3D U-Net for Skull Stripping in Brain MRI
Skull stripping in brain magnetic resonance imaging (MRI) is an essential step to analyze images of the brain. Although manual segmentation has the highest accuracy, it is a time-consuming task. Therefore, various automatic segmentation algorithms of the brain in MRI have been devised and proposed p...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/3/569 |
| _version_ | 1818013966944698368 |
|---|---|
| author | Hyunho Hwang Hafiz Zia Ur Rehman Sungon Lee |
| author_facet | Hyunho Hwang Hafiz Zia Ur Rehman Sungon Lee |
| author_sort | Hyunho Hwang |
| collection | DOAJ |
| description | Skull stripping in brain magnetic resonance imaging (MRI) is an essential step to analyze images of the brain. Although manual segmentation has the highest accuracy, it is a time-consuming task. Therefore, various automatic segmentation algorithms of the brain in MRI have been devised and proposed previously. However, there is still no method that solves the entire brain extraction problem satisfactorily for diverse datasets in a generic and robust way. To address these shortcomings of existing methods, we propose the use of a 3D-UNet for skull stripping in brain MRI. The 3D-UNet was recently proposed and has been widely used for volumetric segmentation in medical images due to its outstanding performance. It is an extended version of the previously proposed 2D-UNet, which is based on a deep learning network, specifically, the convolutional neural network. We evaluated 3D-UNet skull-stripping using a publicly available brain MRI dataset and compared the results with three existing methods (BSE, ROBEX, and Kleesiek’s method; BSE and ROBEX are two conventional methods, and Kleesiek’s method is based on deep learning). The 3D-UNet outperforms two typical methods and shows comparable results with the specific deep learning-based algorithm, exhibiting a mean Dice coefficient of 0.9903, a sensitivity of 0.9853, and a specificity of 0.9953. |
| first_indexed | 2024-04-14T06:40:45Z |
| format | Article |
| id | doaj.art-06a434406d1041f298543c545bf747b8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-14T06:40:45Z |
| publishDate | 2019-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-06a434406d1041f298543c545bf747b82022-12-22T02:07:21ZengMDPI AGApplied Sciences2076-34172019-02-019356910.3390/app9030569app90305693D U-Net for Skull Stripping in Brain MRIHyunho Hwang0Hafiz Zia Ur Rehman1Sungon Lee2Department of Electrical and Electronics Engineering, Hanyang University, Ansan 15588, KoreaDepartment of Mechatronics Engineering, Hanyang University, Ansan 15588, KoreaSchool of Electrical Engineering, Hanyang University, Ansan 15588, KoreaSkull stripping in brain magnetic resonance imaging (MRI) is an essential step to analyze images of the brain. Although manual segmentation has the highest accuracy, it is a time-consuming task. Therefore, various automatic segmentation algorithms of the brain in MRI have been devised and proposed previously. However, there is still no method that solves the entire brain extraction problem satisfactorily for diverse datasets in a generic and robust way. To address these shortcomings of existing methods, we propose the use of a 3D-UNet for skull stripping in brain MRI. The 3D-UNet was recently proposed and has been widely used for volumetric segmentation in medical images due to its outstanding performance. It is an extended version of the previously proposed 2D-UNet, which is based on a deep learning network, specifically, the convolutional neural network. We evaluated 3D-UNet skull-stripping using a publicly available brain MRI dataset and compared the results with three existing methods (BSE, ROBEX, and Kleesiek’s method; BSE and ROBEX are two conventional methods, and Kleesiek’s method is based on deep learning). The 3D-UNet outperforms two typical methods and shows comparable results with the specific deep learning-based algorithm, exhibiting a mean Dice coefficient of 0.9903, a sensitivity of 0.9853, and a specificity of 0.9953.https://www.mdpi.com/2076-3417/9/3/569skull strippingbrian segmentationbrain extractiondeep convolutional neural networksU-Net |
| spellingShingle | Hyunho Hwang Hafiz Zia Ur Rehman Sungon Lee 3D U-Net for Skull Stripping in Brain MRI Applied Sciences skull stripping brian segmentation brain extraction deep convolutional neural networks U-Net |
| title | 3D U-Net for Skull Stripping in Brain MRI |
| title_full | 3D U-Net for Skull Stripping in Brain MRI |
| title_fullStr | 3D U-Net for Skull Stripping in Brain MRI |
| title_full_unstemmed | 3D U-Net for Skull Stripping in Brain MRI |
| title_short | 3D U-Net for Skull Stripping in Brain MRI |
| title_sort | 3d u net for skull stripping in brain mri |
| topic | skull stripping brian segmentation brain extraction deep convolutional neural networks U-Net |
| url | https://www.mdpi.com/2076-3417/9/3/569 |
| work_keys_str_mv | AT hyunhohwang 3dunetforskullstrippinginbrainmri AT hafizziaurrehman 3dunetforskullstrippinginbrainmri AT sungonlee 3dunetforskullstrippinginbrainmri |