An efficient brain tumor image segmentation based on deep residual networks (ResNets)
Automatic segmentation of brain tumor from Magnetic Resonance Images (MRI) is one of the challenging tasks in computer vision. Many proposals investigate the use of Deep Neural Networks (DNN) in image segmentation as they have a high performance in automatic segmentation of brain tumors images. Due...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-09-01
|
| Series: | Journal of King Saud University: Engineering Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1018363920302506 |
| _version_ | 1818354246780715008 |
|---|---|
| author | Lamia H. Shehab Omar M. Fahmy Safa M. Gasser Mohamed S. El-Mahallawy |
| author_facet | Lamia H. Shehab Omar M. Fahmy Safa M. Gasser Mohamed S. El-Mahallawy |
| author_sort | Lamia H. Shehab |
| collection | DOAJ |
| description | Automatic segmentation of brain tumor from Magnetic Resonance Images (MRI) is one of the challenging tasks in computer vision. Many proposals investigate the use of Deep Neural Networks (DNN) in image segmentation as they have a high performance in automatic segmentation of brain tumors images. Due to the gradient diffusion problem and complexity, it generally takes a lot of time and extra computational power for training deeper neural networks. In this paper, we present an automatic technique for brain tumor segmentation depending on Deep Residual Learning Network (ResNet) to get over the gradient problem of DNN. ResNets accomplish more accuracy and can make the training process faster compared to their equivalent DNN. To achieve this enhancement, ResNets add a shortcut skip connection parallel to convolutional neural networks layers. Simulation examples have been carried out on dataset BRATS 2015 to verify the superiority of the proposed technique. Results verify that the proposed technique has an improved accuracy of 83%, 90%, and 85% for the complete, core, and enhancing regions, respectively. Moreover, it has an average computation time (3 times) faster than other DNN techniques. |
| first_indexed | 2024-12-13T19:22:23Z |
| format | Article |
| id | doaj.art-c0a132bcea4a4be596c9b0cf069decf1 |
| institution | Directory Open Access Journal |
| issn | 1018-3639 |
| language | English |
| last_indexed | 2024-12-13T19:22:23Z |
| publishDate | 2021-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Engineering Sciences |
| spelling | doaj.art-c0a132bcea4a4be596c9b0cf069decf12022-12-21T23:34:08ZengElsevierJournal of King Saud University: Engineering Sciences1018-36392021-09-01336404412An efficient brain tumor image segmentation based on deep residual networks (ResNets)Lamia H. Shehab0Omar M. Fahmy1Safa M. Gasser2Mohamed S. El-Mahallawy3Department of Electronics and Communications, Arab Academy for Science, Technology and Maritime Transport, Cairo, Egypt; Department of Electrical Engineering, Future University in Egypt, Egypt; Corresponding author at: Department of Electronics and Communications, Arab Academy for Science, Technology and Maritime Transport, Cairo, Egypt.Department of Electrical Engineering, Future University in Egypt, Egypt; Department of Electrical Engineering, South Ural State University, Chelyabinsk, RussiaDepartment of Electronics and Communications, Arab Academy for Science, Technology and Maritime Transport, Cairo, EgyptDepartment of Electronics and Communications, Arab Academy for Science, Technology and Maritime Transport, Cairo, EgyptAutomatic segmentation of brain tumor from Magnetic Resonance Images (MRI) is one of the challenging tasks in computer vision. Many proposals investigate the use of Deep Neural Networks (DNN) in image segmentation as they have a high performance in automatic segmentation of brain tumors images. Due to the gradient diffusion problem and complexity, it generally takes a lot of time and extra computational power for training deeper neural networks. In this paper, we present an automatic technique for brain tumor segmentation depending on Deep Residual Learning Network (ResNet) to get over the gradient problem of DNN. ResNets accomplish more accuracy and can make the training process faster compared to their equivalent DNN. To achieve this enhancement, ResNets add a shortcut skip connection parallel to convolutional neural networks layers. Simulation examples have been carried out on dataset BRATS 2015 to verify the superiority of the proposed technique. Results verify that the proposed technique has an improved accuracy of 83%, 90%, and 85% for the complete, core, and enhancing regions, respectively. Moreover, it has an average computation time (3 times) faster than other DNN techniques.http://www.sciencedirect.com/science/article/pii/S1018363920302506Brain tumor segmentationMagnetic Resonance Imaging (MRI)Deep Neural Networks (DNN)Deep Residual Learning Network (ResNet) |
| spellingShingle | Lamia H. Shehab Omar M. Fahmy Safa M. Gasser Mohamed S. El-Mahallawy An efficient brain tumor image segmentation based on deep residual networks (ResNets) Journal of King Saud University: Engineering Sciences Brain tumor segmentation Magnetic Resonance Imaging (MRI) Deep Neural Networks (DNN) Deep Residual Learning Network (ResNet) |
| title | An efficient brain tumor image segmentation based on deep residual networks (ResNets) |
| title_full | An efficient brain tumor image segmentation based on deep residual networks (ResNets) |
| title_fullStr | An efficient brain tumor image segmentation based on deep residual networks (ResNets) |
| title_full_unstemmed | An efficient brain tumor image segmentation based on deep residual networks (ResNets) |
| title_short | An efficient brain tumor image segmentation based on deep residual networks (ResNets) |
| title_sort | efficient brain tumor image segmentation based on deep residual networks resnets |
| topic | Brain tumor segmentation Magnetic Resonance Imaging (MRI) Deep Neural Networks (DNN) Deep Residual Learning Network (ResNet) |
| url | http://www.sciencedirect.com/science/article/pii/S1018363920302506 |
| work_keys_str_mv | AT lamiahshehab anefficientbraintumorimagesegmentationbasedondeepresidualnetworksresnets AT omarmfahmy anefficientbraintumorimagesegmentationbasedondeepresidualnetworksresnets AT safamgasser anefficientbraintumorimagesegmentationbasedondeepresidualnetworksresnets AT mohamedselmahallawy anefficientbraintumorimagesegmentationbasedondeepresidualnetworksresnets AT lamiahshehab efficientbraintumorimagesegmentationbasedondeepresidualnetworksresnets AT omarmfahmy efficientbraintumorimagesegmentationbasedondeepresidualnetworksresnets AT safamgasser efficientbraintumorimagesegmentationbasedondeepresidualnetworksresnets AT mohamedselmahallawy efficientbraintumorimagesegmentationbasedondeepresidualnetworksresnets |