An Ensemble Model for the Diagnosis of Brain Tumors through MRIs
Automatic brain tumor detection in MR Images is one of the basic applications of machine vision in medical image processing, which, despite much research, still needs further development. Using multiple machine learning techniques as an ensemble system is one of the solutions that can be effective i...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/3/561 |
| _version_ | 1797624849172004864 |
|---|---|
| author | Ehsan Ghafourian Farshad Samadifam Heidar Fadavian Peren Jerfi Canatalay AmirReza Tajally Sittiporn Channumsin |
| author_facet | Ehsan Ghafourian Farshad Samadifam Heidar Fadavian Peren Jerfi Canatalay AmirReza Tajally Sittiporn Channumsin |
| author_sort | Ehsan Ghafourian |
| collection | DOAJ |
| description | Automatic brain tumor detection in MR Images is one of the basic applications of machine vision in medical image processing, which, despite much research, still needs further development. Using multiple machine learning techniques as an ensemble system is one of the solutions that can be effective in achieving this goal. In this paper, a novel method for diagnosing brain tumors by combining data mining and machine learning techniques has been proposed. In the proposed method, each image is initially pre-processed to eliminate its background region and identify brain tissue. The Social Spider Optimization (SSO) algorithm is then utilized to segment the MRI Images. The MRI Images segmentation allows for a more precise identification of the tumor region in the image. In the next step, the distinctive features of the image are extracted using the SVD technique. In addition to removing redundant information, this strategy boosts the speed of the processing at the classification stage. Finally, a combination of the algorithms Naïve Bayes, Support vector machine and K-nearest neighbor is used to classify the extracted features and detect brain tumors. Each of the three algorithms performs feature classification individually, and the final output of the proposed model is created by integrating the three independent outputs and voting the results. The results indicate that the proposed method can diagnose brain tumors in the BRATS 2014 dataset with an average accuracy of 98.61%, sensitivity of 95.79% and specificity of 99.71%. Additionally, the proposed method could diagnose brain tumors in the BTD20 database with an average accuracy of 99.13%, sensitivity of 99% and specificity of 99.26%. These results show a significant improvement compared to previous efforts. The findings confirm that using the image segmentation technique, as well as the ensemble learning, is effective in improving the efficiency of the proposed method. |
| first_indexed | 2024-03-11T09:48:30Z |
| format | Article |
| id | doaj.art-d527da43f671487c84cb93baea5a3ac3 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T09:48:30Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-d527da43f671487c84cb93baea5a3ac32023-11-16T16:26:36ZengMDPI AGDiagnostics2075-44182023-02-0113356110.3390/diagnostics13030561An Ensemble Model for the Diagnosis of Brain Tumors through MRIsEhsan Ghafourian0Farshad Samadifam1Heidar Fadavian2Peren Jerfi Canatalay3AmirReza Tajally4Sittiporn Channumsin5Department of Computer Science, Iowa State University, Ames, IA 50010, USADepartment of Biomedical Engineering, Medical College of Wisconsin, Milwaukee, WI 53226, USADepartment of Electrical and Computer Engineering, Tarbiat Modares University, Tehran 14115-111, IranComputer Engineering, Faculty of Engineering Department, Halic University, Istanbul 34394, TurkeySchool of Industrial Engineering, College of Engineering, University of Tehran, Tehran 14179-35840, IranSpace Technology Research Center, Geo-Informatics and Space Technology Development Agency (GISTDA), Chonburi 20230, ThailandAutomatic brain tumor detection in MR Images is one of the basic applications of machine vision in medical image processing, which, despite much research, still needs further development. Using multiple machine learning techniques as an ensemble system is one of the solutions that can be effective in achieving this goal. In this paper, a novel method for diagnosing brain tumors by combining data mining and machine learning techniques has been proposed. In the proposed method, each image is initially pre-processed to eliminate its background region and identify brain tissue. The Social Spider Optimization (SSO) algorithm is then utilized to segment the MRI Images. The MRI Images segmentation allows for a more precise identification of the tumor region in the image. In the next step, the distinctive features of the image are extracted using the SVD technique. In addition to removing redundant information, this strategy boosts the speed of the processing at the classification stage. Finally, a combination of the algorithms Naïve Bayes, Support vector machine and K-nearest neighbor is used to classify the extracted features and detect brain tumors. Each of the three algorithms performs feature classification individually, and the final output of the proposed model is created by integrating the three independent outputs and voting the results. The results indicate that the proposed method can diagnose brain tumors in the BRATS 2014 dataset with an average accuracy of 98.61%, sensitivity of 95.79% and specificity of 99.71%. Additionally, the proposed method could diagnose brain tumors in the BTD20 database with an average accuracy of 99.13%, sensitivity of 99% and specificity of 99.26%. These results show a significant improvement compared to previous efforts. The findings confirm that using the image segmentation technique, as well as the ensemble learning, is effective in improving the efficiency of the proposed method.https://www.mdpi.com/2075-4418/13/3/561machine learningmagnetic resonance imagingensemble classifiersingular value decompositionsocial spider optimization |
| spellingShingle | Ehsan Ghafourian Farshad Samadifam Heidar Fadavian Peren Jerfi Canatalay AmirReza Tajally Sittiporn Channumsin An Ensemble Model for the Diagnosis of Brain Tumors through MRIs Diagnostics machine learning magnetic resonance imaging ensemble classifier singular value decomposition social spider optimization |
| title | An Ensemble Model for the Diagnosis of Brain Tumors through MRIs |
| title_full | An Ensemble Model for the Diagnosis of Brain Tumors through MRIs |
| title_fullStr | An Ensemble Model for the Diagnosis of Brain Tumors through MRIs |
| title_full_unstemmed | An Ensemble Model for the Diagnosis of Brain Tumors through MRIs |
| title_short | An Ensemble Model for the Diagnosis of Brain Tumors through MRIs |
| title_sort | ensemble model for the diagnosis of brain tumors through mris |
| topic | machine learning magnetic resonance imaging ensemble classifier singular value decomposition social spider optimization |
| url | https://www.mdpi.com/2075-4418/13/3/561 |
| work_keys_str_mv | AT ehsanghafourian anensemblemodelforthediagnosisofbraintumorsthroughmris AT farshadsamadifam anensemblemodelforthediagnosisofbraintumorsthroughmris AT heidarfadavian anensemblemodelforthediagnosisofbraintumorsthroughmris AT perenjerficanatalay anensemblemodelforthediagnosisofbraintumorsthroughmris AT amirrezatajally anensemblemodelforthediagnosisofbraintumorsthroughmris AT sittipornchannumsin anensemblemodelforthediagnosisofbraintumorsthroughmris AT ehsanghafourian ensemblemodelforthediagnosisofbraintumorsthroughmris AT farshadsamadifam ensemblemodelforthediagnosisofbraintumorsthroughmris AT heidarfadavian ensemblemodelforthediagnosisofbraintumorsthroughmris AT perenjerficanatalay ensemblemodelforthediagnosisofbraintumorsthroughmris AT amirrezatajally ensemblemodelforthediagnosisofbraintumorsthroughmris AT sittipornchannumsin ensemblemodelforthediagnosisofbraintumorsthroughmris |