C>T mice, finding similarities to cerebrovascular changes in AD, suggesting retinal assessment as a potential biomarker.

Intraoperative Augmented Reality for Vitreoretinal Surgery using Edge Computing

This paper develops an AR system for vitreoretinal surgery using CNNs and edge computing to align pre-op and intra-op images in real-time, achieving 14 FPS and high registration accuracy.

Autoencoder-based phenotyping of ophthalmic images highlights genetic loci influencing retinal morphology and provides epidemiologically informative biomarkers.

The paper uses an autoencoder to derive retinal phenotypes from OCT images, identifies 118 genetic loci, and shows their relevance to retinal morphology and disease prediction.

Phenotypic and Genetic Characteristics of Retinal Vascular Parameters and their Association with Diseases

The paper analyzes retinal vascular phenotypes from fundus images and their genetic and disease associations using UK Biobank data, finding novel links between vascular features and health outcomes.

Foveolar drusen decrease fixation stability in presymptomatic AMD

This study links foveal drusen to altered fixation stability in presymptomatic AMD using high-speed retinal imaging.

3DVascNet: an automated software for segmentation and quantification of vascular networks in 3D

3DVascNet is a deep learning-based software that segments and quantifies 3D vascular networks, showing high performance and generalization across datasets and organs.

A Deep Learning Pipeline for Mapping in situ Network-level Neurovascular Coupling in Multi-photon Fluorescence Microscopy

The paper develops a deep learning pipeline to analyze microvascular network changes in response to neuronal activity using two-photon microscopy, revealing network-level coordination in blood flow adjustments.

Longitudinal fundus imaging and its genome-wide association analysis provide evidence for a human retinal aging clock

This paper develops a retinal aging clock from fundus images to predict chronological age and identifies genetic variants associated with accelerated aging.

Retinal microvascular and neuronal pathologies probed in vivo by adaptive optical two-photon fluorescence microscopy

This study uses adaptive optical two-photon fluorescence microscopy to investigate retinal microvascular and neuronal pathologies in vivo, revealing microvascular lesions and pharmacological effects.

MultiHeadGAN: A Deep Learning Method for Low Contrast Retinal Pigment Epithelium Cells Segmentation in Fluorescent Flatmount Microscopy Images

The paper introduces MultiHeadGAN, a deep learning method for segmenting low contrast RPE cells in impaired flatmount images, achieving high segmentation accuracy.

Learning low-dimensional generalizable naturalfeatures from retina using a U-net

The paper uses a U-net architecture to learn a low-dimensional, generalizable representation of time in natural scenes from retinal ganglion cell activity, achieving 17 ms resolution across different movies.

An Artificial Intelligence and Telemedicine Based Screening Tool to Identify Glaucoma Suspects from Color Fundus Imaging

The paper develops a deep learning classifier to identify glaucoma suspects from fundus images, achieving high accuracy in both training and external validation.

Self-supervised retinal thickness prediction enables deep learning from unlabeled data to boost classification of diabetic retinopathy

The paper proposes a self-supervised method to predict retinal thickness from fundus images, enabling efficient diabetic retinopathy classification with fewer annotations.

Mouse retinal cell behaviour in space and time using light sheet fluorescence microscopy

This paper demonstrates the feasibility of 3D/4D light-sheet fluorescence microscopy for imaging mouse retinal pathology, revealing new features in the OIR model and highlighting distorted morphology from flat-mounting.

Quantitative Measurements of Enlarged Perivascular Spaces in the Brain are Associated with Retinal Microvascular Parameters in Older Community-Dwelling Subjects

The paper quantifies perivascular spaces (PVS) in brain MRI and links them to retinal microvascular parameters in older adults, finding associations with arteriolar narrowing and reduced branching complexity.

Imaging single-cell blood flow in the smallest to largest vessels in the living retina

The paper measures single-cell blood flow across retinal vessels in mice using adaptive optics and provides an analysis pipeline for automated speed measurement.

Retinal microvasculature and cerebral small vessel disease in the Lothian Birth Cohort 1936 and Mild Stroke Study

The paper examines associations between retinal vascular parameters and cerebral small vessel disease in two cohorts, finding that arteriolar fractal dimension relates to white matter hyperintensities.

Generating perfusion maps from structural optical coherence tomography with artificial intelligence

This paper uses deep learning to generate perfusion maps from structural OCT images without expert labels, outperforming clinicians in fidelity.

Leveraging uncertainty information from deep neural networks for disease detection

This paper evaluates Bayesian uncertainty measures in deep learning for diabetic retinopathy detection, showing improved diagnostic performance through uncertainty-informed decision referral.

Deep-Learning Based, Automated Segmentation Of Macular Edema In Optical Coherence Tomography

The paper develops a CNN to segment macular edema in OCT images, achieving performance comparable to clinicians.