MRI Brain Tumor Classification Using a Hybrid VGG16-NADE Model
Abstract A brain tumour is determined to be abnormal cell development on the brain walls and inside the skull. A malignant variation is a dangerous form of cancer with an increased mortality rate. Analyzing Magnetic Resonance Imaging (MRI) through deep learning models is the most prevalent and accur...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Instituto de Tecnologia do Paraná (Tecpar)
2022-12-01
|
| Series: | Brazilian Archives of Biology and Technology |
| Subjects: | |
| Online Access: | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132023000100608&tlng=en |
| _version_ | 1811314199535550464 |
|---|---|
| author | Saran Raj Sowrirajan Surendiran Balasubramanian Raja Soosaimarian Peter Raj |
| author_facet | Saran Raj Sowrirajan Surendiran Balasubramanian Raja Soosaimarian Peter Raj |
| author_sort | Saran Raj Sowrirajan |
| collection | DOAJ |
| description | Abstract A brain tumour is determined to be abnormal cell development on the brain walls and inside the skull. A malignant variation is a dangerous form of cancer with an increased mortality rate. Analyzing Magnetic Resonance Imaging (MRI) through deep learning models is the most prevalent and accurate method of early cancer detection. A novel hybrid model is proposed with the VGG16 convolution neural network (CNN) and Neural Autoregressive Distribution Estimation (NADE). The experiment was conducted on 3064 MRI brain tumour images grouped into three categories. The T1 weighted contrast-enhanced MRI images were classified using the hybrid VGG16-NADE model and compared with other methods. The results prove that the proposed hybrid VGG16-NADEmodel outperforms the rest in terms of classification accuracy, specificity, sensitivity and F1 score. The prediction accuracy of the proposed hybrid VGG16-NADE is 96.01%, precision 95.72%, recall 95.64%, F-measure 95.68%, Receiver operating characteristic (ROC) 0.91, error rate 0.075, and the Matthews correlation coefficient (MCC) 0.3564. The numerical outcomes are comparatively higher than those from other approaches and it is evaluated with existing approaches like the hybrid CNN and NADE, CNN, CNN- kernel Extreme Learning Machines (KELM), deep CNN-data augmentation, and CNN- Genetic Algorithm (GA). Other metrics like the p-value, MCC, error rate and ROC are also evaluated. The experimental outcomes show that the hybrid VGG16-NADE classifier model outperforms other approaches. |
| first_indexed | 2024-04-13T11:08:57Z |
| format | Article |
| id | doaj.art-76ca2b94430e4595b82e341be82dee96 |
| institution | Directory Open Access Journal |
| issn | 1678-4324 |
| language | English |
| last_indexed | 2024-04-13T11:08:57Z |
| publishDate | 2022-12-01 |
| publisher | Instituto de Tecnologia do Paraná (Tecpar) |
| record_format | Article |
| series | Brazilian Archives of Biology and Technology |
| spelling | doaj.art-76ca2b94430e4595b82e341be82dee962022-12-22T02:49:12ZengInstituto de Tecnologia do Paraná (Tecpar)Brazilian Archives of Biology and Technology1678-43242022-12-016610.1590/1678-4324-2023220071MRI Brain Tumor Classification Using a Hybrid VGG16-NADE ModelSaran Raj Sowrirajanhttps://orcid.org/0000-0002-5954-5924Surendiran Balasubramanianhttps://orcid.org/0000-0001-5435-0880Raja Soosaimarian Peter Rajhttps://orcid.org/0000-0002-7216-2207Abstract A brain tumour is determined to be abnormal cell development on the brain walls and inside the skull. A malignant variation is a dangerous form of cancer with an increased mortality rate. Analyzing Magnetic Resonance Imaging (MRI) through deep learning models is the most prevalent and accurate method of early cancer detection. A novel hybrid model is proposed with the VGG16 convolution neural network (CNN) and Neural Autoregressive Distribution Estimation (NADE). The experiment was conducted on 3064 MRI brain tumour images grouped into three categories. The T1 weighted contrast-enhanced MRI images were classified using the hybrid VGG16-NADE model and compared with other methods. The results prove that the proposed hybrid VGG16-NADEmodel outperforms the rest in terms of classification accuracy, specificity, sensitivity and F1 score. The prediction accuracy of the proposed hybrid VGG16-NADE is 96.01%, precision 95.72%, recall 95.64%, F-measure 95.68%, Receiver operating characteristic (ROC) 0.91, error rate 0.075, and the Matthews correlation coefficient (MCC) 0.3564. The numerical outcomes are comparatively higher than those from other approaches and it is evaluated with existing approaches like the hybrid CNN and NADE, CNN, CNN- kernel Extreme Learning Machines (KELM), deep CNN-data augmentation, and CNN- Genetic Algorithm (GA). Other metrics like the p-value, MCC, error rate and ROC are also evaluated. The experimental outcomes show that the hybrid VGG16-NADE classifier model outperforms other approaches.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132023000100608&tlng=enMRIbrain tumorVGG16NADE modelclassificationdeep learning. |
| spellingShingle | Saran Raj Sowrirajan Surendiran Balasubramanian Raja Soosaimarian Peter Raj MRI Brain Tumor Classification Using a Hybrid VGG16-NADE Model Brazilian Archives of Biology and Technology MRI brain tumor VGG16 NADE model classification deep learning. |
| title | MRI Brain Tumor Classification Using a Hybrid VGG16-NADE Model |
| title_full | MRI Brain Tumor Classification Using a Hybrid VGG16-NADE Model |
| title_fullStr | MRI Brain Tumor Classification Using a Hybrid VGG16-NADE Model |
| title_full_unstemmed | MRI Brain Tumor Classification Using a Hybrid VGG16-NADE Model |
| title_short | MRI Brain Tumor Classification Using a Hybrid VGG16-NADE Model |
| title_sort | mri brain tumor classification using a hybrid vgg16 nade model |
| topic | MRI brain tumor VGG16 NADE model classification deep learning. |
| url | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132023000100608&tlng=en |
| work_keys_str_mv | AT saranrajsowrirajan mribraintumorclassificationusingahybridvgg16nademodel AT surendiranbalasubramanian mribraintumorclassificationusingahybridvgg16nademodel AT rajasoosaimarianpeterraj mribraintumorclassificationusingahybridvgg16nademodel |