BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder Network
Efficient segmentation of Magnetic Resonance (MR) brain tumor images is of the utmost value for the diagnosis of tumor region. In recent years, advancement in the field of neural networks has been used to refine the segmentation performance of brain tumor sub-regions. The brain tumor segmentation ha...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/2/169 |
| _version_ | 1797407534712094720 |
|---|---|
| author | Mobeen Ur Rehman SeungBin Cho Jeehong Kim Kil To Chong |
| author_facet | Mobeen Ur Rehman SeungBin Cho Jeehong Kim Kil To Chong |
| author_sort | Mobeen Ur Rehman |
| collection | DOAJ |
| description | Efficient segmentation of Magnetic Resonance (MR) brain tumor images is of the utmost value for the diagnosis of tumor region. In recent years, advancement in the field of neural networks has been used to refine the segmentation performance of brain tumor sub-regions. The brain tumor segmentation has proven to be a complicated task even for neural networks, due to the small-scale tumor regions. These small-scale tumor regions are unable to be identified, the reason being their tiny size and the huge difference between area occupancy by different tumor classes. In previous state-of-the-art neural network models, the biggest problem was that the location information along with spatial details gets lost in deeper layers. To address these problems, we have proposed an encoder–decoder based model named BrainSeg-Net. The Feature Enhancer (FE) block is incorporated into the BrainSeg-Net architecture which extracts the middle-level features from low-level features from the shallow layers and shares them with the dense layers. This feature aggregation helps to achieve better performance of tumor identification. To address the problem associated with imbalance class, we have used a custom-designed loss function. For evaluation of BrainSeg-Net architecture, three benchmark datasets are utilized: BraTS2017, BraTS 2018, and BraTS 2019. Segmentation of Enhancing Core (EC), Whole Tumor (WT), and Tumor Core (TC) is carried out. The proposed architecture have exhibited good improvement when compared with existing baseline and state-of-the-art techniques. The MR brain tumor segmentation by BrainSeg-Net uses enhanced location and spatial features, which performs better than the existing plethora of brain MR image segmentation approaches. |
| first_indexed | 2024-03-09T03:42:55Z |
| format | Article |
| id | doaj.art-e72828ac8b1b4f1d9c0fdfb96e482012 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T03:42:55Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-e72828ac8b1b4f1d9c0fdfb96e4820122023-12-03T14:38:22ZengMDPI AGDiagnostics2075-44182021-01-0111216910.3390/diagnostics11020169BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder NetworkMobeen Ur Rehman0SeungBin Cho1Jeehong Kim2Kil To Chong3Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, KoreaDepartment of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, KoreaDepartment of New & Renewable Energy, VISION College of Jeonju, Jeonju 55069, KoreaDepartment of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, KoreaEfficient segmentation of Magnetic Resonance (MR) brain tumor images is of the utmost value for the diagnosis of tumor region. In recent years, advancement in the field of neural networks has been used to refine the segmentation performance of brain tumor sub-regions. The brain tumor segmentation has proven to be a complicated task even for neural networks, due to the small-scale tumor regions. These small-scale tumor regions are unable to be identified, the reason being their tiny size and the huge difference between area occupancy by different tumor classes. In previous state-of-the-art neural network models, the biggest problem was that the location information along with spatial details gets lost in deeper layers. To address these problems, we have proposed an encoder–decoder based model named BrainSeg-Net. The Feature Enhancer (FE) block is incorporated into the BrainSeg-Net architecture which extracts the middle-level features from low-level features from the shallow layers and shares them with the dense layers. This feature aggregation helps to achieve better performance of tumor identification. To address the problem associated with imbalance class, we have used a custom-designed loss function. For evaluation of BrainSeg-Net architecture, three benchmark datasets are utilized: BraTS2017, BraTS 2018, and BraTS 2019. Segmentation of Enhancing Core (EC), Whole Tumor (WT), and Tumor Core (TC) is carried out. The proposed architecture have exhibited good improvement when compared with existing baseline and state-of-the-art techniques. The MR brain tumor segmentation by BrainSeg-Net uses enhanced location and spatial features, which performs better than the existing plethora of brain MR image segmentation approaches.https://www.mdpi.com/2075-4418/11/2/169medical imagingsemantic segmentationbrain tumordiagnosticsFeature Enhancer (FE)Magnetic Resonance (MR) Images |
| spellingShingle | Mobeen Ur Rehman SeungBin Cho Jeehong Kim Kil To Chong BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder Network Diagnostics medical imaging semantic segmentation brain tumor diagnostics Feature Enhancer (FE) Magnetic Resonance (MR) Images |
| title | BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder Network |
| title_full | BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder Network |
| title_fullStr | BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder Network |
| title_full_unstemmed | BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder Network |
| title_short | BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder–Decoder Network |
| title_sort | brainseg net brain tumor mr image segmentation via enhanced encoder decoder network |
| topic | medical imaging semantic segmentation brain tumor diagnostics Feature Enhancer (FE) Magnetic Resonance (MR) Images |
| url | https://www.mdpi.com/2075-4418/11/2/169 |
| work_keys_str_mv | AT mobeenurrehman brainsegnetbraintumormrimagesegmentationviaenhancedencoderdecodernetwork AT seungbincho brainsegnetbraintumormrimagesegmentationviaenhancedencoderdecodernetwork AT jeehongkim brainsegnetbraintumormrimagesegmentationviaenhancedencoderdecodernetwork AT kiltochong brainsegnetbraintumormrimagesegmentationviaenhancedencoderdecodernetwork |