Automated multi-model framework for malaria detection using deep learning and feature fusion

Abstract Malaria remains a critical global health challenge, particularly in tropical and subtropical regions. While traditional methods for diagnosis are effective, they face some limitations related to accuracy, time consumption, and manual effort. This study proposes an advanced, automated diagno...

Full description

Saved in:
Bibliographic Details
Main Authors: Osama R. Shahin, Hamoud H. Alshammari, Raed N. Alabdali, Ahmed M. Salaheldin, Neven Saleh
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-04784-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343683996942336
author Osama R. Shahin
Hamoud H. Alshammari
Raed N. Alabdali
Ahmed M. Salaheldin
Neven Saleh
author_facet Osama R. Shahin
Hamoud H. Alshammari
Raed N. Alabdali
Ahmed M. Salaheldin
Neven Saleh
author_sort Osama R. Shahin
collection DOAJ
description Abstract Malaria remains a critical global health challenge, particularly in tropical and subtropical regions. While traditional methods for diagnosis are effective, they face some limitations related to accuracy, time consumption, and manual effort. This study proposes an advanced, automated diagnostic framework for malaria detection using a multi-model architecture integrating deep learning and machine learning techniques. The framework employs a transfer learning approach that incorporates ResNet 50, VGG16, and DenseNet-201 for feature extraction. This is followed by feature fusion and dimensionality reduction via principal component analysis. A hybrid scheme that combines support vector machine and long short-term memory networks is used for classification. A majority voting mechanism aggregates outputs from all models to enhance prediction robustness. The approach was validated on a publicly available dataset comprising 27,558 microscopic thin blood smear images. The results demonstrated superior performance, achieving an accuracy of 96.47%, sensitivity of 96.03%, specificity of 96.90%, precision of 96.88%, and F1-score of 96.45% using the majority voting ensemble. Comparative analysis highlights the framework’s advancements over existing methods in diagnostic reliability and computational efficiency. This work underscores the potential of AI-driven solutions in advancing malaria diagnostics and lays the foundation for applications in other blood-borne diseases.
format Article
id doaj-art-e7d50afb2fd946468a3aeb5377bae171
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e7d50afb2fd946468a3aeb5377bae1712025-08-20T03:42:53ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-04784-wAutomated multi-model framework for malaria detection using deep learning and feature fusionOsama R. Shahin0Hamoud H. Alshammari1Raed N. Alabdali2Ahmed M. Salaheldin3Neven Saleh4Department of Computer Science, College of Computer and Information Sciences, Jouf UniversityDepartment of Information Systems, College of Computer and Information Sciences, Jouf UniversityDepartment of Computer Science, College of Computer and Information Sciences, Jouf UniversityBiomedical Engineering and Systems Department, Faculty of Engineering, Cairo UniversityBiomedical Engineering Department, Faculty of Engineering and Technology, Future University in EgyptAbstract Malaria remains a critical global health challenge, particularly in tropical and subtropical regions. While traditional methods for diagnosis are effective, they face some limitations related to accuracy, time consumption, and manual effort. This study proposes an advanced, automated diagnostic framework for malaria detection using a multi-model architecture integrating deep learning and machine learning techniques. The framework employs a transfer learning approach that incorporates ResNet 50, VGG16, and DenseNet-201 for feature extraction. This is followed by feature fusion and dimensionality reduction via principal component analysis. A hybrid scheme that combines support vector machine and long short-term memory networks is used for classification. A majority voting mechanism aggregates outputs from all models to enhance prediction robustness. The approach was validated on a publicly available dataset comprising 27,558 microscopic thin blood smear images. The results demonstrated superior performance, achieving an accuracy of 96.47%, sensitivity of 96.03%, specificity of 96.90%, precision of 96.88%, and F1-score of 96.45% using the majority voting ensemble. Comparative analysis highlights the framework’s advancements over existing methods in diagnostic reliability and computational efficiency. This work underscores the potential of AI-driven solutions in advancing malaria diagnostics and lays the foundation for applications in other blood-borne diseases.https://doi.org/10.1038/s41598-025-04784-wMalaria detectionAI solutionsFeature fusionCNNMajority voting
spellingShingle Osama R. Shahin
Hamoud H. Alshammari
Raed N. Alabdali
Ahmed M. Salaheldin
Neven Saleh
Automated multi-model framework for malaria detection using deep learning and feature fusion
Scientific Reports
Malaria detection
AI solutions
Feature fusion
CNN
Majority voting
title Automated multi-model framework for malaria detection using deep learning and feature fusion
title_full Automated multi-model framework for malaria detection using deep learning and feature fusion
title_fullStr Automated multi-model framework for malaria detection using deep learning and feature fusion
title_full_unstemmed Automated multi-model framework for malaria detection using deep learning and feature fusion
title_short Automated multi-model framework for malaria detection using deep learning and feature fusion
title_sort automated multi model framework for malaria detection using deep learning and feature fusion
topic Malaria detection
AI solutions
Feature fusion
CNN
Majority voting
url https://doi.org/10.1038/s41598-025-04784-w
work_keys_str_mv AT osamarshahin automatedmultimodelframeworkformalariadetectionusingdeeplearningandfeaturefusion
AT hamoudhalshammari automatedmultimodelframeworkformalariadetectionusingdeeplearningandfeaturefusion
AT raednalabdali automatedmultimodelframeworkformalariadetectionusingdeeplearningandfeaturefusion
AT ahmedmsalaheldin automatedmultimodelframeworkformalariadetectionusingdeeplearningandfeaturefusion
AT nevensaleh automatedmultimodelframeworkformalariadetectionusingdeeplearningandfeaturefusion