Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data
The biopsy is a gold standard method for tumor grading. However, due to its invasive nature, it has sometimes proved fatal for brain tumor patients. As a result, a non-invasive computer-aided diagnosis (CAD) tool is required. Recently, many magnetic resonance imaging (MRI)-based CAD tools have been...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/3/481 |
| _version_ | 1827760231573094400 |
|---|---|
| author | Gopal S. Tandel Ashish Tiwari Omprakash G. Kakde Neha Gupta Luca Saba Jasjit S. Suri |
| author_facet | Gopal S. Tandel Ashish Tiwari Omprakash G. Kakde Neha Gupta Luca Saba Jasjit S. Suri |
| author_sort | Gopal S. Tandel |
| collection | DOAJ |
| description | The biopsy is a gold standard method for tumor grading. However, due to its invasive nature, it has sometimes proved fatal for brain tumor patients. As a result, a non-invasive computer-aided diagnosis (CAD) tool is required. Recently, many magnetic resonance imaging (MRI)-based CAD tools have been proposed for brain tumor grading. The MRI has several sequences, which can express tumor structure in different ways. However, a suitable MRI sequence for brain tumor classification is not yet known. The most common brain tumor is ‘glioma’, which is the most fatal form. Therefore, in the proposed study, to maximize the classification ability between low-grade versus high-grade glioma, three datasets were designed comprising three MRI sequences: T1-Weighted (T1W), T2-weighted (T2W), and fluid-attenuated inversion recovery (FLAIR). Further, five well-established convolutional neural networks, AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50 were adopted for tumor classification. An ensemble algorithm was proposed using the majority vote of above five deep learning (DL) models to produce more consistent and improved results than any individual model. Five-fold cross validation (K5-CV) protocol was adopted for training and testing. For the proposed ensembled classifier with K5-CV, the highest test accuracies of 98.88 ± 0.63%, 97.98 ± 0.86%, and 94.75 ± 0.61% were achieved for FLAIR, T2W, and T1W-MRI data, respectively. FLAIR-MRI data was found to be most significant for brain tumor classification, where it showed a 4.17% and 0.91% improvement in accuracy against the T1W-MRI and T2W-MRI sequence data, respectively. The proposed ensembled algorithm (MajVot) showed significant improvements in the average accuracy of three datasets of 3.60%, 2.84%, 1.64%, 4.27%, and 1.14%, respectively, against AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50. |
| first_indexed | 2024-03-11T09:48:39Z |
| format | Article |
| id | doaj.art-f6ab38f0418e48f8804cfbb74813a7e1 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T09:48:39Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-f6ab38f0418e48f8804cfbb74813a7e12023-11-16T16:25:21ZengMDPI AGDiagnostics2075-44182023-01-0113348110.3390/diagnostics13030481Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence DataGopal S. Tandel0Ashish Tiwari1Omprakash G. Kakde2Neha Gupta3Luca Saba4Jasjit S. Suri5School of Computer Science and Engineering, VIT Bhopal University, Sehore 466114, IndiaDepartment of Computer Science and Engineering, Visvesvaraya National Institute of Technology, Nagpur 440010, IndiaIndian Institute of Information Technology, Nagpur 441108, IndiaIT Department, Bharati Vidyapeeth’s College of Engineering, New Delhi 110063, IndiaDepartment of Radiology, University of Cagliari, 09124 Cagliari, ItalyStroke Diagnosis and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USAThe biopsy is a gold standard method for tumor grading. However, due to its invasive nature, it has sometimes proved fatal for brain tumor patients. As a result, a non-invasive computer-aided diagnosis (CAD) tool is required. Recently, many magnetic resonance imaging (MRI)-based CAD tools have been proposed for brain tumor grading. The MRI has several sequences, which can express tumor structure in different ways. However, a suitable MRI sequence for brain tumor classification is not yet known. The most common brain tumor is ‘glioma’, which is the most fatal form. Therefore, in the proposed study, to maximize the classification ability between low-grade versus high-grade glioma, three datasets were designed comprising three MRI sequences: T1-Weighted (T1W), T2-weighted (T2W), and fluid-attenuated inversion recovery (FLAIR). Further, five well-established convolutional neural networks, AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50 were adopted for tumor classification. An ensemble algorithm was proposed using the majority vote of above five deep learning (DL) models to produce more consistent and improved results than any individual model. Five-fold cross validation (K5-CV) protocol was adopted for training and testing. For the proposed ensembled classifier with K5-CV, the highest test accuracies of 98.88 ± 0.63%, 97.98 ± 0.86%, and 94.75 ± 0.61% were achieved for FLAIR, T2W, and T1W-MRI data, respectively. FLAIR-MRI data was found to be most significant for brain tumor classification, where it showed a 4.17% and 0.91% improvement in accuracy against the T1W-MRI and T2W-MRI sequence data, respectively. The proposed ensembled algorithm (MajVot) showed significant improvements in the average accuracy of three datasets of 3.60%, 2.84%, 1.64%, 4.27%, and 1.14%, respectively, against AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50.https://www.mdpi.com/2075-4418/13/3/481magnetic resonance imagingdeep learningtransfer learningclassificationbrain tumorcomputer-aided diagnosis |
| spellingShingle | Gopal S. Tandel Ashish Tiwari Omprakash G. Kakde Neha Gupta Luca Saba Jasjit S. Suri Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data Diagnostics magnetic resonance imaging deep learning transfer learning classification brain tumor computer-aided diagnosis |
| title | Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data |
| title_full | Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data |
| title_fullStr | Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data |
| title_full_unstemmed | Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data |
| title_short | Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data |
| title_sort | role of ensemble deep learning for brain tumor classification in multiple magnetic resonance imaging sequence data |
| topic | magnetic resonance imaging deep learning transfer learning classification brain tumor computer-aided diagnosis |
| url | https://www.mdpi.com/2075-4418/13/3/481 |
| work_keys_str_mv | AT gopalstandel roleofensembledeeplearningforbraintumorclassificationinmultiplemagneticresonanceimagingsequencedata AT ashishtiwari roleofensembledeeplearningforbraintumorclassificationinmultiplemagneticresonanceimagingsequencedata AT omprakashgkakde roleofensembledeeplearningforbraintumorclassificationinmultiplemagneticresonanceimagingsequencedata AT nehagupta roleofensembledeeplearningforbraintumorclassificationinmultiplemagneticresonanceimagingsequencedata AT lucasaba roleofensembledeeplearningforbraintumorclassificationinmultiplemagneticresonanceimagingsequencedata AT jasjitssuri roleofensembledeeplearningforbraintumorclassificationinmultiplemagneticresonanceimagingsequencedata |