Hippocampus segmentation after brain tumor resection via postoperative region synthesis
Abstract Purpose Accurately segmenting the hippocampus is an essential step in brain tumor radiotherapy planning. Some patients undergo brain tumor resection beforehand, which can significantly alter the postoperative regions’ appearances and intensity of the 3D MR images. However, there are limited...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-09-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-023-01087-2 |
| _version_ | 1797451053200834560 |
|---|---|
| author | Changjuan Tao Difei Gu Rui Huang Ling Zhou Zhiqiang Hu Yuanyuan Chen Xiaofan Zhang Hongsheng Li |
| author_facet | Changjuan Tao Difei Gu Rui Huang Ling Zhou Zhiqiang Hu Yuanyuan Chen Xiaofan Zhang Hongsheng Li |
| author_sort | Changjuan Tao |
| collection | DOAJ |
| description | Abstract Purpose Accurately segmenting the hippocampus is an essential step in brain tumor radiotherapy planning. Some patients undergo brain tumor resection beforehand, which can significantly alter the postoperative regions’ appearances and intensity of the 3D MR images. However, there are limited tumor resection patient images for deep neural networks to be effective. Methods We propose a novel automatic hippocampus segmentation framework via postoperative image synthesis. The variational generative adversarial network consists of intensity alignment and a weight-map-guided feature fusion module, which transfers the postoperative regions to the preoperative images. In addition, to further boost the performance of hippocampus segmentation, We design a joint training strategy to optimize the image synthesis network and the segmentation task simultaneously. Results Comprehensive experiments demonstrate that our proposed method on the dataset with 48 nasopharyngeal carcinoma patients and 67 brain tumor patients observes consistent improvements over state-of-the-art methods. Conclusion The proposed postoperative image synthesis method act as a novel and powerful scheme to generate additional training data. Compared with existing deep learning methods, it achieves better accuracy for hippocampus segmentation of brain tumor patients who have undergone brain tumor resection. It can be used as an automatic contouring tool for hippocampus delineation in hippocampus-sparing radiotherapy. |
| first_indexed | 2024-03-09T14:48:23Z |
| format | Article |
| id | doaj.art-77b97e2593a84cfbb20967765eb980e6 |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-03-09T14:48:23Z |
| publishDate | 2023-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-77b97e2593a84cfbb20967765eb980e62023-11-26T14:35:23ZengBMCBMC Medical Imaging1471-23422023-09-0123111310.1186/s12880-023-01087-2Hippocampus segmentation after brain tumor resection via postoperative region synthesisChangjuan Tao0Difei Gu1Rui Huang2Ling Zhou3Zhiqiang Hu4Yuanyuan Chen5Xiaofan Zhang6Hongsheng Li7Department of Radiation Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences,Interactive Intelligence (CPII) LimitedSenseTime ResearchDepartment of Radiation oncology, Dongguan People’s HospitalSenseTime ResearchDepartment of Radiation Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences,Qing Yuan Research Institute, Shanghai Jiao Tong UniversityInteractive Intelligence (CPII) LimitedAbstract Purpose Accurately segmenting the hippocampus is an essential step in brain tumor radiotherapy planning. Some patients undergo brain tumor resection beforehand, which can significantly alter the postoperative regions’ appearances and intensity of the 3D MR images. However, there are limited tumor resection patient images for deep neural networks to be effective. Methods We propose a novel automatic hippocampus segmentation framework via postoperative image synthesis. The variational generative adversarial network consists of intensity alignment and a weight-map-guided feature fusion module, which transfers the postoperative regions to the preoperative images. In addition, to further boost the performance of hippocampus segmentation, We design a joint training strategy to optimize the image synthesis network and the segmentation task simultaneously. Results Comprehensive experiments demonstrate that our proposed method on the dataset with 48 nasopharyngeal carcinoma patients and 67 brain tumor patients observes consistent improvements over state-of-the-art methods. Conclusion The proposed postoperative image synthesis method act as a novel and powerful scheme to generate additional training data. Compared with existing deep learning methods, it achieves better accuracy for hippocampus segmentation of brain tumor patients who have undergone brain tumor resection. It can be used as an automatic contouring tool for hippocampus delineation in hippocampus-sparing radiotherapy.https://doi.org/10.1186/s12880-023-01087-2Automatic hippocampus segmentationPostoperative image synthesisVariational generative adversarial networkRadiotherapy |
| spellingShingle | Changjuan Tao Difei Gu Rui Huang Ling Zhou Zhiqiang Hu Yuanyuan Chen Xiaofan Zhang Hongsheng Li Hippocampus segmentation after brain tumor resection via postoperative region synthesis BMC Medical Imaging Automatic hippocampus segmentation Postoperative image synthesis Variational generative adversarial network Radiotherapy |
| title | Hippocampus segmentation after brain tumor resection via postoperative region synthesis |
| title_full | Hippocampus segmentation after brain tumor resection via postoperative region synthesis |
| title_fullStr | Hippocampus segmentation after brain tumor resection via postoperative region synthesis |
| title_full_unstemmed | Hippocampus segmentation after brain tumor resection via postoperative region synthesis |
| title_short | Hippocampus segmentation after brain tumor resection via postoperative region synthesis |
| title_sort | hippocampus segmentation after brain tumor resection via postoperative region synthesis |
| topic | Automatic hippocampus segmentation Postoperative image synthesis Variational generative adversarial network Radiotherapy |
| url | https://doi.org/10.1186/s12880-023-01087-2 |
| work_keys_str_mv | AT changjuantao hippocampussegmentationafterbraintumorresectionviapostoperativeregionsynthesis AT difeigu hippocampussegmentationafterbraintumorresectionviapostoperativeregionsynthesis AT ruihuang hippocampussegmentationafterbraintumorresectionviapostoperativeregionsynthesis AT lingzhou hippocampussegmentationafterbraintumorresectionviapostoperativeregionsynthesis AT zhiqianghu hippocampussegmentationafterbraintumorresectionviapostoperativeregionsynthesis AT yuanyuanchen hippocampussegmentationafterbraintumorresectionviapostoperativeregionsynthesis AT xiaofanzhang hippocampussegmentationafterbraintumorresectionviapostoperativeregionsynthesis AT hongshengli hippocampussegmentationafterbraintumorresectionviapostoperativeregionsynthesis |