A Hybrid VGG16‐ViT Approach With Image Processing Techniques for Improved White Blood Cell Classification and Disease Diagnosis: A Retrospective Study

ABSTRACT Background and Aims White Blood Cells (WBCs) are essential for immune defense against infections. Automated WBC identification from microscopic images aids in diagnosing diseases like leukemia and AIDS. However, the complexity of WBC morphology due to varying maturation stages and staining...

Full description

Saved in:
Bibliographic Details
Main Authors: Md Shahin Ali, Md. Maruf Hossain, Md. Mahfuz Ahmed, Kazi Rubaya Nowrin, S. M. Mahim, Shakib Al Hasan, Moutushi Akter Kona, Md Shafiqul Islam, Kazi Mowdud Ahmed, Md Mahbubur Rahman, Md Khairul Islam
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:Health Science Reports
Subjects:
Online Access:https://doi.org/10.1002/hsr2.70859
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850120155392114688
author Md Shahin Ali
Md. Maruf Hossain
Md. Mahfuz Ahmed
Kazi Rubaya Nowrin
S. M. Mahim
Shakib Al Hasan
Moutushi Akter Kona
Md Shafiqul Islam
Kazi Mowdud Ahmed
Md Mahbubur Rahman
Md Khairul Islam
author_facet Md Shahin Ali
Md. Maruf Hossain
Md. Mahfuz Ahmed
Kazi Rubaya Nowrin
S. M. Mahim
Shakib Al Hasan
Moutushi Akter Kona
Md Shafiqul Islam
Kazi Mowdud Ahmed
Md Mahbubur Rahman
Md Khairul Islam
author_sort Md Shahin Ali
collection DOAJ
description ABSTRACT Background and Aims White Blood Cells (WBCs) are essential for immune defense against infections. Automated WBC identification from microscopic images aids in diagnosing diseases like leukemia and AIDS. However, the complexity of WBC morphology due to varying maturation stages and staining techniques complicates classification. This study aims to enhance WBC detection and classification using a hybrid VGG16‐Vision Transformer (VGG16‐ViT) model. Methods To enhance the efficiency of the classification process, preprocessing techniques such as data normalization, categorical variable encoding, feature extraction, and data augmentation were employed in conjunction with the proposed model before the training phase. The VGG16‐ViT model was trained and evaluated on two datasets to measure its performance. Results The overall success rate for classifying WBCs was 98.12% for Dataset 1% and 99.60% for Dataset 2. The measured average precision, recall, and F1‐score values were 98.59%, 98.23%, and 98.35% for Dataset 1; similarly, 98.95%, 99.98%, and 99.48% for Dataset 2. The experimental results indicated that the classification success was strengthened when the proposed model was combined with specific preprocessing procedures, outperforming existing research. Conclusion The hybrid VGG16‐ViT model, combined with effective preprocessing techniques, significantly improved the detection and classification of WBCs. Additionally, the training approach of the proposed model is less time‐consuming than existing transfer learning models, making it a valuable tool for assisting medical professionals in diagnosing diseases related to WBCs.
format Article
id doaj-art-6824ae44cc6248ed867dbd9739f6beb1
institution OA Journals
issn 2398-8835
language English
publishDate 2025-06-01
publisher Wiley
record_format Article
series Health Science Reports
spelling doaj-art-6824ae44cc6248ed867dbd9739f6beb12025-08-20T02:35:26ZengWileyHealth Science Reports2398-88352025-06-0186n/an/a10.1002/hsr2.70859A Hybrid VGG16‐ViT Approach With Image Processing Techniques for Improved White Blood Cell Classification and Disease Diagnosis: A Retrospective StudyMd Shahin Ali0Md. Maruf Hossain1Md. Mahfuz Ahmed2Kazi Rubaya Nowrin3S. M. Mahim4Shakib Al Hasan5Moutushi Akter Kona6Md Shafiqul Islam7Kazi Mowdud Ahmed8Md Mahbubur Rahman9Md Khairul Islam10Department of Biomedical Engineering Islamic University Kushtia BangladeshDepartment of Biomedical Engineering Islamic University Kushtia BangladeshDepartment of Biomedical Engineering Islamic University Kushtia BangladeshDepartment of Biomedical Engineering Islamic University Kushtia BangladeshDepartment of Biomedical Engineering Islamic University Kushtia BangladeshDepartment of Biomedical Engineering Islamic University Kushtia BangladeshDepartment of Biomedical Engineering Islamic University Kushtia BangladeshDepartment of Electrical and Electronic Engineering Islamic University Kushtia BangladeshDepartment of Information and Communication Technology Islamic University Kushtia BangladeshDepartment of Information and Communication Technology Islamic University Kushtia BangladeshDepartment of Biomedical Engineering Islamic University Kushtia BangladeshABSTRACT Background and Aims White Blood Cells (WBCs) are essential for immune defense against infections. Automated WBC identification from microscopic images aids in diagnosing diseases like leukemia and AIDS. However, the complexity of WBC morphology due to varying maturation stages and staining techniques complicates classification. This study aims to enhance WBC detection and classification using a hybrid VGG16‐Vision Transformer (VGG16‐ViT) model. Methods To enhance the efficiency of the classification process, preprocessing techniques such as data normalization, categorical variable encoding, feature extraction, and data augmentation were employed in conjunction with the proposed model before the training phase. The VGG16‐ViT model was trained and evaluated on two datasets to measure its performance. Results The overall success rate for classifying WBCs was 98.12% for Dataset 1% and 99.60% for Dataset 2. The measured average precision, recall, and F1‐score values were 98.59%, 98.23%, and 98.35% for Dataset 1; similarly, 98.95%, 99.98%, and 99.48% for Dataset 2. The experimental results indicated that the classification success was strengthened when the proposed model was combined with specific preprocessing procedures, outperforming existing research. Conclusion The hybrid VGG16‐ViT model, combined with effective preprocessing techniques, significantly improved the detection and classification of WBCs. Additionally, the training approach of the proposed model is less time‐consuming than existing transfer learning models, making it a valuable tool for assisting medical professionals in diagnosing diseases related to WBCs.https://doi.org/10.1002/hsr2.70859feature extractionGrad‐CAMmedical image processingVGG16‐ViTwhite blood cell
spellingShingle Md Shahin Ali
Md. Maruf Hossain
Md. Mahfuz Ahmed
Kazi Rubaya Nowrin
S. M. Mahim
Shakib Al Hasan
Moutushi Akter Kona
Md Shafiqul Islam
Kazi Mowdud Ahmed
Md Mahbubur Rahman
Md Khairul Islam
A Hybrid VGG16‐ViT Approach With Image Processing Techniques for Improved White Blood Cell Classification and Disease Diagnosis: A Retrospective Study
Health Science Reports
feature extraction
Grad‐CAM
medical image processing
VGG16‐ViT
white blood cell
title A Hybrid VGG16‐ViT Approach With Image Processing Techniques for Improved White Blood Cell Classification and Disease Diagnosis: A Retrospective Study
title_full A Hybrid VGG16‐ViT Approach With Image Processing Techniques for Improved White Blood Cell Classification and Disease Diagnosis: A Retrospective Study
title_fullStr A Hybrid VGG16‐ViT Approach With Image Processing Techniques for Improved White Blood Cell Classification and Disease Diagnosis: A Retrospective Study
title_full_unstemmed A Hybrid VGG16‐ViT Approach With Image Processing Techniques for Improved White Blood Cell Classification and Disease Diagnosis: A Retrospective Study
title_short A Hybrid VGG16‐ViT Approach With Image Processing Techniques for Improved White Blood Cell Classification and Disease Diagnosis: A Retrospective Study
title_sort hybrid vgg16 vit approach with image processing techniques for improved white blood cell classification and disease diagnosis a retrospective study
topic feature extraction
Grad‐CAM
medical image processing
VGG16‐ViT
white blood cell
url https://doi.org/10.1002/hsr2.70859
work_keys_str_mv AT mdshahinali ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdmarufhossain ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdmahfuzahmed ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT kazirubayanowrin ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT smmahim ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT shakibalhasan ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT moutushiakterkona ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdshafiqulislam ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT kazimowdudahmed ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdmahbuburrahman ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdkhairulislam ahybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdshahinali hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdmarufhossain hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdmahfuzahmed hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT kazirubayanowrin hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT smmahim hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT shakibalhasan hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT moutushiakterkona hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdshafiqulislam hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT kazimowdudahmed hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdmahbuburrahman hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy
AT mdkhairulislam hybridvgg16vitapproachwithimageprocessingtechniquesforimprovedwhitebloodcellclassificationanddiseasediagnosisaretrospectivestudy