A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validation
Abstract Background Artificial intelligence (AI) algorithms are capable of automatically detecting contouring boundaries in medical images. However, the algorithms impact on clinical practice of cervical cancer are unclear. We aimed to develop an AI-assisted system for automatic contouring of the cl...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-11-01
|
| Series: | Radiation Oncology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13014-022-02157-5 |
| _version_ | 1811217808900489216 |
|---|---|
| author | Shihong Nie Yuanfeng Wei Fen Zhao Ya Dong Yan Chen Qiaoqi Li Wei Du Xin Li Xi Yang Zhiping Li |
| author_facet | Shihong Nie Yuanfeng Wei Fen Zhao Ya Dong Yan Chen Qiaoqi Li Wei Du Xin Li Xi Yang Zhiping Li |
| author_sort | Shihong Nie |
| collection | DOAJ |
| description | Abstract Background Artificial intelligence (AI) algorithms are capable of automatically detecting contouring boundaries in medical images. However, the algorithms impact on clinical practice of cervical cancer are unclear. We aimed to develop an AI-assisted system for automatic contouring of the clinical target volume (CTV) and organs-at-risk (OARs) in cervical cancer radiotherapy and conduct clinical-based observations. Methods We first retrospectively collected data of 203 patients with cervical cancer from West China Hospital. The proposed method named as SegNet was developed and trained with different data groups. Quantitative metrics and clinical-based grading were used to evaluate differences between several groups of automatic contours. Then, 20 additional cases were conducted to compare the workload and quality of AI-assisted contours with manual delineation from scratch. Results For automatic CTVs, the dice similarity coefficient (DSC) values of the SegNet trained with incorporating multi-group data achieved 0.85 ± 0.02, which was statistically better than the DSC values of SegNet independently trained with the SegNet(A) (0.82 ± 0.04), SegNet(B) (0.82 ± 0.03) or SegNet(C) (0.81 ± 0.04). Moreover, the DSC values of the SegNet and UNet, respectively, 0.85 and 0.82 for the CTV (P < 0.001), 0.93 and 0.92 for the bladder (P = 0.44), 0.84 and 0.81 for the rectum (P = 0.02), 0.89 and 0.84 for the bowel bag (P < 0.001), 0.93 and 0.92 for the right femoral head (P = 0.17), and 0.92 and 0.91 for the left femoral head (P = 0.25). The clinical-based grading also showed that SegNet trained with multi-group data obtained better performance of 352/360 relative to it trained with the SegNet(A) (334/360), SegNet(B) (333/360) or SegNet(C) (320/360). The manual revision time for automatic CTVs (OARs not yet include) was 9.54 ± 2.42 min relative to fully manual delineation with 30.95 ± 15.24 min. Conclusion The proposed SegNet can improve the performance at automatic delineation for cervical cancer radiotherapy by incorporating multi-group data. It is clinically applicable that the AI-assisted system can shorten manual delineation time at no expense of quality. |
| first_indexed | 2024-04-12T07:00:22Z |
| format | Article |
| id | doaj.art-59f6058b6a9643e6adbd447176ada043 |
| institution | Directory Open Access Journal |
| issn | 1748-717X |
| language | English |
| last_indexed | 2024-04-12T07:00:22Z |
| publishDate | 2022-11-01 |
| publisher | BMC |
| record_format | Article |
| series | Radiation Oncology |
| spelling | doaj.art-59f6058b6a9643e6adbd447176ada0432022-12-22T03:43:01ZengBMCRadiation Oncology1748-717X2022-11-011711910.1186/s13014-022-02157-5A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validationShihong Nie0Yuanfeng Wei1Fen Zhao2Ya Dong3Yan Chen4Qiaoqi Li5Wei Du6Xin Li7Xi Yang8Zhiping Li9Department of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityDepartment of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityDepartment of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityDepartment of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityDepartment of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityDepartment of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityDepartment of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityDepartment of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityDepartment of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityDepartment of Radiotherapy, Cancer Center, West China Hospital, Sichuan UniversityAbstract Background Artificial intelligence (AI) algorithms are capable of automatically detecting contouring boundaries in medical images. However, the algorithms impact on clinical practice of cervical cancer are unclear. We aimed to develop an AI-assisted system for automatic contouring of the clinical target volume (CTV) and organs-at-risk (OARs) in cervical cancer radiotherapy and conduct clinical-based observations. Methods We first retrospectively collected data of 203 patients with cervical cancer from West China Hospital. The proposed method named as SegNet was developed and trained with different data groups. Quantitative metrics and clinical-based grading were used to evaluate differences between several groups of automatic contours. Then, 20 additional cases were conducted to compare the workload and quality of AI-assisted contours with manual delineation from scratch. Results For automatic CTVs, the dice similarity coefficient (DSC) values of the SegNet trained with incorporating multi-group data achieved 0.85 ± 0.02, which was statistically better than the DSC values of SegNet independently trained with the SegNet(A) (0.82 ± 0.04), SegNet(B) (0.82 ± 0.03) or SegNet(C) (0.81 ± 0.04). Moreover, the DSC values of the SegNet and UNet, respectively, 0.85 and 0.82 for the CTV (P < 0.001), 0.93 and 0.92 for the bladder (P = 0.44), 0.84 and 0.81 for the rectum (P = 0.02), 0.89 and 0.84 for the bowel bag (P < 0.001), 0.93 and 0.92 for the right femoral head (P = 0.17), and 0.92 and 0.91 for the left femoral head (P = 0.25). The clinical-based grading also showed that SegNet trained with multi-group data obtained better performance of 352/360 relative to it trained with the SegNet(A) (334/360), SegNet(B) (333/360) or SegNet(C) (320/360). The manual revision time for automatic CTVs (OARs not yet include) was 9.54 ± 2.42 min relative to fully manual delineation with 30.95 ± 15.24 min. Conclusion The proposed SegNet can improve the performance at automatic delineation for cervical cancer radiotherapy by incorporating multi-group data. It is clinically applicable that the AI-assisted system can shorten manual delineation time at no expense of quality.https://doi.org/10.1186/s13014-022-02157-5Cervical cancer radiotherapyClinical target volume auto-segmentationOrgans-at-risk auto-segmentationArtificial intelligence-assisted system |
| spellingShingle | Shihong Nie Yuanfeng Wei Fen Zhao Ya Dong Yan Chen Qiaoqi Li Wei Du Xin Li Xi Yang Zhiping Li A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validation Radiation Oncology Cervical cancer radiotherapy Clinical target volume auto-segmentation Organs-at-risk auto-segmentation Artificial intelligence-assisted system |
| title | A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validation |
| title_full | A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validation |
| title_fullStr | A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validation |
| title_full_unstemmed | A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validation |
| title_short | A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validation |
| title_sort | dual deep neural network for auto delineation in cervical cancer radiotherapy with clinical validation |
| topic | Cervical cancer radiotherapy Clinical target volume auto-segmentation Organs-at-risk auto-segmentation Artificial intelligence-assisted system |
| url | https://doi.org/10.1186/s13014-022-02157-5 |
| work_keys_str_mv | AT shihongnie adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT yuanfengwei adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT fenzhao adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT yadong adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT yanchen adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT qiaoqili adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT weidu adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT xinli adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT xiyang adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT zhipingli adualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT shihongnie dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT yuanfengwei dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT fenzhao dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT yadong dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT yanchen dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT qiaoqili dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT weidu dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT xinli dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT xiyang dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation AT zhipingli dualdeepneuralnetworkforautodelineationincervicalcancerradiotherapywithclinicalvalidation |