ManageChatDiscover
411110

Optimizing Multi-Class Brain Tumor Diagnosis Using Transfer Learning with EfficientNetB4

Article

Last updated: 15 Feb 2025

OverviewSimilar Items

Subjects

-

Tags

-

Abstract

Certain types of tumors in individuals with brain cancer proliferate rapidly, with their average size doubling within 25 days. Accurately identifying the type of tumor enables physicians to develop effective treatment plans and determine the appropriate dosage. Magnetic Resonance Imaging (MRI) is a critical diagnostic technique for evaluating and diagnosing brain tumors because it provides high-contrast images of brain tissues. This article introduces an innovative approach for multi-classification brain tumors by utilizing deep convolutional neural networks (DCNNs), specifically employing EfficientNet-B4 as the base model, enhanced with fine-tuned, customized layers. Our approach incorporates a Global Average Pooling (GAP) layer to mitigate overfitting, batch normalization, and dropout layers to reduce losses and improve generalization. A series of experiments are performed on an open-access Kaggle dataset to identify the optimal model, utilizing seven optimization algorithms, including Adadelta, RMSprop, Adam, and Nadam. Among all models tested, EfficientNet-B4 with AdamW was the best-performing, achieving a test accuracy of 99.24%, a precision, recall, and F1-score of 99.22% and a specificity of 99.75%. In contrast, EfficientNet-B4 with AdamX had the lowest performance, with a test accuracy of 98.55%, precision of 98.53%, recall of 98.46%, F1-score of 98.49%, and specificity of 98.52%. These innovations can potentially enhance clinical decision-making and improve patient treatment in neuro-oncology.

DOI

10.21608/jocc.2025.411110

Keywords

brain cancer MRI Deep learning Transfer learning EfficientNet, B4

Authors

First Name

Mohamed

Last Name

Hammad

MiddleName

Tony

Affiliation

Department of Computer Science, Faculty of Computers and Artificial Intelligence, University of Sadat City, Sadat City, Egypt

Email

mohamed.tony@fcai.usc.edu.eg

City

-

Orcid

-

First Name

Abdelmegeid

Last Name

Ali

MiddleName

Amin

Affiliation

Department of Computer Science, Faculty of Computers and Information, Minia University, Minia, Egypt

Email

a.ali@minia.edu.eg

City

Minia

Orcid

-

First Name

Hassan

Last Name

Hassan

MiddleName

Shaban

Affiliation

Department of Computer Science, Faculty of Computers and Information, Minia University, Minia, Egypt

Email

hassanshaban@minia.edu.eg

City

Minia

Orcid

-

Volume

4

Article Issue

1

Related Issue

53728

Issue Date

2025-02-01

Receive Date

2025-01-02

Publish Date

2025-02-01

Page Start

19

Page End

30

Online ISSN

2636-3577

Article File

JOCC_Volume 4_Issue 1_Pages 19-30.pdf

PDF . 1.2MB

Link

https://jocc.journals.ekb.eg/article_411110.html

Detail API

http://journals.ekb.eg?_action=service&article_code=411110

Order

2

Type

Original Article

Type Code

731

Publication Type

Journal

Publication Title

Journal of Computing and Communication

Publication Link

https://jocc.journals.ekb.eg/

MainTitle

Optimizing Multi-Class Brain Tumor Diagnosis Using Transfer Learning with EfficientNetB4

Details

Type

Article

Created At

15 Feb 2025