Fusion‐Brain‐Net: A Novel Deep Fusion Model for Brain Tumor Classification

ABSTRACT Problem Brain tumors are among the most prevalent and lethal diseases. Early diagnosis and precise treatment are crucial. However, the manual classification of brain tumors is a laborious and complex task. Aim This study aimed to develop a fusion model to address certain limitations of prev...

Full description

Saved in:
Bibliographic Details
Main Authors: Yasin Kaya, Ezgisu Akat, Serdar Yıldırım
Format: Article
Language:English
Published: Wiley 2025-05-01
Series:Brain and Behavior
Subjects:
Online Access:https://doi.org/10.1002/brb3.70520
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850141789440180224
author Yasin Kaya
Ezgisu Akat
Serdar Yıldırım
author_facet Yasin Kaya
Ezgisu Akat
Serdar Yıldırım
author_sort Yasin Kaya
collection DOAJ
description ABSTRACT Problem Brain tumors are among the most prevalent and lethal diseases. Early diagnosis and precise treatment are crucial. However, the manual classification of brain tumors is a laborious and complex task. Aim This study aimed to develop a fusion model to address certain limitations of previous works, such as covering diverse image modalities in various datasets. Method We presented a hybrid transfer learning model, Fusion‐Brain‐Net, aimed at automatic brain tumor classification. The proposed method included four stages: preprocessing and data augmentation, fusion of deep feature extractions, fine‐tuning, and classification. Integrating the pre‐trained CNN models, VGG16, ResNet50, and MobileNetV2, the model enhanced comprehensive feature extraction while mitigating overfitting issues, improving the model's performance. Results The proposed model was rigorously tested and verified on four public datasets: Br35H, Figshare, Nickparvar, and Sartaj. It achieved remarkable accuracy rates of 99.66%, 97.56%, 97.08%, and 93.74%, respectively. Conclusion The numerical results highlight that the model should be further investigated for potential use in computer‐aided diagnoses to improve clinical decision‐making.
format Article
id doaj-art-432444d2a5b541a0986baec2d104b415
institution OA Journals
issn 2162-3279
language English
publishDate 2025-05-01
publisher Wiley
record_format Article
series Brain and Behavior
spelling doaj-art-432444d2a5b541a0986baec2d104b4152025-08-20T02:29:19ZengWileyBrain and Behavior2162-32792025-05-01155n/an/a10.1002/brb3.70520Fusion‐Brain‐Net: A Novel Deep Fusion Model for Brain Tumor ClassificationYasin Kaya0Ezgisu Akat1Serdar Yıldırım2Department of Artificial Intelligence Engineering Adana Alparslan Turkes Science and Technology University Adana TurkiyeDepartment of Computer Engineering Adana Alparslan Turkes Science and Technology University Adana TurkiyeDepartment of Computer Engineering Adana Alparslan Turkes Science and Technology University Adana TurkiyeABSTRACT Problem Brain tumors are among the most prevalent and lethal diseases. Early diagnosis and precise treatment are crucial. However, the manual classification of brain tumors is a laborious and complex task. Aim This study aimed to develop a fusion model to address certain limitations of previous works, such as covering diverse image modalities in various datasets. Method We presented a hybrid transfer learning model, Fusion‐Brain‐Net, aimed at automatic brain tumor classification. The proposed method included four stages: preprocessing and data augmentation, fusion of deep feature extractions, fine‐tuning, and classification. Integrating the pre‐trained CNN models, VGG16, ResNet50, and MobileNetV2, the model enhanced comprehensive feature extraction while mitigating overfitting issues, improving the model's performance. Results The proposed model was rigorously tested and verified on four public datasets: Br35H, Figshare, Nickparvar, and Sartaj. It achieved remarkable accuracy rates of 99.66%, 97.56%, 97.08%, and 93.74%, respectively. Conclusion The numerical results highlight that the model should be further investigated for potential use in computer‐aided diagnoses to improve clinical decision‐making.https://doi.org/10.1002/brb3.70520brain tumor classificationfusion of CNNtransfer learning
spellingShingle Yasin Kaya
Ezgisu Akat
Serdar Yıldırım
Fusion‐Brain‐Net: A Novel Deep Fusion Model for Brain Tumor Classification
Brain and Behavior
brain tumor classification
fusion of CNN
transfer learning
title Fusion‐Brain‐Net: A Novel Deep Fusion Model for Brain Tumor Classification
title_full Fusion‐Brain‐Net: A Novel Deep Fusion Model for Brain Tumor Classification
title_fullStr Fusion‐Brain‐Net: A Novel Deep Fusion Model for Brain Tumor Classification
title_full_unstemmed Fusion‐Brain‐Net: A Novel Deep Fusion Model for Brain Tumor Classification
title_short Fusion‐Brain‐Net: A Novel Deep Fusion Model for Brain Tumor Classification
title_sort fusion brain net a novel deep fusion model for brain tumor classification
topic brain tumor classification
fusion of CNN
transfer learning
url https://doi.org/10.1002/brb3.70520
work_keys_str_mv AT yasinkaya fusionbrainnetanoveldeepfusionmodelforbraintumorclassification
AT ezgisuakat fusionbrainnetanoveldeepfusionmodelforbraintumorclassification
AT serdaryıldırım fusionbrainnetanoveldeepfusionmodelforbraintumorclassification