An Automatic Segmentation Method of Cerebral Arterial Tree in TOF-MRA Based on DBCNet
Arterial tree region segmentation from medical images of the brain is an early step in the diagnosis and evaluation of many cerebrovascular diseases. Most of the existing region segmentation methods rely on manual assistance. In this paper, we propose an automatic brain arterial tree partitioning me...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Science Press
2023-09-01
|
| Series: | Chinese Journal of Magnetic Resonance |
| Subjects: | |
| Online Access: | http://121.43.60.238/bpxzz/article/2023/1000-4556/1000-4556-40-3-320.shtml |
| _version_ | 1827812194845196288 |
|---|---|
| author | ZHANG Jiajun LU Yucheng BAO Yifang LI Yuxin GENG Chen HU Fuyuan DAI Yakang |
| author_facet | ZHANG Jiajun LU Yucheng BAO Yifang LI Yuxin GENG Chen HU Fuyuan DAI Yakang |
| author_sort | ZHANG Jiajun |
| collection | DOAJ |
| description | Arterial tree region segmentation from medical images of the brain is an early step in the diagnosis and evaluation of many cerebrovascular diseases. Most of the existing region segmentation methods rely on manual assistance. In this paper, we propose an automatic brain arterial tree partitioning method based on a dual branch connected network (DBCNet), which can partition the arterial tree in time of flight-magnetic resonance angiography (TOF-MRA) into six main regions. The branch feature decoupling module and the global and local feature fusion module based on Swin Transformer mechanism were used for DBCNet. The two-step training strategy of localization followed by segmentation was used for training. In this study, 111 cases of TOF-MRA data were used, of which 81 cases as the training set, 20 cases as the validation set, and 10 cases as the test set. The average Dice coefficient of the model on the test set was 74.72% and 95% Haus dorff distance (HD95) was 3.89 mm. Compared with other advanced segmentation networks, the network reported in this paper can segment each major region more accurately with robustness. |
| first_indexed | 2024-03-11T23:15:27Z |
| format | Article |
| id | doaj.art-561e6248b6a945289488f96a3d808f35 |
| institution | Directory Open Access Journal |
| issn | 1000-4556 |
| language | zho |
| last_indexed | 2024-03-11T23:15:27Z |
| publishDate | 2023-09-01 |
| publisher | Science Press |
| record_format | Article |
| series | Chinese Journal of Magnetic Resonance |
| spelling | doaj.art-561e6248b6a945289488f96a3d808f352023-09-21T02:08:18ZzhoScience PressChinese Journal of Magnetic Resonance1000-45562023-09-01400332033110.11938/cjmr20223046An Automatic Segmentation Method of Cerebral Arterial Tree in TOF-MRA Based on DBCNetZHANG Jiajun0LU Yucheng1BAO Yifang2LI Yuxin3GENG Chen4 HU Fuyuan5DAI Yakang6School of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, ChinaDepartment of Radiology, Huashan Hospital, Fudan University, Shanghai 200040, ChinaDepartment of Radiology, Huashan Hospital, Fudan University, Shanghai 200040, ChinaDepartment of Radiology, Huashan Hospital, Fudan University, Shanghai 200040, ChinaSuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163, China ； Jinan Guoke Medical Industry Technology Development Co., Jinan 250000, ChinaSchool of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, ChinaSchool of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China；Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163, ChinaArterial tree region segmentation from medical images of the brain is an early step in the diagnosis and evaluation of many cerebrovascular diseases. Most of the existing region segmentation methods rely on manual assistance. In this paper, we propose an automatic brain arterial tree partitioning method based on a dual branch connected network (DBCNet), which can partition the arterial tree in time of flight-magnetic resonance angiography (TOF-MRA) into six main regions. The branch feature decoupling module and the global and local feature fusion module based on Swin Transformer mechanism were used for DBCNet. The two-step training strategy of localization followed by segmentation was used for training. In this study, 111 cases of TOF-MRA data were used, of which 81 cases as the training set, 20 cases as the validation set, and 10 cases as the test set. The average Dice coefficient of the model on the test set was 74.72% and 95% Haus dorff distance (HD95) was 3.89 mm. Compared with other advanced segmentation networks, the network reported in this paper can segment each major region more accurately with robustness.http://121.43.60.238/bpxzz/article/2023/1000-4556/1000-4556-40-3-320.shtmlcerebral arterial treetime of flight-magnetic resonance angiography (tof-mra)deep learningdual branch connected networkautomatic segmentation |
| spellingShingle | ZHANG Jiajun LU Yucheng BAO Yifang LI Yuxin GENG Chen HU Fuyuan DAI Yakang An Automatic Segmentation Method of Cerebral Arterial Tree in TOF-MRA Based on DBCNet Chinese Journal of Magnetic Resonance cerebral arterial tree time of flight-magnetic resonance angiography (tof-mra) deep learning dual branch connected network automatic segmentation |
| title | An Automatic Segmentation Method of Cerebral Arterial Tree in TOF-MRA Based on DBCNet |
| title_full | An Automatic Segmentation Method of Cerebral Arterial Tree in TOF-MRA Based on DBCNet |
| title_fullStr | An Automatic Segmentation Method of Cerebral Arterial Tree in TOF-MRA Based on DBCNet |
| title_full_unstemmed | An Automatic Segmentation Method of Cerebral Arterial Tree in TOF-MRA Based on DBCNet |
| title_short | An Automatic Segmentation Method of Cerebral Arterial Tree in TOF-MRA Based on DBCNet |
| title_sort | automatic segmentation method of cerebral arterial tree in tof mra based on dbcnet |
| topic | cerebral arterial tree time of flight-magnetic resonance angiography (tof-mra) deep learning dual branch connected network automatic segmentation |
| url | http://121.43.60.238/bpxzz/article/2023/1000-4556/1000-4556-40-3-320.shtml |
| work_keys_str_mv | AT zhangjiajun anautomaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT luyucheng anautomaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT baoyifang anautomaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT liyuxin anautomaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT gengchen anautomaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT hufuyuan anautomaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT daiyakang anautomaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT zhangjiajun automaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT luyucheng automaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT baoyifang automaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT liyuxin automaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT gengchen automaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT hufuyuan automaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet AT daiyakang automaticsegmentationmethodofcerebralarterialtreeintofmrabasedondbcnet |