Multimodal Magnetic Resonance Image Brain Tumor Segmentation Based on ACU-Net Network
Medical image segmentation has the significance of research in digital image processing. It can locate and identify the organ cells, which is essential for clinical analysis, diagnosis, and treatment. Since the high heterogeneity of pathological tissues and the inconspicuous resolution in multimodal...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9328233/ |
| _version_ | 1818639989391491072 |
|---|---|
| author | Ling Tan Wenjie Ma Jingming Xia Sajib Sarker |
| author_facet | Ling Tan Wenjie Ma Jingming Xia Sajib Sarker |
| author_sort | Ling Tan |
| collection | DOAJ |
| description | Medical image segmentation has the significance of research in digital image processing. It can locate and identify the organ cells, which is essential for clinical analysis, diagnosis, and treatment. Since the high heterogeneity of pathological tissues and the inconspicuous resolution in multimodal magnetic resonance images, we propose a multimodal brain tumor image segmentation method based on ACU-Net network. In the beginning, we preprocess brain images to ensure the balanced number of categories. We adopt deep separable convolutional layers to replace the ordinary architecture in the U-Net to distinguish the spatial correlation and appearance correlation of the mapped convolutional channel. We introduce residual skip connection into the ACU-Net to heighten the propagation capacity of features and quicken the convergence speed of the network, to realize the capture of deep abnormal regions. We use the active contour model to against the image noise and edge cracks, come true the tracking of tumor deformation and solve the problem of edge blur in edema area, so as to divide the tumor core and enhanced necrotic parenchymal area exactly in the abnormal area. In this paper,17926 MRI images of 335 patients in the BraTS 2015, BraTS 2018, and BraTS 2019 datasets are used for training and verifying. Our experiments demonstrate that ACU-Net network has better performance than the other segmentation algorithms in subjective vision and objective indicators when applied to brain tumor image segmentation. |
| first_indexed | 2024-12-16T23:04:08Z |
| format | Article |
| id | doaj.art-627e15a923da4cc69b3a69c1d98c8002 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T23:04:08Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-627e15a923da4cc69b3a69c1d98c80022022-12-21T22:12:37ZengIEEEIEEE Access2169-35362021-01-019146081461810.1109/ACCESS.2021.30525149328233Multimodal Magnetic Resonance Image Brain Tumor Segmentation Based on ACU-Net NetworkLing Tan0https://orcid.org/0000-0002-1600-9814Wenjie Ma1https://orcid.org/0000-0001-5172-9588Jingming Xia2Sajib Sarker3School of Computer and Software, Nanjing University of Information Science & Technology, Nanjing, ChinaSchool of Computer and Software, Nanjing University of Information Science & Technology, Nanjing, ChinaSchool of Artificial Intelligence, Nanjing University of Information Science & Technology, Nanjing, ChinaSchool of Computer and Software, Nanjing University of Information Science & Technology, Nanjing, ChinaMedical image segmentation has the significance of research in digital image processing. It can locate and identify the organ cells, which is essential for clinical analysis, diagnosis, and treatment. Since the high heterogeneity of pathological tissues and the inconspicuous resolution in multimodal magnetic resonance images, we propose a multimodal brain tumor image segmentation method based on ACU-Net network. In the beginning, we preprocess brain images to ensure the balanced number of categories. We adopt deep separable convolutional layers to replace the ordinary architecture in the U-Net to distinguish the spatial correlation and appearance correlation of the mapped convolutional channel. We introduce residual skip connection into the ACU-Net to heighten the propagation capacity of features and quicken the convergence speed of the network, to realize the capture of deep abnormal regions. We use the active contour model to against the image noise and edge cracks, come true the tracking of tumor deformation and solve the problem of edge blur in edema area, so as to divide the tumor core and enhanced necrotic parenchymal area exactly in the abnormal area. In this paper,17926 MRI images of 335 patients in the BraTS 2015, BraTS 2018, and BraTS 2019 datasets are used for training and verifying. Our experiments demonstrate that ACU-Net network has better performance than the other segmentation algorithms in subjective vision and objective indicators when applied to brain tumor image segmentation.https://ieeexplore.ieee.org/document/9328233/Brain tumor segmentationU-Netdense residual blockactive contour model |
| spellingShingle | Ling Tan Wenjie Ma Jingming Xia Sajib Sarker Multimodal Magnetic Resonance Image Brain Tumor Segmentation Based on ACU-Net Network IEEE Access Brain tumor segmentation U-Net dense residual block active contour model |
| title | Multimodal Magnetic Resonance Image Brain Tumor Segmentation Based on ACU-Net Network |
| title_full | Multimodal Magnetic Resonance Image Brain Tumor Segmentation Based on ACU-Net Network |
| title_fullStr | Multimodal Magnetic Resonance Image Brain Tumor Segmentation Based on ACU-Net Network |
| title_full_unstemmed | Multimodal Magnetic Resonance Image Brain Tumor Segmentation Based on ACU-Net Network |
| title_short | Multimodal Magnetic Resonance Image Brain Tumor Segmentation Based on ACU-Net Network |
| title_sort | multimodal magnetic resonance image brain tumor segmentation based on acu net network |
| topic | Brain tumor segmentation U-Net dense residual block active contour model |
| url | https://ieeexplore.ieee.org/document/9328233/ |
| work_keys_str_mv | AT lingtan multimodalmagneticresonanceimagebraintumorsegmentationbasedonacunetnetwork AT wenjiema multimodalmagneticresonanceimagebraintumorsegmentationbasedonacunetnetwork AT jingmingxia multimodalmagneticresonanceimagebraintumorsegmentationbasedonacunetnetwork AT sajibsarker multimodalmagneticresonanceimagebraintumorsegmentationbasedonacunetnetwork |