A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI Images

Background: Cancer ranks second among the causes of mortality worldwide, following cardiovascular diseases. Brain cancer, in particular, has the lowest survival rate of any form of cancer. Brain tumors vary in their morphology, texture, and location, which determine their classification. The accurat...

Full description

Saved in:
Bibliographic Details
Main Authors: Eman M. G. Younis, Mahmoud N. Mahmoud, Abdullah M. Albarrak, Ibrahim A. Ibrahim
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/23/2710
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124309563572224
author Eman M. G. Younis
Mahmoud N. Mahmoud
Abdullah M. Albarrak
Ibrahim A. Ibrahim
author_facet Eman M. G. Younis
Mahmoud N. Mahmoud
Abdullah M. Albarrak
Ibrahim A. Ibrahim
author_sort Eman M. G. Younis
collection DOAJ
description Background: Cancer ranks second among the causes of mortality worldwide, following cardiovascular diseases. Brain cancer, in particular, has the lowest survival rate of any form of cancer. Brain tumors vary in their morphology, texture, and location, which determine their classification. The accurate diagnosis of tumors enables physicians to select the optimal treatment strategies and potentially prolong patients’ lives. Researchers who have implemented deep learning models for the diagnosis of diseases in recent years have largely focused on deep neural network optimization to enhance their performance. This involves implementing models with the best performance and incorporating various network architectures by configuring their hyperparameters. Methods: This paper presents a novel hybrid approach for improved brain tumor classification by combining CNNs and EfficientNetV2B3 for feature extraction, followed by K-nearest neighbors (KNN) for classification, which has been described as one of the simplest machine learning algorithms based on supervised learning techniques. The KNN algorithm assumes similarities between new cases and available cases and assigns new cases to the category that most closely resembles the available categories. Results: To evaluate the recommended method’s efficacy, two widely known benchmark MRI datasets were utilized in the experiments. The initial dataset consisted of 3064 MRI images depicting meningiomas, gliomas, and pituitary tumors. Images from two classes, consisting of healthy brains and brain tumors, were included in the second dataset, which was obtained from Kaggle. Conclusions: In order to enhance the performance even further, this study concatenated the CNN and EfficientNetV2B3’s flattened outputs before feeding them into the KNN classifier. The proposed framework was run on these two different datasets and demonstrated outstanding performance, with accuracy of 99.51% and 99.8%, respectively.
format Article
id doaj-art-b085a62c26734005978027b8fd3688db
institution Kabale University
issn 2075-4418
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-b085a62c26734005978027b8fd3688db2024-12-13T16:24:45ZengMDPI AGDiagnostics2075-44182024-11-011423271010.3390/diagnostics14232710A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI ImagesEman M. G. Younis0Mahmoud N. Mahmoud1Abdullah M. Albarrak2Ibrahim A. Ibrahim3Faculty of Computers and Information, Minia University, Minia 61519, EgyptFaculty of Computers and Information, Minia University, Minia 61519, EgyptCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 13318, Saudi ArabiaFaculty of Computers and Information, Minia University, Minia 61519, EgyptBackground: Cancer ranks second among the causes of mortality worldwide, following cardiovascular diseases. Brain cancer, in particular, has the lowest survival rate of any form of cancer. Brain tumors vary in their morphology, texture, and location, which determine their classification. The accurate diagnosis of tumors enables physicians to select the optimal treatment strategies and potentially prolong patients’ lives. Researchers who have implemented deep learning models for the diagnosis of diseases in recent years have largely focused on deep neural network optimization to enhance their performance. This involves implementing models with the best performance and incorporating various network architectures by configuring their hyperparameters. Methods: This paper presents a novel hybrid approach for improved brain tumor classification by combining CNNs and EfficientNetV2B3 for feature extraction, followed by K-nearest neighbors (KNN) for classification, which has been described as one of the simplest machine learning algorithms based on supervised learning techniques. The KNN algorithm assumes similarities between new cases and available cases and assigns new cases to the category that most closely resembles the available categories. Results: To evaluate the recommended method’s efficacy, two widely known benchmark MRI datasets were utilized in the experiments. The initial dataset consisted of 3064 MRI images depicting meningiomas, gliomas, and pituitary tumors. Images from two classes, consisting of healthy brains and brain tumors, were included in the second dataset, which was obtained from Kaggle. Conclusions: In order to enhance the performance even further, this study concatenated the CNN and EfficientNetV2B3’s flattened outputs before feeding them into the KNN classifier. The proposed framework was run on these two different datasets and demonstrated outstanding performance, with accuracy of 99.51% and 99.8%, respectively.https://www.mdpi.com/2075-4418/14/23/2710brain tumorCNNEfficientNetV2B3KNN
spellingShingle Eman M. G. Younis
Mahmoud N. Mahmoud
Abdullah M. Albarrak
Ibrahim A. Ibrahim
A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI Images
Diagnostics
brain tumor
CNN
EfficientNetV2B3
KNN
title A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI Images
title_full A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI Images
title_fullStr A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI Images
title_full_unstemmed A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI Images
title_short A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI Images
title_sort hybrid deep learning model with data augmentation to improve tumor classification using mri images
topic brain tumor
CNN
EfficientNetV2B3
KNN
url https://www.mdpi.com/2075-4418/14/23/2710
work_keys_str_mv AT emanmgyounis ahybriddeeplearningmodelwithdataaugmentationtoimprovetumorclassificationusingmriimages
AT mahmoudnmahmoud ahybriddeeplearningmodelwithdataaugmentationtoimprovetumorclassificationusingmriimages
AT abdullahmalbarrak ahybriddeeplearningmodelwithdataaugmentationtoimprovetumorclassificationusingmriimages
AT ibrahimaibrahim ahybriddeeplearningmodelwithdataaugmentationtoimprovetumorclassificationusingmriimages
AT emanmgyounis hybriddeeplearningmodelwithdataaugmentationtoimprovetumorclassificationusingmriimages
AT mahmoudnmahmoud hybriddeeplearningmodelwithdataaugmentationtoimprovetumorclassificationusingmriimages
AT abdullahmalbarrak hybriddeeplearningmodelwithdataaugmentationtoimprovetumorclassificationusingmriimages
AT ibrahimaibrahim hybriddeeplearningmodelwithdataaugmentationtoimprovetumorclassificationusingmriimages