An efficient hybrid model of CNNs and different kernels of SVM for brain tumor classification
Technological advancements have had a profound impact on various aspects of human existence. The realm of medicine is one major area where technology has made important advances. We will talk specifically about the role technology has had in treating brain tumors, a serious and widespread condition...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidade Federal de Viçosa (UFV)
2023-10-01
|
| Series: | The Journal of Engineering and Exact Sciences |
| Subjects: | |
| Online Access: | https://periodicos.ufv.br/jcec/article/view/16739 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832569704642772992 |
|---|---|
| author | Mohammed Bourennane Hilal Naimi |
| author_facet | Mohammed Bourennane Hilal Naimi |
| author_sort | Mohammed Bourennane |
| collection | DOAJ |
| description |
Technological advancements have had a profound impact on various aspects of human existence. The realm of medicine is one major area where technology has made important advances. We will talk specifically about the role technology has had in treating brain tumors, a serious and widespread condition. A large number of people pass away from brain tumors every year. Patients with BTs have a worse likelihood of survival when they receive subpar care and a false diagnosis. The most widely employed technique for detecting brain tumors is magnetic resonance imaging (MRI). Moreover, MRI is extensively utilized in medical imaging and image processing to identify variations in various regions of the body. A convolutional neural network (CNN)-based model was developed in this study to classify brain tumor. Using nine pre-trained CNN models (efficientnetb0, mobilenetv2, nasnetlarge, resnet50, resnet10, googlenet, vgg16, vgg19, and shufflenet), deep features were extracted from the acquired images. Then use a Support Vector Machines (SVM) classifier to classify the deep features. The classification accuracy results obtained from the various kernel functions, namely linear, gaussian, cubic, and quadratic—was then compared. The deep features retrieved from the efficientnetb0 model allowed accurate classification of brain tumors. The classification accuracy achieved using the Gaussian kernel function of SVM was recorded at an impressive 99.78%.
|
| format | Article |
| id | doaj-art-0a9e393b804e4f55bc62ce401157622e |
| institution | Kabale University |
| issn | 2527-1075 |
| language | English |
| publishDate | 2023-10-01 |
| publisher | Universidade Federal de Viçosa (UFV) |
| record_format | Article |
| series | The Journal of Engineering and Exact Sciences |
| spelling | doaj-art-0a9e393b804e4f55bc62ce401157622e2025-02-02T19:54:37ZengUniversidade Federal de Viçosa (UFV)The Journal of Engineering and Exact Sciences2527-10752023-10-019810.18540/jcecvl9iss8pp16739-01eAn efficient hybrid model of CNNs and different kernels of SVM for brain tumor classificationMohammed Bourennane0Hilal Naimi1Laboratory of Modeling Simulation and Optimization of Systems Complexes, University of Djelfa, Djelfa 17000, AlgeriaLaboratory of Modeling Simulation and Optimization of Systems Complexes, University of Djelfa, Djelfa 17000, Algeria Technological advancements have had a profound impact on various aspects of human existence. The realm of medicine is one major area where technology has made important advances. We will talk specifically about the role technology has had in treating brain tumors, a serious and widespread condition. A large number of people pass away from brain tumors every year. Patients with BTs have a worse likelihood of survival when they receive subpar care and a false diagnosis. The most widely employed technique for detecting brain tumors is magnetic resonance imaging (MRI). Moreover, MRI is extensively utilized in medical imaging and image processing to identify variations in various regions of the body. A convolutional neural network (CNN)-based model was developed in this study to classify brain tumor. Using nine pre-trained CNN models (efficientnetb0, mobilenetv2, nasnetlarge, resnet50, resnet10, googlenet, vgg16, vgg19, and shufflenet), deep features were extracted from the acquired images. Then use a Support Vector Machines (SVM) classifier to classify the deep features. The classification accuracy results obtained from the various kernel functions, namely linear, gaussian, cubic, and quadratic—was then compared. The deep features retrieved from the efficientnetb0 model allowed accurate classification of brain tumors. The classification accuracy achieved using the Gaussian kernel function of SVM was recorded at an impressive 99.78%. https://periodicos.ufv.br/jcec/article/view/16739Convolutional neural network; Support Vector Machines; Brain tumors; Efficientnetb0; Gaussian kernel function. |
| spellingShingle | Mohammed Bourennane Hilal Naimi An efficient hybrid model of CNNs and different kernels of SVM for brain tumor classification The Journal of Engineering and Exact Sciences Convolutional neural network; Support Vector Machines; Brain tumors; Efficientnetb0; Gaussian kernel function. |
| title | An efficient hybrid model of CNNs and different kernels of SVM for brain tumor classification |
| title_full | An efficient hybrid model of CNNs and different kernels of SVM for brain tumor classification |
| title_fullStr | An efficient hybrid model of CNNs and different kernels of SVM for brain tumor classification |
| title_full_unstemmed | An efficient hybrid model of CNNs and different kernels of SVM for brain tumor classification |
| title_short | An efficient hybrid model of CNNs and different kernels of SVM for brain tumor classification |
| title_sort | efficient hybrid model of cnns and different kernels of svm for brain tumor classification |
| topic | Convolutional neural network; Support Vector Machines; Brain tumors; Efficientnetb0; Gaussian kernel function. |
| url | https://periodicos.ufv.br/jcec/article/view/16739 |
| work_keys_str_mv | AT mohammedbourennane anefficienthybridmodelofcnnsanddifferentkernelsofsvmforbraintumorclassification AT hilalnaimi anefficienthybridmodelofcnnsanddifferentkernelsofsvmforbraintumorclassification AT mohammedbourennane efficienthybridmodelofcnnsanddifferentkernelsofsvmforbraintumorclassification AT hilalnaimi efficienthybridmodelofcnnsanddifferentkernelsofsvmforbraintumorclassification |