Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis

Hypertensive retinopathy (HR) is a serious eye disease that can lead to permanent vision loss if not diagnosed early. The conventional diagnostic methods are subjective and time-consuming, so there is a need for an automated and reliable system. In this study, a three-stage method that provides high...

Full description

Saved in:
Bibliographic Details
Main Authors: Süleyman Burçin Şüyun, Mustafa Yurdakul, Şakir Taşdemir, Serkan Biliş
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/12/6485
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850156964138450944
author Süleyman Burçin Şüyun
Mustafa Yurdakul
Şakir Taşdemir
Serkan Biliş
author_facet Süleyman Burçin Şüyun
Mustafa Yurdakul
Şakir Taşdemir
Serkan Biliş
author_sort Süleyman Burçin Şüyun
collection DOAJ
description Hypertensive retinopathy (HR) is a serious eye disease that can lead to permanent vision loss if not diagnosed early. The conventional diagnostic methods are subjective and time-consuming, so there is a need for an automated and reliable system. In this study, a three-stage method that provides high accuracy in HR diagnosis is proposed. In the first stage, 14 well-known Convolutional Neural Network (CNN) models were evaluated, and the top three models were identified. Among these models, DenseNet169 achieved the highest accuracy rate of 87.73%. In the second stage, the deep features obtained from these three models were combined and classified using machine learning (ML) algorithms including Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The SVM with a sigmoid kernel achieved the best performance (92% accuracy). In the third stage, feature selection was performed using metaheuristic optimization techniques including Genetic Algorithm (GA), Artificial Bee Colony (ABC), Particle Swarm Optimization (PSO), and Harris Hawk Optimization (HHO). The HHO algorithm increased the classification accuracy to 94.66%, enhancing the model’s generalization ability and reducing misclassifications. The proposed method provides superior accuracy in the diagnosis of HR at different severity levels compared to single-model CNN approaches. These results demonstrate that the integration of Deep Learning (DL), ML, and optimization techniques holds significant potential in automated HR diagnosis.
format Article
id doaj-art-2d76b4c1fde94ea29ff04ced8aecfaa4
institution OA Journals
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2d76b4c1fde94ea29ff04ced8aecfaa42025-08-20T02:24:18ZengMDPI AGApplied Sciences2076-34172025-06-011512648510.3390/app15126485Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy DiagnosisSüleyman Burçin Şüyun0Mustafa Yurdakul1Şakir Taşdemir2Serkan Biliş3Computer Engineering Department, Engineering Faculty, Sinop University, Sinop 57000, TurkeyComputer Engineering Department, Engineering and Natural Sciences Faculty, Kırıkkale University, Kırıkkale 71450, TurkeyComputer Engineering Department, Technology Faculty, Selçuk University, Konya 42250, TurkeyEye Diseases Department, Batıgoz Medical Group Hospital, Izmir 35200, TurkeyHypertensive retinopathy (HR) is a serious eye disease that can lead to permanent vision loss if not diagnosed early. The conventional diagnostic methods are subjective and time-consuming, so there is a need for an automated and reliable system. In this study, a three-stage method that provides high accuracy in HR diagnosis is proposed. In the first stage, 14 well-known Convolutional Neural Network (CNN) models were evaluated, and the top three models were identified. Among these models, DenseNet169 achieved the highest accuracy rate of 87.73%. In the second stage, the deep features obtained from these three models were combined and classified using machine learning (ML) algorithms including Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The SVM with a sigmoid kernel achieved the best performance (92% accuracy). In the third stage, feature selection was performed using metaheuristic optimization techniques including Genetic Algorithm (GA), Artificial Bee Colony (ABC), Particle Swarm Optimization (PSO), and Harris Hawk Optimization (HHO). The HHO algorithm increased the classification accuracy to 94.66%, enhancing the model’s generalization ability and reducing misclassifications. The proposed method provides superior accuracy in the diagnosis of HR at different severity levels compared to single-model CNN approaches. These results demonstrate that the integration of Deep Learning (DL), ML, and optimization techniques holds significant potential in automated HR diagnosis.https://www.mdpi.com/2076-3417/15/12/6485Convolutional Neural Networkeye diseasefeature fusionHarris Hawk Optimizationhypertensive retinopathy
spellingShingle Süleyman Burçin Şüyun
Mustafa Yurdakul
Şakir Taşdemir
Serkan Biliş
Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis
Applied Sciences
Convolutional Neural Network
eye disease
feature fusion
Harris Hawk Optimization
hypertensive retinopathy
title Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis
title_full Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis
title_fullStr Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis
title_full_unstemmed Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis
title_short Triple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis
title_sort triple stream deep feature selection with metaheuristic optimization and machine learning for multi stage hypertensive retinopathy diagnosis
topic Convolutional Neural Network
eye disease
feature fusion
Harris Hawk Optimization
hypertensive retinopathy
url https://www.mdpi.com/2076-3417/15/12/6485
work_keys_str_mv AT suleymanburcinsuyun triplestreamdeepfeatureselectionwithmetaheuristicoptimizationandmachinelearningformultistagehypertensiveretinopathydiagnosis
AT mustafayurdakul triplestreamdeepfeatureselectionwithmetaheuristicoptimizationandmachinelearningformultistagehypertensiveretinopathydiagnosis
AT sakirtasdemir triplestreamdeepfeatureselectionwithmetaheuristicoptimizationandmachinelearningformultistagehypertensiveretinopathydiagnosis
AT serkanbilis triplestreamdeepfeatureselectionwithmetaheuristicoptimizationandmachinelearningformultistagehypertensiveretinopathydiagnosis