Graph-Based Radiomics Feature Extraction From 2D Retina Images

Medical image analysis offers valuable visual support for clinical decision-making, yet the incorporation of quantitative data is essential for deeper diagnostic insight. The radiomics approach addresses this need by combining quantitative image analysis with Machine Learning (ML) techniques, furthe...

Full description

Saved in:
Bibliographic Details
Main Authors: Ofelio Jorreia, Nuno Goncalves, Rui Cortesao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11079971/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849245893537038336
author Ofelio Jorreia
Nuno Goncalves
Rui Cortesao
author_facet Ofelio Jorreia
Nuno Goncalves
Rui Cortesao
author_sort Ofelio Jorreia
collection DOAJ
description Medical image analysis offers valuable visual support for clinical decision-making, yet the incorporation of quantitative data is essential for deeper diagnostic insight. The radiomics approach addresses this need by combining quantitative image analysis with Machine Learning (ML) techniques, further enhancing Explainable Artificial Intelligence (XAI) for clinical applications. While working with two-dimensional (2D) images derived from volumetric data offers computational advantages, accurately estimating structural properties within these images remains challenging. Within the radiomics framework, this study introduces a methodology to distinguish bifurcations from other structural variations in 2D local fragments of retinal vasculature. Using a publicly available dataset of 29 retinal images, we extracted 1003 feature fragments for experiments. The regions of interest (ROIs) are identified using morphological image processing techniques. Specifically, candidate points are detected by applying structuring elements (SEs) to the skeletonized and binarized vasculature. From each candidate point, a local fragment of <inline-formula> <tex-math notation="LaTeX">$35\times 35$ </tex-math></inline-formula> pixels is extracted and used as input to the classification model. A Convolutional Neural Network (CNN) model, tailored for small image datasets and binary classification tasks is created. The trained model achieved an accuracy of 94.95% in correctly identifying bifurcation points. Based on predicted bifurcation points and blood vessel segments, we use the Graph-Based Radiomics Feature Extraction Algorithm (Graph-BRFExtract) to extract the adjacency matrix. This matrix serves as mathematical representation of the retinal vascular network, constituting a novel form of graph-based radiomic features.
format Article
id doaj-art-e0acc0990f2e425fa0c6fe266c0cd836
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e0acc0990f2e425fa0c6fe266c0cd8362025-08-20T03:58:40ZengIEEEIEEE Access2169-35362025-01-011312535912537310.1109/ACCESS.2025.358881711079971Graph-Based Radiomics Feature Extraction From 2D Retina ImagesOfelio Jorreia0https://orcid.org/0000-0001-5166-8826Nuno Goncalves1https://orcid.org/0000-0002-1854-049XRui Cortesao2https://orcid.org/0000-0003-1338-3138Department of Electrical and Computer Engineering, Institute of Systems and Robotics, University of Coimbra, Coimbra, PortugalInstitute of Systems and Robotics, University of Coimbra, Coimbra, PortugalInstitute of Systems and Robotics, University of Coimbra, Coimbra, PortugalMedical image analysis offers valuable visual support for clinical decision-making, yet the incorporation of quantitative data is essential for deeper diagnostic insight. The radiomics approach addresses this need by combining quantitative image analysis with Machine Learning (ML) techniques, further enhancing Explainable Artificial Intelligence (XAI) for clinical applications. While working with two-dimensional (2D) images derived from volumetric data offers computational advantages, accurately estimating structural properties within these images remains challenging. Within the radiomics framework, this study introduces a methodology to distinguish bifurcations from other structural variations in 2D local fragments of retinal vasculature. Using a publicly available dataset of 29 retinal images, we extracted 1003 feature fragments for experiments. The regions of interest (ROIs) are identified using morphological image processing techniques. Specifically, candidate points are detected by applying structuring elements (SEs) to the skeletonized and binarized vasculature. From each candidate point, a local fragment of <inline-formula> <tex-math notation="LaTeX">$35\times 35$ </tex-math></inline-formula> pixels is extracted and used as input to the classification model. A Convolutional Neural Network (CNN) model, tailored for small image datasets and binary classification tasks is created. The trained model achieved an accuracy of 94.95% in correctly identifying bifurcation points. Based on predicted bifurcation points and blood vessel segments, we use the Graph-Based Radiomics Feature Extraction Algorithm (Graph-BRFExtract) to extract the adjacency matrix. This matrix serves as mathematical representation of the retinal vascular network, constituting a novel form of graph-based radiomic features.https://ieeexplore.ieee.org/document/11079971/Bifurcationblood vasculatureexplainable AIgraph-structured datainterpretabilityradiomics
spellingShingle Ofelio Jorreia
Nuno Goncalves
Rui Cortesao
Graph-Based Radiomics Feature Extraction From 2D Retina Images
IEEE Access
Bifurcation
blood vasculature
explainable AI
graph-structured data
interpretability
radiomics
title Graph-Based Radiomics Feature Extraction From 2D Retina Images
title_full Graph-Based Radiomics Feature Extraction From 2D Retina Images
title_fullStr Graph-Based Radiomics Feature Extraction From 2D Retina Images
title_full_unstemmed Graph-Based Radiomics Feature Extraction From 2D Retina Images
title_short Graph-Based Radiomics Feature Extraction From 2D Retina Images
title_sort graph based radiomics feature extraction from 2d retina images
topic Bifurcation
blood vasculature
explainable AI
graph-structured data
interpretability
radiomics
url https://ieeexplore.ieee.org/document/11079971/
work_keys_str_mv AT ofeliojorreia graphbasedradiomicsfeatureextractionfrom2dretinaimages
AT nunogoncalves graphbasedradiomicsfeatureextractionfrom2dretinaimages
AT ruicortesao graphbasedradiomicsfeatureextractionfrom2dretinaimages