Fusion of Multi-Size Candidate Regions Enhances Two-Stage Hippocampus Segmentation
The hippocampus plays an important role in the memory and cognition abilities of humans. Precise three-dimensional (3D) segmentation of the hippocampus from magnetic resonance imaging scans is of great importance in the diagnosis of neurological diseases. Conventional automatic segmentation methods...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9051819/ |
| _version_ | 1830351354723303424 |
|---|---|
| author | Ping Cao Qiuyang Sheng Siqi Fang Xinyi Li Gangmin Ning Qing Pan |
| author_facet | Ping Cao Qiuyang Sheng Siqi Fang Xinyi Li Gangmin Ning Qing Pan |
| author_sort | Ping Cao |
| collection | DOAJ |
| description | The hippocampus plays an important role in the memory and cognition abilities of humans. Precise three-dimensional (3D) segmentation of the hippocampus from magnetic resonance imaging scans is of great importance in the diagnosis of neurological diseases. Conventional automatic segmentation methods poorly achieve satisfactory performance because of the irregular shape and small volume of the hippocampus. We propose a novel two-stage segmentation method, which includes a localization stage and a segmentation stage, to handle the task of the 3D segmentation of the hippocampus. In the localization stage, a novel strategy for localizing multi-size candidate regions was developed to improve the sample balance for the 3D segmentation task. In the segmentation stage, a method which fuses the multi-size candidate regions was proposed to improve the accuracy in predicting the hippocampal boundary, after which we aggregated the segmentation results from three orthogonal views to further improve the performance. Quantitative evaluation was performed on the Alzheimer's Disease Neuroimaging Initiative dataset. The experimental results achieved Dice similarity coefficients of 92.48 ± 0.61% and 92.90 ± 0.51% for the left and right hippocampus, respectively, outperforming state-of-the-art studies in hippocampus segmentation tasks. |
| first_indexed | 2024-12-20T00:36:30Z |
| format | Article |
| id | doaj.art-346a15dff8a04f26977d6cbd6b24a1c4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T00:36:30Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-346a15dff8a04f26977d6cbd6b24a1c42022-12-21T19:59:44ZengIEEEIEEE Access2169-35362020-01-018632256323810.1109/ACCESS.2020.29846619051819Fusion of Multi-Size Candidate Regions Enhances Two-Stage Hippocampus SegmentationPing Cao0https://orcid.org/0000-0002-7981-6517Qiuyang Sheng1https://orcid.org/0000-0002-4140-9094Siqi Fang2https://orcid.org/0000-0002-7979-5170Xinyi Li3https://orcid.org/0000-0003-0580-6874Gangmin Ning4https://orcid.org/0000-0001-9107-5785Qing Pan5https://orcid.org/0000-0001-7145-6011Zhijiang College, Zhejiang University of Technology, Shaoxing, ChinaCollege of Information Engineering, Zhejiang University of Technology, Hangzhou, ChinaDepartment of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, CB3 OWA, U.KCollege of Information Engineering, Zhejiang University of Technology, Hangzhou, ChinaDepartment of Biomedical Engineering, Zhejiang University, Hangzhou, ChinaCollege of Information Engineering, Zhejiang University of Technology, Hangzhou, ChinaThe hippocampus plays an important role in the memory and cognition abilities of humans. Precise three-dimensional (3D) segmentation of the hippocampus from magnetic resonance imaging scans is of great importance in the diagnosis of neurological diseases. Conventional automatic segmentation methods poorly achieve satisfactory performance because of the irregular shape and small volume of the hippocampus. We propose a novel two-stage segmentation method, which includes a localization stage and a segmentation stage, to handle the task of the 3D segmentation of the hippocampus. In the localization stage, a novel strategy for localizing multi-size candidate regions was developed to improve the sample balance for the 3D segmentation task. In the segmentation stage, a method which fuses the multi-size candidate regions was proposed to improve the accuracy in predicting the hippocampal boundary, after which we aggregated the segmentation results from three orthogonal views to further improve the performance. Quantitative evaluation was performed on the Alzheimer's Disease Neuroimaging Initiative dataset. The experimental results achieved Dice similarity coefficients of 92.48 ± 0.61% and 92.90 ± 0.51% for the left and right hippocampus, respectively, outperforming state-of-the-art studies in hippocampus segmentation tasks.https://ieeexplore.ieee.org/document/9051819/Hippocampus segmentationhippocampus localizationfully convolutional networktwo-stage segmentation |
| spellingShingle | Ping Cao Qiuyang Sheng Siqi Fang Xinyi Li Gangmin Ning Qing Pan Fusion of Multi-Size Candidate Regions Enhances Two-Stage Hippocampus Segmentation IEEE Access Hippocampus segmentation hippocampus localization fully convolutional network two-stage segmentation |
| title | Fusion of Multi-Size Candidate Regions Enhances Two-Stage Hippocampus Segmentation |
| title_full | Fusion of Multi-Size Candidate Regions Enhances Two-Stage Hippocampus Segmentation |
| title_fullStr | Fusion of Multi-Size Candidate Regions Enhances Two-Stage Hippocampus Segmentation |
| title_full_unstemmed | Fusion of Multi-Size Candidate Regions Enhances Two-Stage Hippocampus Segmentation |
| title_short | Fusion of Multi-Size Candidate Regions Enhances Two-Stage Hippocampus Segmentation |
| title_sort | fusion of multi size candidate regions enhances two stage hippocampus segmentation |
| topic | Hippocampus segmentation hippocampus localization fully convolutional network two-stage segmentation |
| url | https://ieeexplore.ieee.org/document/9051819/ |
| work_keys_str_mv | AT pingcao fusionofmultisizecandidateregionsenhancestwostagehippocampussegmentation AT qiuyangsheng fusionofmultisizecandidateregionsenhancestwostagehippocampussegmentation AT siqifang fusionofmultisizecandidateregionsenhancestwostagehippocampussegmentation AT xinyili fusionofmultisizecandidateregionsenhancestwostagehippocampussegmentation AT gangminning fusionofmultisizecandidateregionsenhancestwostagehippocampussegmentation AT qingpan fusionofmultisizecandidateregionsenhancestwostagehippocampussegmentation |