Modeling and recognition of retinal blood vessels tortuosity in ROP plus disease: A hybrid segmentation - classification scheme

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00843989%3A_____%2F25%3AE0111657" target="_blank" >RIV/00843989:_____/25:E0111657 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61988987:17110/25:A2603DN5 RIV/61989100:27240/25:10257077

Výsledek na webu

<a href="https://onlinelibrary.wiley.com/doi/10.1155/int/6688133" target="_blank" >https://onlinelibrary.wiley.com/doi/10.1155/int/6688133</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1155/int/6688133" target="_blank" >10.1155/int/6688133</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Modeling and recognition of retinal blood vessels tortuosity in ROP plus disease: A hybrid segmentation - classification scheme

Popis výsledku v původním jazyce

Retinopathy of prematurity (ROP) remains a significant cause of childhood blindness despite advancements in neonatal care. Identifying the plus form of ROP, characterized by dilated and tortuous blood vessels, is crucial for timely intervention. This study introduces an intelligent segmentation–classification system for the autonomous detection of retinal blood vessels and the classification of ROP plus form. Utilizing Clarity RetCam 3 images, our system employs morphological image processing and convolutional neural networks (CNNs) for segmentation and classification, respectively. Testing on a dataset of premature infants’ retinal images demonstrates high segmentation accuracy (median = 0.974) and superior classification performance (accuracy = 0.975, sensitivity = 0.950, and specificity = 1). In addition, the system exhibits versatility, with successful segmentation in adult retinal images from public databases. These findings highlight the system’s potential for clinical use in retinal vessel identification, feature extraction, and ROP plus form classification. The proposed system is capable of effectively identifying retinal blood vessels from both alternatives including adult and premature born retinal images with a high accuracy in contrast to related studies. Thus, this system has the potential to be used in clinical practice for retinal blood vessels’ identification, retinal blood vessels’ feature extraction, and ROP plus form classification.

Název v anglickém jazyce

Modeling and recognition of retinal blood vessels tortuosity in ROP plus disease: A hybrid segmentation - classification scheme

Popis výsledku anglicky

Retinopathy of prematurity (ROP) remains a significant cause of childhood blindness despite advancements in neonatal care. Identifying the plus form of ROP, characterized by dilated and tortuous blood vessels, is crucial for timely intervention. This study introduces an intelligent segmentation–classification system for the autonomous detection of retinal blood vessels and the classification of ROP plus form. Utilizing Clarity RetCam 3 images, our system employs morphological image processing and convolutional neural networks (CNNs) for segmentation and classification, respectively. Testing on a dataset of premature infants’ retinal images demonstrates high segmentation accuracy (median = 0.974) and superior classification performance (accuracy = 0.975, sensitivity = 0.950, and specificity = 1). In addition, the system exhibits versatility, with successful segmentation in adult retinal images from public databases. These findings highlight the system’s potential for clinical use in retinal vessel identification, feature extraction, and ROP plus form classification. The proposed system is capable of effectively identifying retinal blood vessels from both alternatives including adult and premature born retinal images with a high accuracy in contrast to related studies. Thus, this system has the potential to be used in clinical practice for retinal blood vessels’ identification, retinal blood vessels’ feature extraction, and ROP plus form classification.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

30207 - Ophthalmology

Projekt

—

Návaznosti

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

International journal of intelligent systems

ISSN

0884-8173

e-ISSN

1098-111X

Svazek periodika

2025

Číslo periodika v rámci svazku

article 6688133

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

29

Strana od-do

1-29

Kód UT WoS článku

001431379800001

EID výsledku v databázi Scopus

2-s2.0-105000760610