Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical application
Abstract Radiotherapy has been demonstrated to be one of the most significant treatments for cervical cancer, during which accurate and efficient delineation of target volumes is critical. To alleviate the data demand of deep learning and promote the establishment and promotion of auto-segmentation...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-78424-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850196017359618048 |
|---|---|
| author | Haibo Peng Tao Liu Pengcheng Li Fang Yang Xing Luo Xiaoqing Sun Dong Gao Fengyu Lin Lecheng Jia Ningyue Xu Huigang Tan Xi Wang Tao Ren |
| author_facet | Haibo Peng Tao Liu Pengcheng Li Fang Yang Xing Luo Xiaoqing Sun Dong Gao Fengyu Lin Lecheng Jia Ningyue Xu Huigang Tan Xi Wang Tao Ren |
| author_sort | Haibo Peng |
| collection | DOAJ |
| description | Abstract Radiotherapy has been demonstrated to be one of the most significant treatments for cervical cancer, during which accurate and efficient delineation of target volumes is critical. To alleviate the data demand of deep learning and promote the establishment and promotion of auto-segmentation models in small and medium-sized oncology departments and single centres, we proposed an auto-segmentation algorithm to determine the cervical cancer target volume in small samples based on multi-decoder and semi-supervised learning (MDSSL), and we evaluated the accuracy via an independent test cohort. In this study, we retrospectively collected computed tomography (CT) datasets from 71 pelvic cervical cancer patients, and a 3:4 ratio was used for the training and testing sets. The clinical target volumes (CTVs) of the primary tumour area (CTV1) and pelvic lymph drainage area (CTV2) were delineated. For definitive radiotherapy (dRT), the primary gross target volume (GTVp) was simultaneously delineated. According to the data characteristics for small samples, the MDSSL network structure based on 3D U-Net was established to train the model by combining clinical anatomical information, which was compared with other segmentation methods, including supervised learning (SL) and transfer learning (TL). The dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and average surface distance (ASD) were used to evaluate the segmentation performance. The ability of the segmentation algorithm to improve the efficiency of online adaptive radiation therapy (ART) was assessed via geometric indicators and a subjective evaluation of radiation oncologists (ROs) in prospective clinical applications. Compared with the SL model and TL model, the proposed MDSSL model displayed the best DSC, HD95 and ASD overall, especially for the GTVp of dRT. We calculated the above geometric indicators in the range of the ground truth (head-foot direction). In the test set, the DSC, HD95 and ASD of the MDSSL model were 0.80/5.85 mm/0.95 mm for CTV1 of post-operative radiotherapy (pRT), 0.84/ 4.88 mm/0.73 mm for CTV2 of pRT, 0.84/6.58 mm/0.89 mm for GTVp of dRT, 0.85/5.36 mm/1.35 mm for CTV1 of dRT, and 0.84/4.09 mm/0.73 mm for CTV2 of dRT, respectively. In a prospective clinical study of online ART, the target volume modification time (MTime) was 3–5 min for dRT and 2–4 min for pRT, and the main duration of CTV1 modification was approximately 2 min. The introduction of the MDSSL method successfully improved the accuracy of auto-segmentation for the cervical cancer target volume in small samples, showed good consistency with RO delineation and satisfied clinical requirements. In this prospective online ART study, the application of the segmentation model was demonstrated to be useful for reducing the target volume delineation time and improving the efficiency of the online ART workflow, which can contribute to the development and promotion of cervical cancer online ART. |
| format | Article |
| id | doaj-art-14432ac074454a4ebac3c2fcd455410c |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-14432ac074454a4ebac3c2fcd455410c2025-08-20T02:13:35ZengNature PortfolioScientific Reports2045-23222024-11-0114111210.1038/s41598-024-78424-0Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical applicationHaibo Peng0Tao Liu1Pengcheng Li2Fang Yang3Xing Luo4Xiaoqing Sun5Dong Gao6Fengyu Lin7Lecheng Jia8Ningyue Xu9Huigang Tan10Xi Wang11Tao Ren12Oncology Department, Clinical Medical College, The First Affiliated Hospital of Chengdu Medical CollegeOncology Department, Clinical Medical College, The First Affiliated Hospital of Chengdu Medical CollegeOncology Department, Clinical Medical College, The First Affiliated Hospital of Chengdu Medical CollegeOncology Department, Clinical Medical College, The First Affiliated Hospital of Chengdu Medical CollegeOncology Department, Clinical Medical College, The First Affiliated Hospital of Chengdu Medical CollegeRadiotherapy Laboratory, Shenzhen United Imaging Research Institute of Innovative Medical EquipmentUnited Imaging Central Research Institute Co., LtdRadiotherapy Laboratory, Shenzhen United Imaging Research Institute of Innovative Medical EquipmentRadiotherapy Laboratory, Shenzhen United Imaging Research Institute of Innovative Medical EquipmentOncology Department, Clinical Medical College, The First Affiliated Hospital of Chengdu Medical CollegeOncology Department, Clinical Medical College, The First Affiliated Hospital of Chengdu Medical CollegeDepartment of Ultrasound, The General Hospital of Western Theater CommandOncology Department, Clinical Medical College, The First Affiliated Hospital of Chengdu Medical CollegeAbstract Radiotherapy has been demonstrated to be one of the most significant treatments for cervical cancer, during which accurate and efficient delineation of target volumes is critical. To alleviate the data demand of deep learning and promote the establishment and promotion of auto-segmentation models in small and medium-sized oncology departments and single centres, we proposed an auto-segmentation algorithm to determine the cervical cancer target volume in small samples based on multi-decoder and semi-supervised learning (MDSSL), and we evaluated the accuracy via an independent test cohort. In this study, we retrospectively collected computed tomography (CT) datasets from 71 pelvic cervical cancer patients, and a 3:4 ratio was used for the training and testing sets. The clinical target volumes (CTVs) of the primary tumour area (CTV1) and pelvic lymph drainage area (CTV2) were delineated. For definitive radiotherapy (dRT), the primary gross target volume (GTVp) was simultaneously delineated. According to the data characteristics for small samples, the MDSSL network structure based on 3D U-Net was established to train the model by combining clinical anatomical information, which was compared with other segmentation methods, including supervised learning (SL) and transfer learning (TL). The dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and average surface distance (ASD) were used to evaluate the segmentation performance. The ability of the segmentation algorithm to improve the efficiency of online adaptive radiation therapy (ART) was assessed via geometric indicators and a subjective evaluation of radiation oncologists (ROs) in prospective clinical applications. Compared with the SL model and TL model, the proposed MDSSL model displayed the best DSC, HD95 and ASD overall, especially for the GTVp of dRT. We calculated the above geometric indicators in the range of the ground truth (head-foot direction). In the test set, the DSC, HD95 and ASD of the MDSSL model were 0.80/5.85 mm/0.95 mm for CTV1 of post-operative radiotherapy (pRT), 0.84/ 4.88 mm/0.73 mm for CTV2 of pRT, 0.84/6.58 mm/0.89 mm for GTVp of dRT, 0.85/5.36 mm/1.35 mm for CTV1 of dRT, and 0.84/4.09 mm/0.73 mm for CTV2 of dRT, respectively. In a prospective clinical study of online ART, the target volume modification time (MTime) was 3–5 min for dRT and 2–4 min for pRT, and the main duration of CTV1 modification was approximately 2 min. The introduction of the MDSSL method successfully improved the accuracy of auto-segmentation for the cervical cancer target volume in small samples, showed good consistency with RO delineation and satisfied clinical requirements. In this prospective online ART study, the application of the segmentation model was demonstrated to be useful for reducing the target volume delineation time and improving the efficiency of the online ART workflow, which can contribute to the development and promotion of cervical cancer online ART.https://doi.org/10.1038/s41598-024-78424-0Multi-decoder semi-supervised learningSmall samplesAuto-segmentationCervical cancerOnline adaptive radiation therapy |
| spellingShingle | Haibo Peng Tao Liu Pengcheng Li Fang Yang Xing Luo Xiaoqing Sun Dong Gao Fengyu Lin Lecheng Jia Ningyue Xu Huigang Tan Xi Wang Tao Ren Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical application Scientific Reports Multi-decoder semi-supervised learning Small samples Auto-segmentation Cervical cancer Online adaptive radiation therapy |
| title | Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical application |
| title_full | Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical application |
| title_fullStr | Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical application |
| title_full_unstemmed | Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical application |
| title_short | Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical application |
| title_sort | automatic delineation of cervical cancer target volumes in small samples based on multi decoder and semi supervised learning and clinical application |
| topic | Multi-decoder semi-supervised learning Small samples Auto-segmentation Cervical cancer Online adaptive radiation therapy |
| url | https://doi.org/10.1038/s41598-024-78424-0 |
| work_keys_str_mv | AT haibopeng automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT taoliu automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT pengchengli automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT fangyang automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT xingluo automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT xiaoqingsun automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT donggao automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT fengyulin automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT lechengjia automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT ningyuexu automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT huigangtan automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT xiwang automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication AT taoren automaticdelineationofcervicalcancertargetvolumesinsmallsamplesbasedonmultidecoderandsemisupervisedlearningandclinicalapplication |