Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 31, 2026

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

Validation of a Rule-Based Automated Method for RPE Cell Detection Using Adaptive Optics Transscleral Flood

Masakazu Hiraoka^1,2, Marika Taniguchi¹, Leandre Fura³

¹Department of Ophthalmology, Kobe City Eye Hospital, Kobe, Hyogo, Japan.

Translational Vision Science & Technology

|May 29, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Decline in physical function and baseline depressive symptoms are associated with worsening asthma outcomes in older adults: A 12-month prospective cohort study.

Respiratory investigation·2026

Same author

RPE Abnormality Is a Potential Primary Cause for Retinal Degeneration in Mucopolysaccharidosis Type VI Patients and a Rat Model.

Investigative ophthalmology & visual science·2026

Same author

Genotype-Phenotype Correlations in RPGRIP1-Associated Retinal Dystrophy in a Nationwide Japanese Cohort.

American journal of ophthalmology·2026

Same author

Prospective natural history and clinical biomarkers of EYS-associated retinopathy in the KEYS study.

Scientific reports·2026

Same author

Earlier first-time memory clinic visits during the COVID-19 pandemic: A comparison of dementia severity and caregiver burden.

Journal of family medicine and primary care·2026

Same author

Survey of Mobile Phone Usage Among Patients With Cognitive Impairment.

Alzheimer disease and associated disorders·2026

This summary is machine-generated.

This study validated an automated method for detecting retinal pigment epithelium (RPE) cells in adaptive optics (AO) images. While stable, the automated RPE cell detection showed lower performance than human graders, indicating a need for further validation.

Area of Science:

Ophthalmology
Medical Imaging
Cell Biology

Background:

Retinal pigment epithelium (RPE) cell analysis is crucial for understanding retinal diseases.
Adaptive optics (AO) imaging techniques provide high-resolution visualization of the retina.
Quantitative assessment of RPE cells is challenging with current methods.

Purpose of the Study:

To validate a rule-based automated method for detecting RPE cells in AO transscleral flood illumination (AO-TFI) images.
To compare the automated method's performance against manual annotation and inter-grader agreement.
To assess the feasibility of automated RPE cell quantification using AO-TFI.

Main Methods:

A cross-sectional study analyzed AO-TFI images from healthy and retinitis pigmentosa (RP) eyes.

More Related Videos

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

Bioorthogonal Chemical Imaging of Cell Metabolism Regulated by Aromatic Amino Acids

Bioorthogonal Chemical Imaging of Cell Metabolism Regulated by Aromatic Amino Acids

Published on: May 12, 2023

Related Experiment Videos

Last Updated: May 31, 2026

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

Bioorthogonal Chemical Imaging of Cell Metabolism Regulated by Aromatic Amino Acids

Bioorthogonal Chemical Imaging of Cell Metabolism Regulated by Aromatic Amino Acids

Published on: May 12, 2023

A rule-based algorithm was developed for RPE cell detection based on local maxima and distance filtering.

Automated detections were compared to manual annotations (ground truth) using Precision, Recall, and F1-score.

Inter-grader agreement was assessed to establish a benchmark for performance.

Main Results:

The automated RPE cell detection method demonstrated stable performance across different regions of interest (ROIs).
F1-scores for automated detection ranged from 0.55 to 0.92, with a micro-averaged F1-score of 0.80.
Automated detection performance was significantly lower than inter-grader agreement in both healthy and RP eyes.
Performance remained stable across various signal-to-noise ratios (SNRs).

Conclusions:

The rule-based automated AO-TFI method for RPE cell detection shows promise as a proof-of-concept for quantitative analysis.
The method's performance, while stable, did not reach the level of human expert agreement.
Further validation with larger datasets is necessary to refine the method for clinical applications and biomarker development.