Chen Zi-Hang, Li Song-Feng, Xu Ling-Xin, Tian Meng-Qiu, Li Feng, Yang Yu-Xian, Wu Chen-Fei, Zhou Guan-Qun, Lin Li, Lu Yao, Sun Ying
Department of Radiation Oncology, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, 510060, P. R. China.
Perception Vision Medical Technologies Co., Ltd., Guangzhou, P. R. China.
BMC Med Inform Decis Mak. 2025 Jul 15;25(1):268. doi: 10.1186/s12911-025-03062-z.
Accurate delineation of organs at risk (OARs) is crucial for precision radiotherapy. Most previous autosegmentation models were only constructed for single anatomical region without evaluation of dosimetric impact. We aimed to validate the clinical practicability of deep-learning (DL) models for autosegmentation of whole-body OARs with respect to delineation accuracy, clinical acceptance and dosimetric impact.
OARs in various anatomical regions, including the head and neck, thorax, abdomen, and pelvis, were automatedly delineated by DL models (DLD) and compared to manual delineations (MD) by an experienced radiation oncologist (RO). The geometric performance was evaluated using the Dice similarity coefficient (DSC) and average surface distance (ASD). RO A corrected DLD to create delineations approved in clinical practice (CPD). RO B graded the accuracy of DLD to assess clinical acceptance. The dosimetric impact was determined by assessing the difference in dosimetric parameters for each OAR in the DLD-based radiotherapy plan (Plan_DLD) and the CPD-based radiotherapy plan (Plan_CPD).
The automatic delineation model has a high OAR delineation accuracy, and the median DSCs can reach 0.841 (IQR, 0.791-0.867) in the head and neck OAR, 0.903 (IQR, 0.777-0.932) in thoracic OAR, 0.847 (IQR, 0.834-0.931) in abdominal OAR, 0.916 (IQR, 0.906-0.964) in pelvic OAR. The majority of DL-generated OARs were graded as clinically acceptable with no editing or little editing needed. No significant differences in dosimetric parameters were found by comparing Plan_DLD with Plan_CPD.
For OARs of whole bodily regions, DL-based segmentation is fast; DL models perform sufficiently well for clinical practice with respect to delineation accuracy, clinical accepatance and dosimetric impact.
精确勾画危及器官（OARs）对于精确放疗至关重要。以往大多数自动分割模型仅针对单一解剖区域构建，未评估剂量学影响。我们旨在验证深度学习（DL）模型在全身OARs自动分割方面在勾画准确性、临床可接受性和剂量学影响方面的临床实用性。
通过DL模型（DLD）自动勾画包括头颈部、胸部、腹部和骨盆在内的不同解剖区域的OARs，并与经验丰富的放射肿瘤学家（RO）的手动勾画（MD）进行比较。使用骰子相似系数（DSC）和平均表面距离（ASD）评估几何性能。放射肿瘤学家A对DLD进行校正以创建临床实践中认可的勾画（CPD）。放射肿瘤学家B对DLD的准确性进行分级以评估临床可接受性。通过评估基于DLD的放疗计划（Plan_DLD）和基于CPD的放疗计划（Plan_CPD）中每个OAR的剂量学参数差异来确定剂量学影响。
自动勾画模型具有较高的OAR勾画准确性，头颈部OAR的DSC中位数可达0.841（IQR，0.791 - 0.867），胸部OAR为0.903（IQR，0.777 - 0.932），腹部OAR为0.847（IQR，0.834 - 0.931），盆腔OAR为0.916（IQR，0.906 - 0.964）。大多数由DL生成的OARs被评为临床可接受，无需编辑或只需少量编辑。比较Plan_DLD和Plan_CPD时，未发现剂量学参数有显著差异。
对于全身各区域的OARs，基于DL的分割速度快；DL模型在勾画准确性、临床可接受性和剂量学影响方面在临床实践中表现良好。
