Advancing Brain MRI Image Classification: Integrating VGG16 and ResNet50 with a Multi-Verse Optimization Method
<b>Background/Objectives:</b> The accurate categorization of brain MRI images into tumor and non-tumor categories is essential for a prompt and effective diagnosis. This paper presents a novel methodology utilizing advanced Convolutional Neural Network (CNN) designs to tackle the complex...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | BioMed |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-8430/4/4/38 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846105730749300736 |
|---|---|
| author | Nazanin Tataei Sarshar Soroush Sadeghi Mohammadreza Kamsari Mahrokh Avazpour Saeid Jafarzadeh Ghoushchi Ramin Ranjbarzadeh |
| author_facet | Nazanin Tataei Sarshar Soroush Sadeghi Mohammadreza Kamsari Mahrokh Avazpour Saeid Jafarzadeh Ghoushchi Ramin Ranjbarzadeh |
| author_sort | Nazanin Tataei Sarshar |
| collection | DOAJ |
| description | <b>Background/Objectives:</b> The accurate categorization of brain MRI images into tumor and non-tumor categories is essential for a prompt and effective diagnosis. This paper presents a novel methodology utilizing advanced Convolutional Neural Network (CNN) designs to tackle the complexity and unpredictability present in brain MRI data. <b>Methods:</b> The methodology commences with an extensive preparation phase that includes image resizing, grayscale conversion, Gaussian blurring, and the delineation of the brain region for preparing the MRI images for analysis. The Multi-verse Optimizer (MVO) is utilized to optimize data augmentation parameters and refine the configuration of trainable layers in VGG16 and ResNet50. The model’s generalization capabilities are significantly improved by the MVO’s ability to effectively balance computational cost and performance. <b>Results:</b> The amalgamation of VGG16 and ResNet50, further refined by the MVO, exhibits substantial enhancements in classification metrics. The MVO-optimized hybrid model demonstrates enhanced performance, exhibiting a well-calibrated balance between precision and recall, rendering it exceptionally trustworthy for medical diagnostic applications. <b>Conclusions:</b> The results highlight the effectiveness of MVO-optimized CNN models for classifying brain tumors in MRI data. Future investigations may examine the model’s applicability to multiclass issues and its validation in practical clinical environments. |
| format | Article |
| id | doaj-art-b6d9eaf8c2c1497d9d182c0b61f4e6e9 |
| institution | Kabale University |
| issn | 2673-8430 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | BioMed |
| spelling | doaj-art-b6d9eaf8c2c1497d9d182c0b61f4e6e92024-12-27T14:12:23ZengMDPI AGBioMed2673-84302024-11-014449952310.3390/biomed4040038Advancing Brain MRI Image Classification: Integrating VGG16 and ResNet50 with a Multi-Verse Optimization MethodNazanin Tataei Sarshar0Soroush Sadeghi1Mohammadreza Kamsari2Mahrokh Avazpour3Saeid Jafarzadeh Ghoushchi4Ramin Ranjbarzadeh5Department of Engineering, Islamic Azad University, Tehran North Branch, Tehran 1584743311, IranSchool of Electrical and Computer Engineering, University of Tehran, Tehran 1417935840, IranFaculty of Electrical Engineering, Malek-Ashtar University of Technology (MUT), Esfahan 83154/115, IranRadio and Optics Communication Laboratory, School of Electronic Engineering, Dublin City University, D09 V209 Dublin, IrelandFaculty of Industrial Engineering, Urmia University of Technology, Urmia 5756151818, IranSchool of Computing, Faculty of Engineering and Computing, Dublin City University, D09 V209 Dublin, Ireland<b>Background/Objectives:</b> The accurate categorization of brain MRI images into tumor and non-tumor categories is essential for a prompt and effective diagnosis. This paper presents a novel methodology utilizing advanced Convolutional Neural Network (CNN) designs to tackle the complexity and unpredictability present in brain MRI data. <b>Methods:</b> The methodology commences with an extensive preparation phase that includes image resizing, grayscale conversion, Gaussian blurring, and the delineation of the brain region for preparing the MRI images for analysis. The Multi-verse Optimizer (MVO) is utilized to optimize data augmentation parameters and refine the configuration of trainable layers in VGG16 and ResNet50. The model’s generalization capabilities are significantly improved by the MVO’s ability to effectively balance computational cost and performance. <b>Results:</b> The amalgamation of VGG16 and ResNet50, further refined by the MVO, exhibits substantial enhancements in classification metrics. The MVO-optimized hybrid model demonstrates enhanced performance, exhibiting a well-calibrated balance between precision and recall, rendering it exceptionally trustworthy for medical diagnostic applications. <b>Conclusions:</b> The results highlight the effectiveness of MVO-optimized CNN models for classifying brain tumors in MRI data. Future investigations may examine the model’s applicability to multiclass issues and its validation in practical clinical environments.https://www.mdpi.com/2673-8430/4/4/38brain tumor classificationMRI image analysisoptimizationdeep learningdata augmentationmulti-verse optimizer |
| spellingShingle | Nazanin Tataei Sarshar Soroush Sadeghi Mohammadreza Kamsari Mahrokh Avazpour Saeid Jafarzadeh Ghoushchi Ramin Ranjbarzadeh Advancing Brain MRI Image Classification: Integrating VGG16 and ResNet50 with a Multi-Verse Optimization Method BioMed brain tumor classification MRI image analysis optimization deep learning data augmentation multi-verse optimizer |
| title | Advancing Brain MRI Image Classification: Integrating VGG16 and ResNet50 with a Multi-Verse Optimization Method |
| title_full | Advancing Brain MRI Image Classification: Integrating VGG16 and ResNet50 with a Multi-Verse Optimization Method |
| title_fullStr | Advancing Brain MRI Image Classification: Integrating VGG16 and ResNet50 with a Multi-Verse Optimization Method |
| title_full_unstemmed | Advancing Brain MRI Image Classification: Integrating VGG16 and ResNet50 with a Multi-Verse Optimization Method |
| title_short | Advancing Brain MRI Image Classification: Integrating VGG16 and ResNet50 with a Multi-Verse Optimization Method |
| title_sort | advancing brain mri image classification integrating vgg16 and resnet50 with a multi verse optimization method |
| topic | brain tumor classification MRI image analysis optimization deep learning data augmentation multi-verse optimizer |
| url | https://www.mdpi.com/2673-8430/4/4/38 |
| work_keys_str_mv | AT nazanintataeisarshar advancingbrainmriimageclassificationintegratingvgg16andresnet50withamultiverseoptimizationmethod AT soroushsadeghi advancingbrainmriimageclassificationintegratingvgg16andresnet50withamultiverseoptimizationmethod AT mohammadrezakamsari advancingbrainmriimageclassificationintegratingvgg16andresnet50withamultiverseoptimizationmethod AT mahrokhavazpour advancingbrainmriimageclassificationintegratingvgg16andresnet50withamultiverseoptimizationmethod AT saeidjafarzadehghoushchi advancingbrainmriimageclassificationintegratingvgg16andresnet50withamultiverseoptimizationmethod AT raminranjbarzadeh advancingbrainmriimageclassificationintegratingvgg16andresnet50withamultiverseoptimizationmethod |