Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging
Aim: Brain tumors are among the most fatal cancers worldwide. Diagnosing and manually segmenting tumors are time-consuming clinical tasks, and success strongly depends on the doctor's experience. Automatic quantitative analysis and accurate segmentation of brain tumors are greatly needed for ca...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-04-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2019.00285/full |
| _version_ | 1830481576588214272 |
|---|---|
| author | Liansheng Wang Liansheng Wang Shuxin Wang Rongzhen Chen Xiaobo Qu Yiping Chen Yiping Chen Shaohui Huang Changhua Liu |
| author_facet | Liansheng Wang Liansheng Wang Shuxin Wang Rongzhen Chen Xiaobo Qu Yiping Chen Yiping Chen Shaohui Huang Changhua Liu |
| author_sort | Liansheng Wang |
| collection | DOAJ |
| description | Aim: Brain tumors are among the most fatal cancers worldwide. Diagnosing and manually segmenting tumors are time-consuming clinical tasks, and success strongly depends on the doctor's experience. Automatic quantitative analysis and accurate segmentation of brain tumors are greatly needed for cancer diagnosis.Methods:This paper presents an advanced three-dimensional multimodal segmentation algorithm called nested dilation networks (NDNs). It is inspired by the U-Net architecture, a convolutional neural network (CNN) developed for biomedical image segmentation and is modified to achieve better performance for brain tumor segmentation. Thus, we propose residual blocks nested with dilations (RnD) in the encoding part to enrich the low-level features and use squeeze-and-excitation (SE) blocks in both the encoding and decoding parts to boost significant features. To prove the reliability of the network structure, we compare our results with those of the standard U-Net and its transmutation networks. Different loss functions are considered to cope with class imbalance problems to maximize the brain tumor segmentation results. A cascade training strategy is employed to run NDNs for coarse-to-fine tumor segmentation. This strategy decomposes the multiclass segmentation problem into three binary segmentation problems and trains each task sequentially. Various augmentation techniques are utilized to increase the diversity of the data to avoid overfitting.Results: This approach achieves Dice similarity scores of 0.6652, 0.5880, and 0.6682 for edema, non-enhancing tumors, and enhancing tumors, respectively, in which the Dice loss is used for single-pass training. After cascade training, the Dice similarity scores rise to 0.7043, 0.5889, and 0.7206, respectively.Conclusion: Experiments show that the proposed deep learning algorithm outperforms other U-Net transmutation networks for brain tumor segmentation. Moreover, applying cascade training to NDNs facilitates better performance than other methods. The findings of this study provide considerable insight into the automatic and accurate segmentation of brain tumors. |
| first_indexed | 2024-12-21T17:21:35Z |
| format | Article |
| id | doaj.art-744faf8d920c4deb91fbe5e83fc3669a |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-21T17:21:35Z |
| publishDate | 2019-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-744faf8d920c4deb91fbe5e83fc3669a2022-12-21T18:56:09ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2019-04-011310.3389/fnins.2019.00285448471Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance ImagingLiansheng Wang0Liansheng Wang1Shuxin Wang2Rongzhen Chen3Xiaobo Qu4Yiping Chen5Yiping Chen6Shaohui Huang7Changhua Liu8Fujian Key Laboratory of Sensing and Computing for Smart City, School of Information Science and Engineering, Xiamen University, Xiamen, ChinaDepartment of Computer Science, School of Information Science and Engineering, Xiamen University, Xiamen, ChinaDepartment of Computer Science, School of Information Science and Engineering, Xiamen University, Xiamen, ChinaDepartment of Computer Science, School of Information Science and Engineering, Xiamen University, Xiamen, ChinaDepartment of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, School of Electronic Science and Engineering (National Model Microelectronics College), Xiamen University, Xiamen, ChinaFujian Key Laboratory of Sensing and Computing for Smart City, School of Information Science and Engineering, Xiamen University, Xiamen, ChinaDepartment of Computer Science, School of Information Science and Engineering, Xiamen University, Xiamen, ChinaDepartment of Computer Science, School of Information Science and Engineering, Xiamen University, Xiamen, ChinaDepartment of Medical Imaging, Chenggong Hospital Affiliated to Xiamen University, Xiamen, ChinaAim: Brain tumors are among the most fatal cancers worldwide. Diagnosing and manually segmenting tumors are time-consuming clinical tasks, and success strongly depends on the doctor's experience. Automatic quantitative analysis and accurate segmentation of brain tumors are greatly needed for cancer diagnosis.Methods:This paper presents an advanced three-dimensional multimodal segmentation algorithm called nested dilation networks (NDNs). It is inspired by the U-Net architecture, a convolutional neural network (CNN) developed for biomedical image segmentation and is modified to achieve better performance for brain tumor segmentation. Thus, we propose residual blocks nested with dilations (RnD) in the encoding part to enrich the low-level features and use squeeze-and-excitation (SE) blocks in both the encoding and decoding parts to boost significant features. To prove the reliability of the network structure, we compare our results with those of the standard U-Net and its transmutation networks. Different loss functions are considered to cope with class imbalance problems to maximize the brain tumor segmentation results. A cascade training strategy is employed to run NDNs for coarse-to-fine tumor segmentation. This strategy decomposes the multiclass segmentation problem into three binary segmentation problems and trains each task sequentially. Various augmentation techniques are utilized to increase the diversity of the data to avoid overfitting.Results: This approach achieves Dice similarity scores of 0.6652, 0.5880, and 0.6682 for edema, non-enhancing tumors, and enhancing tumors, respectively, in which the Dice loss is used for single-pass training. After cascade training, the Dice similarity scores rise to 0.7043, 0.5889, and 0.7206, respectively.Conclusion: Experiments show that the proposed deep learning algorithm outperforms other U-Net transmutation networks for brain tumor segmentation. Moreover, applying cascade training to NDNs facilitates better performance than other methods. The findings of this study provide considerable insight into the automatic and accurate segmentation of brain tumors.https://www.frontiersin.org/article/10.3389/fnins.2019.00285/fullbrain tumor segmentationnested dilation networksresidual blocks nested with dilationssqueeze-and-excitation blockscoarse-to-fine |
| spellingShingle | Liansheng Wang Liansheng Wang Shuxin Wang Rongzhen Chen Xiaobo Qu Yiping Chen Yiping Chen Shaohui Huang Changhua Liu Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging Frontiers in Neuroscience brain tumor segmentation nested dilation networks residual blocks nested with dilations squeeze-and-excitation blocks coarse-to-fine |
| title | Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging |
| title_full | Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging |
| title_fullStr | Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging |
| title_full_unstemmed | Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging |
| title_short | Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging |
| title_sort | nested dilation networks for brain tumor segmentation based on magnetic resonance imaging |
| topic | brain tumor segmentation nested dilation networks residual blocks nested with dilations squeeze-and-excitation blocks coarse-to-fine |
| url | https://www.frontiersin.org/article/10.3389/fnins.2019.00285/full |
| work_keys_str_mv | AT lianshengwang nesteddilationnetworksforbraintumorsegmentationbasedonmagneticresonanceimaging AT lianshengwang nesteddilationnetworksforbraintumorsegmentationbasedonmagneticresonanceimaging AT shuxinwang nesteddilationnetworksforbraintumorsegmentationbasedonmagneticresonanceimaging AT rongzhenchen nesteddilationnetworksforbraintumorsegmentationbasedonmagneticresonanceimaging AT xiaoboqu nesteddilationnetworksforbraintumorsegmentationbasedonmagneticresonanceimaging AT yipingchen nesteddilationnetworksforbraintumorsegmentationbasedonmagneticresonanceimaging AT yipingchen nesteddilationnetworksforbraintumorsegmentationbasedonmagneticresonanceimaging AT shaohuihuang nesteddilationnetworksforbraintumorsegmentationbasedonmagneticresonanceimaging AT changhualiu nesteddilationnetworksforbraintumorsegmentationbasedonmagneticresonanceimaging |