A Novel Hybrid Model for Brain Ischemic Stroke Detection Using Feature Fusion and Convolutional Block Attention Module

Brain stroke is the second leading cause of death worldwide, following ischemic heart disease. Ischemic stroke occurs when blood vessels are obstructed by a thrombus or other blockages. Prompt and accurate diagnosis of ischemic stroke is critical for patient survival. This study proposes a novel app...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmad Abumihsan, Amani Yousef Owda, Majdi Owda, Mobarak Abumohsen, Lampros Stergioulas, Mohammad Ahmad Abu Amer
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10916628/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770718513856512
author Ahmad Abumihsan
Amani Yousef Owda
Majdi Owda
Mobarak Abumohsen
Lampros Stergioulas
Mohammad Ahmad Abu Amer
author_facet Ahmad Abumihsan
Amani Yousef Owda
Majdi Owda
Mobarak Abumohsen
Lampros Stergioulas
Mohammad Ahmad Abu Amer
author_sort Ahmad Abumihsan
collection DOAJ
description Brain stroke is the second leading cause of death worldwide, following ischemic heart disease. Ischemic stroke occurs when blood vessels are obstructed by a thrombus or other blockages. Prompt and accurate diagnosis of ischemic stroke is critical for patient survival. This study proposes a novel approach for ischemic stroke detection from computed tomography (CT) images, utilizing a hybrid feature extraction technique combined with a convolutional block attention module (CBAM). The hybrid feature extraction leverages the strengths of two pre-trained models, DenseNet121 and MobileNetV3, through feature fusion to provide a comprehensive representation of brain CT images. The CBAM module is integrated to enhance the most relevant features by focusing on both channel and spatial attention mechanisms, significantly improving the model’s ability to detect ischemic strokes with high accuracy. The proposed approach was developed and evaluated on a unique first-hand dataset (Dataset 1) collected from the Specialized private Hospital in Palestine. To further demonstrate the robustness and generalizability of the method, it was also tested on a public dataset (Dataset 2). The results show that the proposed model achieved outstanding performance across all metrics: on Dataset 1, it reached an accuracy of 99.21%, precision of 99.17%, recall of 99.32%, and an F1-score of 99.24%. On Dataset 2, it achieved an accuracy of 98.73%, precision of 98.71%, recall of 98.74%, and an F1-score of 98.88%. The exceptional results are attributed to the power of feature fusion, which creates a robust and comprehensive feature representation. In addition to the CBAM, which refines the feature maps by selectively focusing on the most important channels and spatial regions in brain CT images. This has led to substantial improvement in the detection of ischemic stroke areas.
format Article
id doaj-art-917a0a54743a476e890ebe7b0de9b3cb
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-917a0a54743a476e890ebe7b0de9b3cb2025-08-20T03:02:55ZengIEEEIEEE Access2169-35362025-01-0113444664448310.1109/ACCESS.2025.354926910916628A Novel Hybrid Model for Brain Ischemic Stroke Detection Using Feature Fusion and Convolutional Block Attention ModuleAhmad Abumihsan0https://orcid.org/0000-0003-3154-445XAmani Yousef Owda1https://orcid.org/0000-0002-6104-9508Majdi Owda2https://orcid.org/0000-0002-7393-2381Mobarak Abumohsen3https://orcid.org/0000-0001-7263-4772Lampros Stergioulas4https://orcid.org/0000-0002-8615-2253Mohammad Ahmad Abu Amer5https://orcid.org/0009-0007-4513-1572Faculty of Artificial Intelligence and Data Science, Arab American University, Ramallah, PalestineDepartment of Natural, Engineering and Technology Sciences, Arab American University, Ramallah, PalestineFaculty of Artificial Intelligence and Data Science, UNESCO Chair in Data Science for Sustainable Development, Arab American University, Ramallah, PalestineDepartment of Natural, Engineering and Technology Sciences, Arab American University, Ramallah, PalestineFaculty of IT and Design, UNESCO Chair on AI and Data Science, The Hague University of Applied Sciences, The Hague, The NetherlandsFaculty of Medicine, Public Health and Nursing, Gadjah Mada University, Yogyakarta, IndonesiaBrain stroke is the second leading cause of death worldwide, following ischemic heart disease. Ischemic stroke occurs when blood vessels are obstructed by a thrombus or other blockages. Prompt and accurate diagnosis of ischemic stroke is critical for patient survival. This study proposes a novel approach for ischemic stroke detection from computed tomography (CT) images, utilizing a hybrid feature extraction technique combined with a convolutional block attention module (CBAM). The hybrid feature extraction leverages the strengths of two pre-trained models, DenseNet121 and MobileNetV3, through feature fusion to provide a comprehensive representation of brain CT images. The CBAM module is integrated to enhance the most relevant features by focusing on both channel and spatial attention mechanisms, significantly improving the model’s ability to detect ischemic strokes with high accuracy. The proposed approach was developed and evaluated on a unique first-hand dataset (Dataset 1) collected from the Specialized private Hospital in Palestine. To further demonstrate the robustness and generalizability of the method, it was also tested on a public dataset (Dataset 2). The results show that the proposed model achieved outstanding performance across all metrics: on Dataset 1, it reached an accuracy of 99.21%, precision of 99.17%, recall of 99.32%, and an F1-score of 99.24%. On Dataset 2, it achieved an accuracy of 98.73%, precision of 98.71%, recall of 98.74%, and an F1-score of 98.88%. The exceptional results are attributed to the power of feature fusion, which creates a robust and comprehensive feature representation. In addition to the CBAM, which refines the feature maps by selectively focusing on the most important channels and spatial regions in brain CT images. This has led to substantial improvement in the detection of ischemic stroke areas.https://ieeexplore.ieee.org/document/10916628/Brain strokecomputed tomographyfeature fusionconvolutional block attention moduleMobileNetV3DenseNet121
spellingShingle Ahmad Abumihsan
Amani Yousef Owda
Majdi Owda
Mobarak Abumohsen
Lampros Stergioulas
Mohammad Ahmad Abu Amer
A Novel Hybrid Model for Brain Ischemic Stroke Detection Using Feature Fusion and Convolutional Block Attention Module
IEEE Access
Brain stroke
computed tomography
feature fusion
convolutional block attention module
MobileNetV3
DenseNet121
title A Novel Hybrid Model for Brain Ischemic Stroke Detection Using Feature Fusion and Convolutional Block Attention Module
title_full A Novel Hybrid Model for Brain Ischemic Stroke Detection Using Feature Fusion and Convolutional Block Attention Module
title_fullStr A Novel Hybrid Model for Brain Ischemic Stroke Detection Using Feature Fusion and Convolutional Block Attention Module
title_full_unstemmed A Novel Hybrid Model for Brain Ischemic Stroke Detection Using Feature Fusion and Convolutional Block Attention Module
title_short A Novel Hybrid Model for Brain Ischemic Stroke Detection Using Feature Fusion and Convolutional Block Attention Module
title_sort novel hybrid model for brain ischemic stroke detection using feature fusion and convolutional block attention module
topic Brain stroke
computed tomography
feature fusion
convolutional block attention module
MobileNetV3
DenseNet121
url https://ieeexplore.ieee.org/document/10916628/
work_keys_str_mv AT ahmadabumihsan anovelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT amaniyousefowda anovelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT majdiowda anovelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT mobarakabumohsen anovelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT lamprosstergioulas anovelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT mohammadahmadabuamer anovelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT ahmadabumihsan novelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT amaniyousefowda novelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT majdiowda novelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT mobarakabumohsen novelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT lamprosstergioulas novelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule
AT mohammadahmadabuamer novelhybridmodelforbrainischemicstrokedetectionusingfeaturefusionandconvolutionalblockattentionmodule