Improving Automatic Coronary Stenosis Classification Using a Hybrid Metaheuristic with Diversity Control

This study proposes a novel Hybrid Metaheuristic with explicit diversity control, aimed at finding an optimal feature subset by thoroughly exploring the search space to prevent premature convergence. <b>Background/Objectives</b>: Unlike traditional evolutionary computing techniques, whic...

Full description

Saved in:
Bibliographic Details
Main Authors: Miguel-Angel Gil-Rios, Ivan Cruz-Aceves, Arturo Hernandez-Aguirre, Martha-Alicia Hernandez-Gonzalez, Sergio-Eduardo Solorio-Meza
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/21/2372
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850197064282013696
author Miguel-Angel Gil-Rios
Ivan Cruz-Aceves
Arturo Hernandez-Aguirre
Martha-Alicia Hernandez-Gonzalez
Sergio-Eduardo Solorio-Meza
author_facet Miguel-Angel Gil-Rios
Ivan Cruz-Aceves
Arturo Hernandez-Aguirre
Martha-Alicia Hernandez-Gonzalez
Sergio-Eduardo Solorio-Meza
author_sort Miguel-Angel Gil-Rios
collection DOAJ
description This study proposes a novel Hybrid Metaheuristic with explicit diversity control, aimed at finding an optimal feature subset by thoroughly exploring the search space to prevent premature convergence. <b>Background/Objectives</b>: Unlike traditional evolutionary computing techniques, which only consider the best individuals in a population, the proposed strategy also considers the worst individuals under certain conditions. In consequence, feature selection frequencies tend to be more uniform, decreasing the probability of premature convergent results and local-optima solutions. <b>Methods</b>: An image database containing 608 images, evenly balanced between positive and negative coronary stenosis cases, was used for experiments. A total of 473 features, including intensity, texture, and morphological types, were extracted from the image bank. A Support Vector Machine was employed to classify positive and negative stenosis cases, with Accuracy and the Jaccard Coefficient used as performance metrics. <b>Results</b>: The proposed strategy achieved a classification rate of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.92</mn></mrow></semantics></math></inline-formula> for Accuracy and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.85</mn></mrow></semantics></math></inline-formula> for the Jaccard Coefficient, obtaining a subset of 16 features, which represents a discrimination rate of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.97</mn></mrow></semantics></math></inline-formula> from the 473 initial features. <b>Conclusions</b>: The Hybrid Metaheuristic with explicit diversity control improved the classification performance of coronary stenosis cases compared to previous literature. Based on the achieved results, the identified feature subset demonstrates potential for use in clinical practice, particularly in decision-support information systems.
format Article
id doaj-art-9384d80a00414039a7009e0de82a2ddd
institution OA Journals
issn 2075-4418
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-9384d80a00414039a7009e0de82a2ddd2025-08-20T02:13:16ZengMDPI AGDiagnostics2075-44182024-10-011421237210.3390/diagnostics14212372Improving Automatic Coronary Stenosis Classification Using a Hybrid Metaheuristic with Diversity ControlMiguel-Angel Gil-Rios0Ivan Cruz-Aceves1Arturo Hernandez-Aguirre2Martha-Alicia Hernandez-Gonzalez3Sergio-Eduardo Solorio-Meza4Universidad Área Académica de Tecnologías de la Información, Universidad Tecnológica de León, Blvd. Universidad Tecnológica 225, Col. San Carlos, León 37670, MexicoCONAHCYT, Consejo Nacional de Humanidades, Ciencia y Tecnología (CONAHCYT), Centro de Investigación en Matemáticas (CIMAT), A.C., Jalisco S/N, Col. Valenciana, Guanajuato 36000, MexicoCentro de Investigación en Matemáticas (CIMAT), A.C., Jalisco S/N, Col. Valenciana, Guanajuato 36000, MexicoUnidad Médica de Alta Especialidad (UMAE), Hospital de Especialidades No.1. Centro Médico Nacional del Bajio, Instituto Mexicano del Seguro Social (IMSS), Blvd. Adolfo López Mateos S/N, León 37150, MexicoDivisión de Ciencias e Ingenierías, Universidad de Guanajuato, Campus León, Loma del Bosque 103, Col. Lomas del Campestre, León 37150, MexicoThis study proposes a novel Hybrid Metaheuristic with explicit diversity control, aimed at finding an optimal feature subset by thoroughly exploring the search space to prevent premature convergence. <b>Background/Objectives</b>: Unlike traditional evolutionary computing techniques, which only consider the best individuals in a population, the proposed strategy also considers the worst individuals under certain conditions. In consequence, feature selection frequencies tend to be more uniform, decreasing the probability of premature convergent results and local-optima solutions. <b>Methods</b>: An image database containing 608 images, evenly balanced between positive and negative coronary stenosis cases, was used for experiments. A total of 473 features, including intensity, texture, and morphological types, were extracted from the image bank. A Support Vector Machine was employed to classify positive and negative stenosis cases, with Accuracy and the Jaccard Coefficient used as performance metrics. <b>Results</b>: The proposed strategy achieved a classification rate of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.92</mn></mrow></semantics></math></inline-formula> for Accuracy and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.85</mn></mrow></semantics></math></inline-formula> for the Jaccard Coefficient, obtaining a subset of 16 features, which represents a discrimination rate of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.97</mn></mrow></semantics></math></inline-formula> from the 473 initial features. <b>Conclusions</b>: The Hybrid Metaheuristic with explicit diversity control improved the classification performance of coronary stenosis cases compared to previous literature. Based on the achieved results, the identified feature subset demonstrates potential for use in clinical practice, particularly in decision-support information systems.https://www.mdpi.com/2075-4418/14/21/2372coronary angiographyevolutionary algorithmfeature selectionpopulation diversitystenosis classification
spellingShingle Miguel-Angel Gil-Rios
Ivan Cruz-Aceves
Arturo Hernandez-Aguirre
Martha-Alicia Hernandez-Gonzalez
Sergio-Eduardo Solorio-Meza
Improving Automatic Coronary Stenosis Classification Using a Hybrid Metaheuristic with Diversity Control
Diagnostics
coronary angiography
evolutionary algorithm
feature selection
population diversity
stenosis classification
title Improving Automatic Coronary Stenosis Classification Using a Hybrid Metaheuristic with Diversity Control
title_full Improving Automatic Coronary Stenosis Classification Using a Hybrid Metaheuristic with Diversity Control
title_fullStr Improving Automatic Coronary Stenosis Classification Using a Hybrid Metaheuristic with Diversity Control
title_full_unstemmed Improving Automatic Coronary Stenosis Classification Using a Hybrid Metaheuristic with Diversity Control
title_short Improving Automatic Coronary Stenosis Classification Using a Hybrid Metaheuristic with Diversity Control
title_sort improving automatic coronary stenosis classification using a hybrid metaheuristic with diversity control
topic coronary angiography
evolutionary algorithm
feature selection
population diversity
stenosis classification
url https://www.mdpi.com/2075-4418/14/21/2372
work_keys_str_mv AT miguelangelgilrios improvingautomaticcoronarystenosisclassificationusingahybridmetaheuristicwithdiversitycontrol
AT ivancruzaceves improvingautomaticcoronarystenosisclassificationusingahybridmetaheuristicwithdiversitycontrol
AT arturohernandezaguirre improvingautomaticcoronarystenosisclassificationusingahybridmetaheuristicwithdiversitycontrol
AT marthaaliciahernandezgonzalez improvingautomaticcoronarystenosisclassificationusingahybridmetaheuristicwithdiversitycontrol
AT sergioeduardosoloriomeza improvingautomaticcoronarystenosisclassificationusingahybridmetaheuristicwithdiversitycontrol