DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images
Abstract Segmentation of intracranial aneurysm images acquired using magnetic resonance angiography (MRA) is essential for medical auxiliary treatments, which can effectively prevent subarachnoid hemorrhages. This paper proposes an image segmentation model based on a dense convolutional attention U-...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-03-01
|
| Series: | Visual Computing for Industry, Biomedicine, and Art |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42492-022-00105-4 |
| _version_ | 1819052410464632832 |
|---|---|
| author | Wenwen Yuan Yanjun Peng Yanfei Guo Yande Ren Qianwen Xue |
| author_facet | Wenwen Yuan Yanjun Peng Yanfei Guo Yande Ren Qianwen Xue |
| author_sort | Wenwen Yuan |
| collection | DOAJ |
| description | Abstract Segmentation of intracranial aneurysm images acquired using magnetic resonance angiography (MRA) is essential for medical auxiliary treatments, which can effectively prevent subarachnoid hemorrhages. This paper proposes an image segmentation model based on a dense convolutional attention U-Net, which fuses deep and rich semantic information with shallow-detail information for adaptive and accurate segmentation of MRA-acquired aneurysm images with large size differences. The U-Net model serves as a backbone, combining dense block and convolution block attention module (CBAM). The dense block is composed of a batch normalization layer, an randomly rectified linear unit activation function, and a convolutional layer, for mitigation of vanishing gradients, for multiplexing of aneurysm features, and for improving the network training efficiency. The CBAM is composed of a channel attention module and a spatial attention module, improving the segmentation performance of feature discrimination and enhancing the acquisition of key feature information. Owing to the large variation of aneurysm sizes, multi-scale fusion is performed during up-sampling, for adaptive segmentation of MRA-acquired aneurysm images. The model was tested on the MICCAI 2020 ADAM dataset, and its generalizability was validated on the clinical aneurysm dataset (aneurysm sizes: < 3 mm, 3–7 mm, and > 7 mm) supplied by the Affiliated Hospital of Qingdao University. A good clinical application segmentation performance was demonstrated. |
| first_indexed | 2024-12-21T12:19:24Z |
| format | Article |
| id | doaj.art-732480022d1642db92ffe8d66ca6bf32 |
| institution | Directory Open Access Journal |
| issn | 2524-4442 |
| language | English |
| last_indexed | 2024-12-21T12:19:24Z |
| publishDate | 2022-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Visual Computing for Industry, Biomedicine, and Art |
| spelling | doaj.art-732480022d1642db92ffe8d66ca6bf322022-12-21T19:04:21ZengSpringerOpenVisual Computing for Industry, Biomedicine, and Art2524-44422022-03-015111810.1186/s42492-022-00105-4DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm imagesWenwen Yuan0Yanjun Peng1Yanfei Guo2Yande Ren3Qianwen Xue4College of Computer Science and Engineering, Shandong University of Science and TechnologyCollege of Computer Science and Engineering, Shandong University of Science and TechnologyCollege of Computer Science and Engineering, Shandong University of Science and TechnologyThe Department of Radiology, the Affiliated Hospital of Qingdao UniversityQingdao Maternal & Child Health and Family Planning Service CenterAbstract Segmentation of intracranial aneurysm images acquired using magnetic resonance angiography (MRA) is essential for medical auxiliary treatments, which can effectively prevent subarachnoid hemorrhages. This paper proposes an image segmentation model based on a dense convolutional attention U-Net, which fuses deep and rich semantic information with shallow-detail information for adaptive and accurate segmentation of MRA-acquired aneurysm images with large size differences. The U-Net model serves as a backbone, combining dense block and convolution block attention module (CBAM). The dense block is composed of a batch normalization layer, an randomly rectified linear unit activation function, and a convolutional layer, for mitigation of vanishing gradients, for multiplexing of aneurysm features, and for improving the network training efficiency. The CBAM is composed of a channel attention module and a spatial attention module, improving the segmentation performance of feature discrimination and enhancing the acquisition of key feature information. Owing to the large variation of aneurysm sizes, multi-scale fusion is performed during up-sampling, for adaptive segmentation of MRA-acquired aneurysm images. The model was tested on the MICCAI 2020 ADAM dataset, and its generalizability was validated on the clinical aneurysm dataset (aneurysm sizes: < 3 mm, 3–7 mm, and > 7 mm) supplied by the Affiliated Hospital of Qingdao University. A good clinical application segmentation performance was demonstrated.https://doi.org/10.1186/s42492-022-00105-4Deep learningIntracranial aneurysm segmentationMagnetic resonance angiographyMulti-scale fusion |
| spellingShingle | Wenwen Yuan Yanjun Peng Yanfei Guo Yande Ren Qianwen Xue DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images Visual Computing for Industry, Biomedicine, and Art Deep learning Intracranial aneurysm segmentation Magnetic resonance angiography Multi-scale fusion |
| title | DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images |
| title_full | DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images |
| title_fullStr | DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images |
| title_full_unstemmed | DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images |
| title_short | DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images |
| title_sort | dcau net dense convolutional attention u net for segmentation of intracranial aneurysm images |
| topic | Deep learning Intracranial aneurysm segmentation Magnetic resonance angiography Multi-scale fusion |
| url | https://doi.org/10.1186/s42492-022-00105-4 |
| work_keys_str_mv | AT wenwenyuan dcaunetdenseconvolutionalattentionunetforsegmentationofintracranialaneurysmimages AT yanjunpeng dcaunetdenseconvolutionalattentionunetforsegmentationofintracranialaneurysmimages AT yanfeiguo dcaunetdenseconvolutionalattentionunetforsegmentationofintracranialaneurysmimages AT yanderen dcaunetdenseconvolutionalattentionunetforsegmentationofintracranialaneurysmimages AT qianwenxue dcaunetdenseconvolutionalattentionunetforsegmentationofintracranialaneurysmimages |