Ensemble Deep Learning Technique for Detecting MRI Brain Tumor
The classification process of MRI (magnetic resonance imaging) is frequently used for making medical diagnoses for conditions including pituitary, glioma, meningioma, and no tumor. For this reason, determining the type of MRI and its quantity are significant and valuable measurements that reveal the...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Applied Computational Intelligence and Soft Computing |
| Online Access: | http://dx.doi.org/10.1155/2024/6615468 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832559415499161600 |
|---|---|
| author | Rasool Fakhir Jader Shahab Wahhab Kareem Hoshang Qasim Awla |
| author_facet | Rasool Fakhir Jader Shahab Wahhab Kareem Hoshang Qasim Awla |
| author_sort | Rasool Fakhir Jader |
| collection | DOAJ |
| description | The classification process of MRI (magnetic resonance imaging) is frequently used for making medical diagnoses for conditions including pituitary, glioma, meningioma, and no tumor. For this reason, determining the type of MRI and its quantity are significant and valuable measurements that reveal the brain’s state of health. To segment and classify brain analysis, laboratory personnel employ manual examination via screen; this requires a lot of labour and time. On the other hand, the devices used by specialists are not practical or inexpensive for every doctor or institution. In recent years, a variety of computational algorithms for segmentation and classification have been developed with improved results to get around the issue. Artificial neural networks (ANNs) have the capability and promise to classify in this regard. The purpose of this paper is to create and put into practice a system for classifying different types of MRI images of brain tumor samples. As a result, this paper concentrated on the tasks of segmentation, feature extraction, classifier building, and classification into four categories using various machine learning algorithms. The authors used VGG-16, ResNet-50, and AlexNet models based on the transfer learning algorithm for three models to classify images as an ensemble model. As a result, MRI brain tumor segmentation is more precise because each spatial feature point can now refer to all other contextual data. In the specifics, our models outperformed every other published modern ensemble model in the official deep learning challenge without any postprocessing. The ensemble model achieved an accuracy of 99.16%, a sensitivity of 98.47%, a specificity of 98.57%, a precision of 98.74%, a recall of 98.49%, and an F1-score of 98.18%. These results significantly surpass the accuracy of other methods such as Naive Bayes, decision tree classifier, random forest, and DNN models. |
| format | Article |
| id | doaj-art-5493495d3b8f4cd6b8ace08b23ba1453 |
| institution | Kabale University |
| issn | 1687-9732 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied Computational Intelligence and Soft Computing |
| spelling | doaj-art-5493495d3b8f4cd6b8ace08b23ba14532025-02-03T01:30:04ZengWileyApplied Computational Intelligence and Soft Computing1687-97322024-01-01202410.1155/2024/6615468Ensemble Deep Learning Technique for Detecting MRI Brain TumorRasool Fakhir Jader0Shahab Wahhab Kareem1Hoshang Qasim Awla2Computer Science DepartmentInformation System Engineering DepartmentComputer Science DepartmentThe classification process of MRI (magnetic resonance imaging) is frequently used for making medical diagnoses for conditions including pituitary, glioma, meningioma, and no tumor. For this reason, determining the type of MRI and its quantity are significant and valuable measurements that reveal the brain’s state of health. To segment and classify brain analysis, laboratory personnel employ manual examination via screen; this requires a lot of labour and time. On the other hand, the devices used by specialists are not practical or inexpensive for every doctor or institution. In recent years, a variety of computational algorithms for segmentation and classification have been developed with improved results to get around the issue. Artificial neural networks (ANNs) have the capability and promise to classify in this regard. The purpose of this paper is to create and put into practice a system for classifying different types of MRI images of brain tumor samples. As a result, this paper concentrated on the tasks of segmentation, feature extraction, classifier building, and classification into four categories using various machine learning algorithms. The authors used VGG-16, ResNet-50, and AlexNet models based on the transfer learning algorithm for three models to classify images as an ensemble model. As a result, MRI brain tumor segmentation is more precise because each spatial feature point can now refer to all other contextual data. In the specifics, our models outperformed every other published modern ensemble model in the official deep learning challenge without any postprocessing. The ensemble model achieved an accuracy of 99.16%, a sensitivity of 98.47%, a specificity of 98.57%, a precision of 98.74%, a recall of 98.49%, and an F1-score of 98.18%. These results significantly surpass the accuracy of other methods such as Naive Bayes, decision tree classifier, random forest, and DNN models.http://dx.doi.org/10.1155/2024/6615468 |
| spellingShingle | Rasool Fakhir Jader Shahab Wahhab Kareem Hoshang Qasim Awla Ensemble Deep Learning Technique for Detecting MRI Brain Tumor Applied Computational Intelligence and Soft Computing |
| title | Ensemble Deep Learning Technique for Detecting MRI Brain Tumor |
| title_full | Ensemble Deep Learning Technique for Detecting MRI Brain Tumor |
| title_fullStr | Ensemble Deep Learning Technique for Detecting MRI Brain Tumor |
| title_full_unstemmed | Ensemble Deep Learning Technique for Detecting MRI Brain Tumor |
| title_short | Ensemble Deep Learning Technique for Detecting MRI Brain Tumor |
| title_sort | ensemble deep learning technique for detecting mri brain tumor |
| url | http://dx.doi.org/10.1155/2024/6615468 |
| work_keys_str_mv | AT rasoolfakhirjader ensembledeeplearningtechniquefordetectingmribraintumor AT shahabwahhabkareem ensembledeeplearningtechniquefordetectingmribraintumor AT hoshangqasimawla ensembledeeplearningtechniquefordetectingmribraintumor |