Tortuosity Index Calculations in Retinal Images: Some Criticalities Arising from Commonly Used Approaches

A growing body of research in retinal imaging is recently considering vascular tortuosity measures or indexes, with definitions and methods mostly derived from cardiovascular research. However, retinal microvasculature has its own peculiarities that must be considered in order to produce reliable me...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Francesco Martelli, Claudia Giacomozzi
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/a22c23997ccb43198cd5b49efae34772
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:a22c23997ccb43198cd5b49efae34772
record_format dspace
spelling oai:doaj.org-article:a22c23997ccb43198cd5b49efae347722021-11-25T17:58:35ZTortuosity Index Calculations in Retinal Images: Some Criticalities Arising from Commonly Used Approaches10.3390/info121104662078-2489https://doaj.org/article/a22c23997ccb43198cd5b49efae347722021-11-01T00:00:00Zhttps://www.mdpi.com/2078-2489/12/11/466https://doaj.org/toc/2078-2489A growing body of research in retinal imaging is recently considering vascular tortuosity measures or indexes, with definitions and methods mostly derived from cardiovascular research. However, retinal microvasculature has its own peculiarities that must be considered in order to produce reliable measurements. This study analyzed and compared various derived metrics (e.g., TI, TI_avg, TI*CV) across four existing computational workflows. Specifically, the implementation of the models on two critical OCT images highlighted main pitfalls of the methods, which may fail in reliably differentiating a highly tortuous image from a normal one. A tentative, encouraging approach to mitigate the issue on the same OCT exemplificative images is described in the paper, based on the suggested index TI*CV.Francesco MartelliClaudia GiacomozziMDPI AGarticleoptical coherence tomographyvessel tortuositybiomedical image processingInformation technologyT58.5-58.64ENInformation, Vol 12, Iss 466, p 466 (2021)
institution DOAJ
collection DOAJ
language EN
topic optical coherence tomography
vessel tortuosity
biomedical image processing
Information technology
T58.5-58.64
spellingShingle optical coherence tomography
vessel tortuosity
biomedical image processing
Information technology
T58.5-58.64
Francesco Martelli
Claudia Giacomozzi
Tortuosity Index Calculations in Retinal Images: Some Criticalities Arising from Commonly Used Approaches
description A growing body of research in retinal imaging is recently considering vascular tortuosity measures or indexes, with definitions and methods mostly derived from cardiovascular research. However, retinal microvasculature has its own peculiarities that must be considered in order to produce reliable measurements. This study analyzed and compared various derived metrics (e.g., TI, TI_avg, TI*CV) across four existing computational workflows. Specifically, the implementation of the models on two critical OCT images highlighted main pitfalls of the methods, which may fail in reliably differentiating a highly tortuous image from a normal one. A tentative, encouraging approach to mitigate the issue on the same OCT exemplificative images is described in the paper, based on the suggested index TI*CV.
format article
author Francesco Martelli
Claudia Giacomozzi
author_facet Francesco Martelli
Claudia Giacomozzi
author_sort Francesco Martelli
title Tortuosity Index Calculations in Retinal Images: Some Criticalities Arising from Commonly Used Approaches
title_short Tortuosity Index Calculations in Retinal Images: Some Criticalities Arising from Commonly Used Approaches
title_full Tortuosity Index Calculations in Retinal Images: Some Criticalities Arising from Commonly Used Approaches
title_fullStr Tortuosity Index Calculations in Retinal Images: Some Criticalities Arising from Commonly Used Approaches
title_full_unstemmed Tortuosity Index Calculations in Retinal Images: Some Criticalities Arising from Commonly Used Approaches
title_sort tortuosity index calculations in retinal images: some criticalities arising from commonly used approaches
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/a22c23997ccb43198cd5b49efae34772
work_keys_str_mv AT francescomartelli tortuosityindexcalculationsinretinalimagessomecriticalitiesarisingfromcommonlyusedapproaches
AT claudiagiacomozzi tortuosityindexcalculationsinretinalimagessomecriticalitiesarisingfromcommonlyusedapproaches
_version_ 1718411763867713536