Evaluation of auto-segmentation for EBRT planning structures using deep learning-based workflow on cervical cancer
Abstract Deep learning (DL) based approach aims to construct a full workflow solution for cervical cancer with external beam radiation therapy (EBRT) and brachytherapy (BT). The purpose of this study was to evaluate the accuracy of EBRT planning structures derived from DL based auto-segmentation com...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-18084-0 |
| _version_ | 1818084425798254592 |
|---|---|
| author | Jiahao Wang Yuanyuan Chen Hongling Xie Lumeng Luo Qiu Tang |
| author_facet | Jiahao Wang Yuanyuan Chen Hongling Xie Lumeng Luo Qiu Tang |
| author_sort | Jiahao Wang |
| collection | DOAJ |
| description | Abstract Deep learning (DL) based approach aims to construct a full workflow solution for cervical cancer with external beam radiation therapy (EBRT) and brachytherapy (BT). The purpose of this study was to evaluate the accuracy of EBRT planning structures derived from DL based auto-segmentation compared with standard manual delineation. Auto-segmentation model based on convolutional neural networks (CNN) was developed to delineate clinical target volumes (CTVs) and organs at risk (OARs) in cervical cancer radiotherapy. A total of 300 retrospective patients from multiple cancer centers were used to train and validate the model, and 75 independent cases were selected as testing data. The accuracy of auto-segmented contours were evaluated using geometric and dosimetric metrics including dice similarity coefficient (DSC), 95% hausdorff distance (95%HD), jaccard coefficient (JC) and dose-volume index (DVI). The correlation between geometric metrics and dosimetric difference was performed by Spearman’s correlation analysis. The right and left kidney, bladder, right and left femoral head showed superior geometric accuracy (DSC: 0.88–0.93; 95%HD: 1.03 mm–2.96 mm; JC: 0.78–0.88), and the Bland–Altman test obtained dose agreement for these contours (P > 0.05) between manual and DL based methods. Wilcoxon’s signed-rank test indicated significant dosimetric differences in CTV, spinal cord and pelvic bone (P < 0.001). A strong correlation between the mean dose of pelvic bone and its 95%HD (R = 0.843, P < 0.001) was found in Spearman’s correlation analysis, and the remaining structures showed weak link between dosimetric difference and all of geometric metrics. Our auto-segmentation achieved a satisfied agreement for most EBRT planning structures, although the clinical acceptance of CTV was a concern. DL based auto-segmentation was an essential component in cervical cancer workflow which would generate the accurate contouring. |
| first_indexed | 2024-12-10T19:53:41Z |
| format | Article |
| id | doaj.art-09e415fd8bc744db9b3c68a18efacb8d |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-10T19:53:41Z |
| publishDate | 2022-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-09e415fd8bc744db9b3c68a18efacb8d2022-12-22T01:35:42ZengNature PortfolioScientific Reports2045-23222022-08-0112111210.1038/s41598-022-18084-0Evaluation of auto-segmentation for EBRT planning structures using deep learning-based workflow on cervical cancerJiahao Wang0Yuanyuan Chen1Hongling Xie2Lumeng Luo3Qiu Tang4Department of Radiation Oncology, Women’s Hospital, School of Medicine, Zhejiang UniversityDepartment of Radiation Oncology, Women’s Hospital, School of Medicine, Zhejiang UniversityDepartment of Radiation Oncology, Women’s Hospital, School of Medicine, Zhejiang UniversityDepartment of Radiation Oncology, Women’s Hospital, School of Medicine, Zhejiang UniversityDepartment of Radiation Oncology, Women’s Hospital, School of Medicine, Zhejiang UniversityAbstract Deep learning (DL) based approach aims to construct a full workflow solution for cervical cancer with external beam radiation therapy (EBRT) and brachytherapy (BT). The purpose of this study was to evaluate the accuracy of EBRT planning structures derived from DL based auto-segmentation compared with standard manual delineation. Auto-segmentation model based on convolutional neural networks (CNN) was developed to delineate clinical target volumes (CTVs) and organs at risk (OARs) in cervical cancer radiotherapy. A total of 300 retrospective patients from multiple cancer centers were used to train and validate the model, and 75 independent cases were selected as testing data. The accuracy of auto-segmented contours were evaluated using geometric and dosimetric metrics including dice similarity coefficient (DSC), 95% hausdorff distance (95%HD), jaccard coefficient (JC) and dose-volume index (DVI). The correlation between geometric metrics and dosimetric difference was performed by Spearman’s correlation analysis. The right and left kidney, bladder, right and left femoral head showed superior geometric accuracy (DSC: 0.88–0.93; 95%HD: 1.03 mm–2.96 mm; JC: 0.78–0.88), and the Bland–Altman test obtained dose agreement for these contours (P > 0.05) between manual and DL based methods. Wilcoxon’s signed-rank test indicated significant dosimetric differences in CTV, spinal cord and pelvic bone (P < 0.001). A strong correlation between the mean dose of pelvic bone and its 95%HD (R = 0.843, P < 0.001) was found in Spearman’s correlation analysis, and the remaining structures showed weak link between dosimetric difference and all of geometric metrics. Our auto-segmentation achieved a satisfied agreement for most EBRT planning structures, although the clinical acceptance of CTV was a concern. DL based auto-segmentation was an essential component in cervical cancer workflow which would generate the accurate contouring.https://doi.org/10.1038/s41598-022-18084-0 |
| spellingShingle | Jiahao Wang Yuanyuan Chen Hongling Xie Lumeng Luo Qiu Tang Evaluation of auto-segmentation for EBRT planning structures using deep learning-based workflow on cervical cancer Scientific Reports |
| title | Evaluation of auto-segmentation for EBRT planning structures using deep learning-based workflow on cervical cancer |
| title_full | Evaluation of auto-segmentation for EBRT planning structures using deep learning-based workflow on cervical cancer |
| title_fullStr | Evaluation of auto-segmentation for EBRT planning structures using deep learning-based workflow on cervical cancer |
| title_full_unstemmed | Evaluation of auto-segmentation for EBRT planning structures using deep learning-based workflow on cervical cancer |
| title_short | Evaluation of auto-segmentation for EBRT planning structures using deep learning-based workflow on cervical cancer |
| title_sort | evaluation of auto segmentation for ebrt planning structures using deep learning based workflow on cervical cancer |
| url | https://doi.org/10.1038/s41598-022-18084-0 |
| work_keys_str_mv | AT jiahaowang evaluationofautosegmentationforebrtplanningstructuresusingdeeplearningbasedworkflowoncervicalcancer AT yuanyuanchen evaluationofautosegmentationforebrtplanningstructuresusingdeeplearningbasedworkflowoncervicalcancer AT honglingxie evaluationofautosegmentationforebrtplanningstructuresusingdeeplearningbasedworkflowoncervicalcancer AT lumengluo evaluationofautosegmentationforebrtplanningstructuresusingdeeplearningbasedworkflowoncervicalcancer AT qiutang evaluationofautosegmentationforebrtplanningstructuresusingdeeplearningbasedworkflowoncervicalcancer |