Clinical Validation and Treatment Plan Evaluation Based on Autodelineation of the Clinical Target Volume for Prostate Cancer Radiotherapy
Purpose Clinical target volumes (CTVs) and organs at risk (OARs) could be autocontoured to save workload. This study aimed to assess a convolutional neural network for automatic and accurate CTV and OARs in prostate cancer, while comparing possible treatment plans based on autocontouring CTV to clin...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-03-01
|
| Series: | Technology in Cancer Research & Treatment |
| Online Access: | https://doi.org/10.1177/15330338231164883 |
| _version_ | 1797856166425919488 |
|---|---|
| author | Jing Shen MD Yinjie Tao MD Hui Guan MD Hongnan Zhen MD Lei He PhD Tingting Dong PhD Shaobin Wang PhD Yu Chen PhD Qi Chen PhD Zhikai Liu MD Fuquan Zhang MD |
| author_facet | Jing Shen MD Yinjie Tao MD Hui Guan MD Hongnan Zhen MD Lei He PhD Tingting Dong PhD Shaobin Wang PhD Yu Chen PhD Qi Chen PhD Zhikai Liu MD Fuquan Zhang MD |
| author_sort | Jing Shen MD |
| collection | DOAJ |
| description | Purpose Clinical target volumes (CTVs) and organs at risk (OARs) could be autocontoured to save workload. This study aimed to assess a convolutional neural network for automatic and accurate CTV and OARs in prostate cancer, while comparing possible treatment plans based on autocontouring CTV to clinical treatment plans. Methods Computer tomography (CT) scans of 217 patients with locally advanced prostate cancer treated at our hospital were retrospectively collected and analyzed from January 2013 to January 2019. A deep learning-based method, CUNet, was used to delineate CTV and OARs. A training set of 195 CT scans and a test set of 28 CT scans were randomly chosen from the dataset. The mean Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD), and subjective evaluation were used to evaluate the performance of this strategy. Predetermined evaluation criteria were used to grade treatment plans, and percentage errors for clinical doses to the planned target volume (PTV) and OARs were calculated. Results The mean DSC and 95HD values of the defined CTVs were (0.84 ± 0.05) and (5.04 ± 2.15) mm, respectively. The average delineation time was < 15 s for each patient's CT scan. The overall positive rates for clinicians A and B were 53.15% versus 46.85%, and 54.05% versus 45.95%, respectively ( P > .05) when CTV outlines from CUNet were blindly chosen and compared with the ground truth (GT). Furthermore, 8 test patients were randomly chosen to design the predicted plan based on the autocontouring CTVs and OARs, demonstrating acceptable agreement with the clinical plan: average absolute dose differences in mean value of D2, D50, D98, Dmax, and Dmean for PTV were within 0.74%, and average absolute volume differences in mean value of V45 and V50 for OARs were within 3.4%. Conclusion Our results revealed that the CTVs and OARs for prostate cancer defined by CUNet were close to the GT. CUNet could halve the time spent by radiation oncologists in contouring, demonstrating the potential of the novel autocontouring method. |
| first_indexed | 2024-04-09T20:35:58Z |
| format | Article |
| id | doaj.art-a74483a672984c60a4db8d9ff33b489f |
| institution | Directory Open Access Journal |
| issn | 1533-0338 |
| language | English |
| last_indexed | 2024-04-09T20:35:58Z |
| publishDate | 2023-03-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Technology in Cancer Research & Treatment |
| spelling | doaj.art-a74483a672984c60a4db8d9ff33b489f2023-03-30T10:03:34ZengSAGE PublishingTechnology in Cancer Research & Treatment1533-03382023-03-012210.1177/15330338231164883Clinical Validation and Treatment Plan Evaluation Based on Autodelineation of the Clinical Target Volume for Prostate Cancer RadiotherapyJing Shen MD0Yinjie Tao MD1Hui Guan MD2Hongnan Zhen MD3Lei He PhD4Tingting Dong PhD5Shaobin Wang PhD6Yu Chen PhD7Qi Chen PhD8Zhikai Liu MD9Fuquan Zhang MD10 Department of Radiation Oncology, , Beijing, China Department of Radiation Oncology, , Beijing, China Department of Radiation Oncology, , Beijing, China Department of Radiation Oncology, , Beijing, China Department of Radiation Oncology, , Beijing, China Department of Radiation Oncology, , Beijing, China Radiotherapy Technique Development Department, MedMind Technology Co., Beijing, China Radiotherapy Technique Development Department, MedMind Technology Co., Beijing, China Radiotherapy Technique Development Department, MedMind Technology Co., Beijing, China Department of Radiation Oncology, , Beijing, China Department of Radiation Oncology, , Beijing, ChinaPurpose Clinical target volumes (CTVs) and organs at risk (OARs) could be autocontoured to save workload. This study aimed to assess a convolutional neural network for automatic and accurate CTV and OARs in prostate cancer, while comparing possible treatment plans based on autocontouring CTV to clinical treatment plans. Methods Computer tomography (CT) scans of 217 patients with locally advanced prostate cancer treated at our hospital were retrospectively collected and analyzed from January 2013 to January 2019. A deep learning-based method, CUNet, was used to delineate CTV and OARs. A training set of 195 CT scans and a test set of 28 CT scans were randomly chosen from the dataset. The mean Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD), and subjective evaluation were used to evaluate the performance of this strategy. Predetermined evaluation criteria were used to grade treatment plans, and percentage errors for clinical doses to the planned target volume (PTV) and OARs were calculated. Results The mean DSC and 95HD values of the defined CTVs were (0.84 ± 0.05) and (5.04 ± 2.15) mm, respectively. The average delineation time was < 15 s for each patient's CT scan. The overall positive rates for clinicians A and B were 53.15% versus 46.85%, and 54.05% versus 45.95%, respectively ( P > .05) when CTV outlines from CUNet were blindly chosen and compared with the ground truth (GT). Furthermore, 8 test patients were randomly chosen to design the predicted plan based on the autocontouring CTVs and OARs, demonstrating acceptable agreement with the clinical plan: average absolute dose differences in mean value of D2, D50, D98, Dmax, and Dmean for PTV were within 0.74%, and average absolute volume differences in mean value of V45 and V50 for OARs were within 3.4%. Conclusion Our results revealed that the CTVs and OARs for prostate cancer defined by CUNet were close to the GT. CUNet could halve the time spent by radiation oncologists in contouring, demonstrating the potential of the novel autocontouring method.https://doi.org/10.1177/15330338231164883 |
| spellingShingle | Jing Shen MD Yinjie Tao MD Hui Guan MD Hongnan Zhen MD Lei He PhD Tingting Dong PhD Shaobin Wang PhD Yu Chen PhD Qi Chen PhD Zhikai Liu MD Fuquan Zhang MD Clinical Validation and Treatment Plan Evaluation Based on Autodelineation of the Clinical Target Volume for Prostate Cancer Radiotherapy Technology in Cancer Research & Treatment |
| title | Clinical Validation and Treatment Plan Evaluation Based on Autodelineation of the Clinical Target Volume for Prostate Cancer Radiotherapy |
| title_full | Clinical Validation and Treatment Plan Evaluation Based on Autodelineation of the Clinical Target Volume for Prostate Cancer Radiotherapy |
| title_fullStr | Clinical Validation and Treatment Plan Evaluation Based on Autodelineation of the Clinical Target Volume for Prostate Cancer Radiotherapy |
| title_full_unstemmed | Clinical Validation and Treatment Plan Evaluation Based on Autodelineation of the Clinical Target Volume for Prostate Cancer Radiotherapy |
| title_short | Clinical Validation and Treatment Plan Evaluation Based on Autodelineation of the Clinical Target Volume for Prostate Cancer Radiotherapy |
| title_sort | clinical validation and treatment plan evaluation based on autodelineation of the clinical target volume for prostate cancer radiotherapy |
| url | https://doi.org/10.1177/15330338231164883 |
| work_keys_str_mv | AT jingshenmd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT yinjietaomd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT huiguanmd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT hongnanzhenmd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT leihephd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT tingtingdongphd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT shaobinwangphd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT yuchenphd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT qichenphd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT zhikailiumd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy AT fuquanzhangmd clinicalvalidationandtreatmentplanevaluationbasedonautodelineationoftheclinicaltargetvolumeforprostatecancerradiotherapy |